Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 306 results for author: <span class="mathjax">Li, Q</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/eess" aria-role="search"> Searching in archive <strong>eess</strong>. <a href="/search/?searchtype=author&query=Li%2C+Q">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Li, Q"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Li%2C+Q&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Li, Q"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Li%2C+Q&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=300" class="pagination-link " aria-label="Page 7" aria-current="page">7 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.07085">arXiv:2502.07085</a> <span> [<a href="https://arxiv.org/pdf/2502.07085">pdf</a>, <a href="https://arxiv.org/format/2502.07085">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Real-time Optimization for Wind-to-H2 Driven Critical Infrastructures Based on Active Constraints Identification and Integer Variables Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Goodarzi%2C+M">Mostafa Goodarzi</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qifeng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.07085v1-abstract-short" style="display: inline;"> This paper proposes a concept of wind-to-hydrogen-driven critical infrastructure (W2H-CI) as an engineering solution for decarbonizing the power generation sector where it utilizes wind power to produce hydrogen through electrolysis and combines it with the carbon captured from fossil fuel power plants. First, a convex mathematical model of W2H-CI is developed. Then, an optimization model for opti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07085v1-abstract-full').style.display = 'inline'; document.getElementById('2502.07085v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.07085v1-abstract-full" style="display: none;"> This paper proposes a concept of wind-to-hydrogen-driven critical infrastructure (W2H-CI) as an engineering solution for decarbonizing the power generation sector where it utilizes wind power to produce hydrogen through electrolysis and combines it with the carbon captured from fossil fuel power plants. First, a convex mathematical model of W2H-CI is developed. Then, an optimization model for optimal operation of W2H-CI, which is a large-scale mixed-integer convex program (MICP), is proposed. Moreover, we propose to solve this problem in real-time in order to hedge against the uncertainty of wind power. For this purpose, a novel solution method based on active constraints identification and integer variable prediction is introduced. This method can solve MICP problems very fast since it uses historical optimization data to predict the values of binary variables and a limited number of constraints which most likely contain all active constraints. We validate the effectiveness of the proposed fast solution method using two W2H-CI case studies. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07085v1-abstract-full').style.display = 'none'; document.getElementById('2502.07085v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 6 Figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.01078">arXiv:2502.01078</a> <span> [<a href="https://arxiv.org/pdf/2502.01078">pdf</a>, <a href="https://arxiv.org/ps/2502.01078">ps</a>, <a href="https://arxiv.org/format/2502.01078">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Parallel Coding for Orthogonal Delay-Doppler Division Multiplexing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+J">Jinhong Yuan</a>, <a href="/search/eess?searchtype=author&query=Qiu%2C+M">Min Qiu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.01078v1-abstract-short" style="display: inline;"> This paper proposes a novel parallel coding transmission strategy and an iterative detection and decoding receiver signal processing technique for orthogonal delay-Doppler division multiplexing (ODDM) modulation. Specifically, the proposed approach employs a parallel channel encoding (PCE) scheme that consists of multiple short-length codewords for each delay-Doppler multicarrier (DDMC) symbol. Bu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01078v1-abstract-full').style.display = 'inline'; document.getElementById('2502.01078v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.01078v1-abstract-full" style="display: none;"> This paper proposes a novel parallel coding transmission strategy and an iterative detection and decoding receiver signal processing technique for orthogonal delay-Doppler division multiplexing (ODDM) modulation. Specifically, the proposed approach employs a parallel channel encoding (PCE) scheme that consists of multiple short-length codewords for each delay-Doppler multicarrier (DDMC) symbol. Building upon such a PCE transmission framework, we then introduce an iterative detection and decoding algorithm incorporating a successive decoding feedback (SDF) technique, which enables instant information exchange between the detector and decoder for each DDMC symbol. To characterize the error performance of the proposed scheme, we perform density evolution analysis considering the finite blocklength effects. Our analysis results, coupled with extensive simulations, demonstrate that the proposed PCE scheme with the SDF algorithm not only showcases a better overall performance but also requires much less decoding complexity to implement, compared to the conventional benchmark scheme that relies on a single long channel code for coding the entire ODDM frame. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.01078v1-abstract-full').style.display = 'none'; document.getElementById('2502.01078v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 12 figures, accepted by IEEE Transactions on Communications</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.00700">arXiv:2502.00700</a> <span> [<a href="https://arxiv.org/pdf/2502.00700">pdf</a>, <a href="https://arxiv.org/format/2502.00700">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> S2CFormer: Reorienting Learned Image Compression from Spatial Interaction to Channel Aggregation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yunuo Chen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qian Li</a>, <a href="/search/eess?searchtype=author&query=He%2C+B">Bing He</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+D">Donghui Feng</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ronghua Wu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Q">Qi Wang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+L">Li Song</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+G">Guo Lu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wenjun Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.00700v2-abstract-short" style="display: inline;"> Transformers have achieved significant success in learned image compression (LIC), with Swin Transformers emerging as the mainstream choice for nonlinear transforms. A common belief is that their sophisticated spatial operations contribute most to their efficacy. However, the crucial role of the feed-forward network (FFN) based Channel Aggregation module within the transformer architecture has bee… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00700v2-abstract-full').style.display = 'inline'; document.getElementById('2502.00700v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.00700v2-abstract-full" style="display: none;"> Transformers have achieved significant success in learned image compression (LIC), with Swin Transformers emerging as the mainstream choice for nonlinear transforms. A common belief is that their sophisticated spatial operations contribute most to their efficacy. However, the crucial role of the feed-forward network (FFN) based Channel Aggregation module within the transformer architecture has been largely overlooked, and the over-design of spatial operations leads to a suboptimal trade-off between decoding latency and R-D performance. In this paper, we reevaluate the key factors behind the competence of transformers in LIC. By replacing spatial operations with identity mapping, we are surprised to find that channel operations alone can approach the R-D performance of the leading methods. This solid lower bound of performance emphasizes that the presence of channel aggregation is more essential for the LIC model to achieve competitive performance, while the previously complex spatial interactions are partly redundant. Based on this insight, we initiate the "S2CFormer" paradigm, a general architecture that reorients the focus of LIC from Spatial Interaction to Channel Aggregation. We present two instantiations of the S2CFormer: S2C-Conv, and S2C-Attention. Each one incorporates a simple operator for spatial interaction and serves as nonlinear transform blocks for our LIC models. Both models demonstrate state-of-the-art (SOTA) R-D performance and significantly faster decoding speed. These results also motivate further exploration of advanced FFN structures to enhance the R-D performance while maintaining model efficiency. With these foundations, we introduce S2C-Hybrid, an enhanced LIC model that combines the strengths of different S2CFormer instantiations. This model outperforms all the existing methods on several datasets, setting a new benchmark for efficient and high-performance LIC. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00700v2-abstract-full').style.display = 'none'; document.getElementById('2502.00700v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.00619">arXiv:2502.00619</a> <span> [<a href="https://arxiv.org/pdf/2502.00619">pdf</a>, <a href="https://arxiv.org/format/2502.00619">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Oh%2C+Y">Yujin Oh</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Pengfei Jin</a>, <a href="/search/eess?searchtype=author&query=Park%2C+S">Sangjoon Park</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+S">Sekeun Kim</a>, <a href="/search/eess?searchtype=author&query=Yoon%2C+S">Siyeop Yoon</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+K">Kyungsang Kim</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+J+S">Jin Sung Kim</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.00619v1-abstract-short" style="display: inline;"> Ensuring fairness in medical image segmentation is critical due to biases in imbalanced clinical data acquisition caused by demographic attributes (e.g., age, sex, race) and clinical factors (e.g., disease severity). To address these challenges, we introduce Distribution-aware Mixture of Experts (dMoE), inspired by optimal control theory. We provide a comprehensive analysis of its underlying mecha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00619v1-abstract-full').style.display = 'inline'; document.getElementById('2502.00619v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.00619v1-abstract-full" style="display: none;"> Ensuring fairness in medical image segmentation is critical due to biases in imbalanced clinical data acquisition caused by demographic attributes (e.g., age, sex, race) and clinical factors (e.g., disease severity). To address these challenges, we introduce Distribution-aware Mixture of Experts (dMoE), inspired by optimal control theory. We provide a comprehensive analysis of its underlying mechanisms and clarify dMoE's role in adapting to heterogeneous distributions in medical image segmentation. Furthermore, we integrate dMoE into multiple network architectures, demonstrating its broad applicability across diverse medical image analysis tasks. By incorporating demographic and clinical factors, dMoE achieves state-of-the-art performance on two 2D benchmark datasets and a 3D in-house dataset. Our results highlight the effectiveness of dMoE in mitigating biases from imbalanced distributions, offering a promising approach to bridging control theory and medical image segmentation within fairness learning paradigms. The source code will be made available. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00619v1-abstract-full').style.display = 'none'; document.getElementById('2502.00619v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">12 pages, 3 figures, 9 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.12773">arXiv:2501.12773</a> <span> [<a href="https://arxiv.org/pdf/2501.12773">pdf</a>, <a href="https://arxiv.org/format/2501.12773">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Low-Complexity Channel Estimation for RIS-Assisted Multi-User Wireless Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingchao Li</a>, <a href="/search/eess?searchtype=author&query=El-Hajjar%2C+M">Mohammed El-Hajjar</a>, <a href="/search/eess?searchtype=author&query=Hemadeh%2C+I">Ibrahim Hemadeh</a>, <a href="/search/eess?searchtype=author&query=Shojaeifard%2C+A">Arman Shojaeifard</a>, <a href="/search/eess?searchtype=author&query=Hanzo%2C+L">Lajos Hanzo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.12773v1-abstract-short" style="display: inline;"> Reconfigurable intelligent surfaces (RISs) are eminently suitable for improving the reliability of wireless communications by jointly designing the active beamforming at the base station (BS) and the passive beamforming at the RIS. Therefore, the accuracy of channel estimation is crucial for RIS-aided systems. The challenge is that only the cascaded two-hop channel spanning from the user equipment… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12773v1-abstract-full').style.display = 'inline'; document.getElementById('2501.12773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.12773v1-abstract-full" style="display: none;"> Reconfigurable intelligent surfaces (RISs) are eminently suitable for improving the reliability of wireless communications by jointly designing the active beamforming at the base station (BS) and the passive beamforming at the RIS. Therefore, the accuracy of channel estimation is crucial for RIS-aided systems. The challenge is that only the cascaded two-hop channel spanning from the user equipments (UEs) to the RIS and spanning from the RIS to the BS can be estimated, due to the lack of active radio frequency (RF) chains at RIS elements, which leads to high pilot overhead. In this paper, we propose a low-overhead linear minimum mean square error (LMMSE) channel estimation method by exploiting the spatial correlation of channel links, which strikes a trade-off between the pilot overhead and the channel estimation accuracy. Moreover, we calculate the theoretical normalized mean square error (MSE) for our channel estimation method. Finally, we verify numerically that the proposed LMMSE estimator has lower MSE than the state-of-the-art (SoA) grouping based estimators. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.12773v1-abstract-full').style.display = 'none'; document.getElementById('2501.12773v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.11333">arXiv:2501.11333</a> <span> [<a href="https://arxiv.org/pdf/2501.11333">pdf</a>, <a href="https://arxiv.org/format/2501.11333">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> A Dynamic Improvement Framework for Vehicular Task Offloading </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qianren Li</a>, <a href="/search/eess?searchtype=author&query=Hong%2C+Y">Yuncong Hong</a>, <a href="/search/eess?searchtype=author&query=Lv%2C+B">Bojie Lv</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+R">Rui Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.11333v1-abstract-short" style="display: inline;"> In this paper, the task offloading from vehicles with random velocities is optimized via a novel dynamic improvement framework. Particularly, in a vehicular network with multiple vehicles and base stations (BSs), computing tasks of vehicles are offloaded via BSs to an edge server. Due to the random velocities, the exact trajectories of vehicles cannot be predicted in advance. Hence, instead of det… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.11333v1-abstract-full').style.display = 'inline'; document.getElementById('2501.11333v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.11333v1-abstract-full" style="display: none;"> In this paper, the task offloading from vehicles with random velocities is optimized via a novel dynamic improvement framework. Particularly, in a vehicular network with multiple vehicles and base stations (BSs), computing tasks of vehicles are offloaded via BSs to an edge server. Due to the random velocities, the exact trajectories of vehicles cannot be predicted in advance. Hence, instead of deterministic optimization, the cell association, uplink time and throughput allocation of multiple vehicles in a period of task offloading are formulated as a finite-horizon Markov decision process. In the proposed solution framework, we first obtain a reference scheduling scheme of cell association, uplink time and throughput allocation via deterministic optimization at the very beginning. The reference scheduling scheme is then used to approximate the value functions of the Bellman's equations, and the actual scheduling action is determined in each time slot according to the current system state and approximate value functions. Thus, the intensive computation for value iteration in the conventional solution is eliminated. Moreover, a non-trivial average cost upper bound is provided for the proposed solution framework. In the simulation, the random trajectories of vehicles are generated from a high-fidelity traffic simulator. It is shown that the performance gain of the proposed scheduling framework over the baselines is significant. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.11333v1-abstract-full').style.display = 'none'; document.getElementById('2501.11333v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.09054">arXiv:2501.09054</a> <span> [<a href="https://arxiv.org/pdf/2501.09054">pdf</a>, <a href="https://arxiv.org/format/2501.09054">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</span> </div> </div> <p class="title is-5 mathjax"> NeurOp-Diff:Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+Z">Zihao Xu</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yuzhi Tang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+B">Bowen Xu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingquan Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.09054v2-abstract-short" style="display: inline;"> Most publicly accessible remote sensing data suffer from low resolution, limiting their practical applications. To address this, we propose a diffusion model guided by neural operators for continuous remote sensing image super-resolution (NeurOp-Diff). Neural operators are used to learn resolution representations at arbitrary scales, encoding low-resolution (LR) images into high-dimensional featur… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09054v2-abstract-full').style.display = 'inline'; document.getElementById('2501.09054v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.09054v2-abstract-full" style="display: none;"> Most publicly accessible remote sensing data suffer from low resolution, limiting their practical applications. To address this, we propose a diffusion model guided by neural operators for continuous remote sensing image super-resolution (NeurOp-Diff). Neural operators are used to learn resolution representations at arbitrary scales, encoding low-resolution (LR) images into high-dimensional features, which are then used as prior conditions to guide the diffusion model for denoising. This effectively addresses the artifacts and excessive smoothing issues present in existing super-resolution (SR) methods, enabling the generation of high-quality, continuous super-resolution images. Specifically, we adjust the super-resolution scale by a scaling factor s, allowing the model to adapt to different super-resolution magnifications. Furthermore, experiments on multiple datasets demonstrate the effectiveness of NeurOp-Diff. Our code is available at https://github.com/zerono000/NeurOp-Diff. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.09054v2-abstract-full').style.display = 'none'; document.getElementById('2501.09054v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.05085">arXiv:2501.05085</a> <span> [<a href="https://arxiv.org/pdf/2501.05085">pdf</a>, <a href="https://arxiv.org/format/2501.05085">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> End-to-End Deep Learning for Interior Tomography with Low-Dose X-ray CT </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Han%2C+Y">Yoseob Han</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+D">Dufan Wu</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+K">Kyungsang Kim</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.05085v1-abstract-short" style="display: inline;"> Objective: There exist several X-ray computed tomography (CT) scanning strategies to reduce a radiation dose, such as (1) sparse-view CT, (2) low-dose CT, and (3) region-of-interest (ROI) CT (called interior tomography). To further reduce the dose, the sparse-view and/or low-dose CT settings can be applied together with interior tomography. Interior tomography has various advantages in terms of re… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05085v1-abstract-full').style.display = 'inline'; document.getElementById('2501.05085v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.05085v1-abstract-full" style="display: none;"> Objective: There exist several X-ray computed tomography (CT) scanning strategies to reduce a radiation dose, such as (1) sparse-view CT, (2) low-dose CT, and (3) region-of-interest (ROI) CT (called interior tomography). To further reduce the dose, the sparse-view and/or low-dose CT settings can be applied together with interior tomography. Interior tomography has various advantages in terms of reducing the number of detectors and decreasing the X-ray radiation dose. However, a large patient or small field-of-view (FOV) detector can cause truncated projections, and then the reconstructed images suffer from severe cupping artifacts. In addition, although the low-dose CT can reduce the radiation exposure dose, analytic reconstruction algorithms produce image noise. Recently, many researchers have utilized image-domain deep learning (DL) approaches to remove each artifact and demonstrated impressive performances, and the theory of deep convolutional framelets supports the reason for the performance improvement. Approach: In this paper, we found that the image-domain convolutional neural network (CNN) is difficult to solve coupled artifacts, based on deep convolutional framelets. Significance: To address the coupled problem, we decouple it into two sub-problems: (i) image domain noise reduction inside truncated projection to solve low-dose CT problem and (ii) extrapolation of projection outside truncated projection to solve the ROI CT problem. The decoupled sub-problems are solved directly with a novel proposed end-to-end learning using dual-domain CNNs. Main results: We demonstrate that the proposed method outperforms the conventional image-domain deep learning methods, and a projection-domain CNN shows better performance than the image-domain CNNs which are commonly used by many researchers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05085v1-abstract-full').style.display = 'none'; document.getElementById('2501.05085v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published by Physics in Medicine & Biology (2022.5)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.04164">arXiv:2501.04164</a> <span> [<a href="https://arxiv.org/pdf/2501.04164">pdf</a>, <a href="https://arxiv.org/format/2501.04164">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Holographic Metasurface-Based Beamforming for Multi-Altitude LEO Satellite Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingchao Li</a>, <a href="/search/eess?searchtype=author&query=El-Hajjar%2C+M">Mohammed El-Hajjar</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+K">Kaijun Cao</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+C">Chao Xu</a>, <a href="/search/eess?searchtype=author&query=Haas%2C+H">Harald Haas</a>, <a href="/search/eess?searchtype=author&query=Hanzo%2C+L">Lajos Hanzo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.04164v1-abstract-short" style="display: inline;"> Low Earth Orbit (LEO) satellite networks are capable of improving the global Internet service coverage. In this context, we propose a hybrid beamforming design for holographic metasurface based terrestrial users in multi-altitude LEO satellite networks. Firstly, the holographic beamformer is optimized by maximizing the downlink channel gain from the serving satellite to the terrestrial user. Then,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04164v1-abstract-full').style.display = 'inline'; document.getElementById('2501.04164v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.04164v1-abstract-full" style="display: none;"> Low Earth Orbit (LEO) satellite networks are capable of improving the global Internet service coverage. In this context, we propose a hybrid beamforming design for holographic metasurface based terrestrial users in multi-altitude LEO satellite networks. Firstly, the holographic beamformer is optimized by maximizing the downlink channel gain from the serving satellite to the terrestrial user. Then, the digital beamformer is designed by conceiving a minimum mean square error (MMSE) based detection algorithm for mitigating the interference arriving from other satellites. To dispense with excessive overhead of full channel state information (CSI) acquisition of all satellites, we propose a low-complexity MMSE beamforming algorithm that only relies on the distribution of the LEO satellite constellation harnessing stochastic geometry, which can achieve comparable throughput to that of the algorithm based on the full CSI in the case of a dense LEO satellite deployment. Furthermore, it outperforms the maximum ratio combining (MRC) algorithm, thanks to its inter-satellite interference mitigation capacity. The simulation results show that our proposed holographic metasurface based hybrid beamforming architecture is capable of outperforming the state-of-the-art antenna array architecture in terms of its throughput, given the same physical size of the transceivers. Moreover, we demonstrate that the beamforming performance attained can be substantially improved by taking into account the mutual coupling effect, imposed by the dense placement of the holographic metasurface elements. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.04164v1-abstract-full').style.display = 'none'; document.getElementById('2501.04164v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.16747">arXiv:2412.16747</a> <span> [<a href="https://arxiv.org/pdf/2412.16747">pdf</a>, <a href="https://arxiv.org/ps/2412.16747">ps</a>, <a href="https://arxiv.org/format/2412.16747">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Space-Air-Ground Integrated Networks: Their Channel Model and Performance Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+C">Chao Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingchao Li</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+C">Chao Xu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+L">Lie-Liang Yang</a>, <a href="/search/eess?searchtype=author&query=Hanzo%2C+L">Lajos Hanzo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.16747v1-abstract-short" style="display: inline;"> Given their extensive geographic coverage, low Earth orbit (LEO) satellites are envisioned to find their way into next-generation (6G) wireless communications. This paper explores space-air-ground integrated networks (SAGINs) leveraging LEOs to support terrestrial and non-terrestrial users. We first propose a practical satellite-ground channel model that incorporates five key aspects: 1) the small… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16747v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16747v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16747v1-abstract-full" style="display: none;"> Given their extensive geographic coverage, low Earth orbit (LEO) satellites are envisioned to find their way into next-generation (6G) wireless communications. This paper explores space-air-ground integrated networks (SAGINs) leveraging LEOs to support terrestrial and non-terrestrial users. We first propose a practical satellite-ground channel model that incorporates five key aspects: 1) the small-scale fading characterized by the Shadowed-Rician distribution in terms of the Rician factor K, 2) the path loss effect of bending rays due to atmospheric refraction, 3) the molecular absorption modelled by the Beer-Lambert law, 4) the Doppler effects including the Earth's rotation, and 5) the impact of weather conditions according to the International Telecommunication Union Recommendations (ITU-R). Harnessing the proposed model, we analyze the long-term performance of the SAGIN considered. Explicitly, the closed-form expressions of both the outage probability and of the ergodic rates are derived. Additionally, the upper bounds of bit-error rates and of the Goodput are investigated. The numerical results yield the following insights: 1) The shadowing effect and the ratio between the line-of-sight and scattering components can be conveniently modeled by the factors of K and m in the proposed Shadowed-Rician small-scale fading model. 2) The atmospheric refraction has a modest effect on the path loss. 3) When calculating the transmission distance of waves, Earth's curvature and its geometric relationship with the satellites must be considered, particularly at small elevation angles. 3) High-frequency carriers suffer from substantial path loss, and 4) the Goodput metric is eminently suitable for characterizing the performance of different coding as well as modulation methods and of the estimation error of the Doppler effects. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16747v1-abstract-full').style.display = 'none'; document.getElementById('2412.16747v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.10554">arXiv:2412.10554</a> <span> [<a href="https://arxiv.org/pdf/2412.10554">pdf</a>, <a href="https://arxiv.org/format/2412.10554">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Prescribing Decision Conservativeness in Two-Stage Power Markets: A Distributionally Robust End-to-End Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liang%2C+Z">Zhirui Liang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+A">Anqi Liu</a>, <a href="/search/eess?searchtype=author&query=Dvorkin%2C+Y">Yury Dvorkin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.10554v1-abstract-short" style="display: inline;"> This paper presents an end-to-end framework for calibrating wind power forecast models to minimize operational costs in two-stage power markets, where the first stage involves a distributionally robust optimal power flow (DR-OPF) model. Unlike traditional methods that adjust forecast parameters and uncertainty quantification (UQ) separately, this framework jointly optimizes both the forecast model… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10554v1-abstract-full').style.display = 'inline'; document.getElementById('2412.10554v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.10554v1-abstract-full" style="display: none;"> This paper presents an end-to-end framework for calibrating wind power forecast models to minimize operational costs in two-stage power markets, where the first stage involves a distributionally robust optimal power flow (DR-OPF) model. Unlike traditional methods that adjust forecast parameters and uncertainty quantification (UQ) separately, this framework jointly optimizes both the forecast model parameters and the decision conservativeness, which determines the size of the ambiguity set in the DR-OPF model. The framework aligns UQ with actual uncertainty realizations by directly optimizing downstream operational costs, a process referred to as cost-oriented calibration. The calibration is achieved using a gradient descent approach. To enable efficient differentiation, the DR-OPF problem is reformulated into a convex form, and the Envelope Theorem is leveraged to simplify gradient derivation in the two-stage setting. Additionally, the framework supports distributed implementation, enhancing data privacy and reducing computational overhead. By proactively calibrating forecast parameters and prescribing optimal decision conservativeness, the framework significantly enhances cost efficiency and reliability in power system operations. Numerical experiments on an IEEE 5-bus system demonstrate the effectiveness and efficiency of the proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10554v1-abstract-full').style.display = 'none'; document.getElementById('2412.10554v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.06279">arXiv:2412.06279</a> <span> [<a href="https://arxiv.org/pdf/2412.06279">pdf</a>, <a href="https://arxiv.org/format/2412.06279">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Reconfigurable Holographic Surface-aided Distributed MIMO Radar Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qian Li</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Z">Ziang Yang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+D">Dou Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hongliang Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.06279v2-abstract-short" style="display: inline;"> Distributed phased Multiple-Input Multiple-Output (phased-MIMO) radar systems have attracted wide attention in target detection and tracking. However, the phase-shifting circuits in phased subarrays contribute to high power consumption and hardware cost. To address this issue, an energy-efficient and cost-efficient metamaterial antenna array, i.e., reconfigurable holographic surface (RHS), has bee… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06279v2-abstract-full').style.display = 'inline'; document.getElementById('2412.06279v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.06279v2-abstract-full" style="display: none;"> Distributed phased Multiple-Input Multiple-Output (phased-MIMO) radar systems have attracted wide attention in target detection and tracking. However, the phase-shifting circuits in phased subarrays contribute to high power consumption and hardware cost. To address this issue, an energy-efficient and cost-efficient metamaterial antenna array, i.e., reconfigurable holographic surface (RHS), has been developed. In this letter, we propose RHS-aided distributed MIMO radar systems to achieve more accurate multi-target detection under equivalent power consumption and hardware cost as that of distributed phased-MIMO radar systems. Different from phased arrays, the RHS achieves beam steering by regulating the radiation amplitude of its elements, and thus conventional beamforming schemes designed for phased arrays are no longer applicable. Aiming to maximize detection accuracy, we design an amplitude-controlled beamforming scheme for multiple RHS transceiver subarrays. The simulations validate the superiority of the proposed scheme over the distributed phased-MIMO radar scheme and reveal the optimal allocation of spatial diversity and coherent processing gain that leads to the best system performance when hardware resources are fixed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06279v2-abstract-full').style.display = 'none'; document.getElementById('2412.06279v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00715">arXiv:2412.00715</a> <span> [<a href="https://arxiv.org/pdf/2412.00715">pdf</a>, <a href="https://arxiv.org/format/2412.00715">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Han%2C+X">Xiaoxiang Han</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yiman Liu</a>, <a href="/search/eess?searchtype=author&query=Shang%2C+J">Jiang Shang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingli Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jiangang Chen</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+M">Menghan Hu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Q">Qi Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yuqi Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.00715v1-abstract-short" style="display: inline;"> Segmenting internal structure from echocardiography is essential for the diagnosis and treatment of various heart diseases. Semi-supervised learning shows its ability in alleviating annotations scarcity. While existing semi-supervised methods have been successful in image segmentation across various medical imaging modalities, few have attempted to design methods specifically addressing the challe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00715v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00715v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00715v1-abstract-full" style="display: none;"> Segmenting internal structure from echocardiography is essential for the diagnosis and treatment of various heart diseases. Semi-supervised learning shows its ability in alleviating annotations scarcity. While existing semi-supervised methods have been successful in image segmentation across various medical imaging modalities, few have attempted to design methods specifically addressing the challenges posed by the poor contrast, blurred edge details and noise of echocardiography. These characteristics pose challenges to the generation of high-quality pseudo-labels in semi-supervised segmentation based on Mean Teacher. Inspired by human reflection on erroneous practices, we devise an error reflection strategy for echocardiography semi-supervised segmentation architecture. The process triggers the model to reflect on inaccuracies in unlabeled image segmentation, thereby enhancing the robustness of pseudo-label generation. Specifically, the strategy is divided into two steps. The first step is called reconstruction reflection. The network is tasked with reconstructing authentic proxy images from the semantic masks of unlabeled images and their auxiliary sketches, while maximizing the structural similarity between the original inputs and the proxies. The second step is called guidance correction. Reconstruction error maps decouple unreliable segmentation regions. Then, reliable data that are more likely to occur near high-density areas are leveraged to guide the optimization of unreliable data potentially located around decision boundaries. Additionally, we introduce an effective data augmentation strategy, termed as multi-scale mixing up strategy, to minimize the empirical distribution gap between labeled and unlabeled images and perceive diverse scales of cardiac anatomical structures. Extensive experiments demonstrate the competitiveness of the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00715v1-abstract-full').style.display = 'none'; document.getElementById('2412.00715v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 4 figure, accepted by 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2024)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.00481">arXiv:2412.00481</a> <span> [<a href="https://arxiv.org/pdf/2412.00481">pdf</a>, <a href="https://arxiv.org/format/2412.00481">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> MaintAGT:Sim2Real-Guided Multimodal Large Model for Intelligent Maintenance with Chain-of-Thought Reasoning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=He%2C+H">Hongliang He</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+J">Jinfeng Huang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xu Wang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+F">Feibin Zhang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+K">Kangding Yang</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+L">Li Meng</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+F">Fulei Chu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.00481v1-abstract-short" style="display: inline;"> In recent years, large language models have made significant advancements in the field of natural language processing, yet there are still inadequacies in specific domain knowledge and applications. This paper Proposes MaintAGT, a professional large model for intelligent operations and maintenance, aimed at addressing this issue. The system comprises three key components: a signal-to-text model, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00481v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00481v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00481v1-abstract-full" style="display: none;"> In recent years, large language models have made significant advancements in the field of natural language processing, yet there are still inadequacies in specific domain knowledge and applications. This paper Proposes MaintAGT, a professional large model for intelligent operations and maintenance, aimed at addressing this issue. The system comprises three key components: a signal-to-text model, a pure text model, and a multimodal model. Firstly, the signal-to-text model was designed to convert raw signal data into textual descriptions, bridging the gap between signal data and text-based analysis. Secondly, the pure text model was fine-tuned using the GLM4 model with specialized knowledge to enhance its understanding of domain-specific texts. Finally, these two models were integrated to develop a comprehensive multimodal model that effectively processes and analyzes both signal and textual data.The dataset used for training and evaluation was sourced from academic papers, textbooks, international standards, and vibration analyst training materials, undergoing meticulous preprocessing to ensure high-quality data. As a result, the model has demonstrated outstanding performance across multiple intelligent operations and maintenance tasks, providing a low-cost, high-quality method for constructing large-scale monitoring signal-text description-fault pattern datasets. Experimental results indicate that the model holds significant advantages in condition monitoring, signal processing, and fault diagnosis.In the constructed general test set, MaintAGT achieved an accuracy of 70%, surpassing all existing general large language models and reaching the level of an ISO Level III human vibration analyst.This advancement signifies a crucial step forward from traditional maintenance practices toward intelligent and AI-driven maintenance solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00481v1-abstract-full').style.display = 'none'; document.getElementById('2412.00481v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.19000">arXiv:2411.19000</a> <span> [<a href="https://arxiv.org/pdf/2411.19000">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> A Unified Platform for At-Home Post-Stroke Rehabilitation Enabled by Wearable Technologies and Artificial Intelligence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Tang%2C+C">Chenyu Tang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Ruizhi Zhang</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+S">Shuo Gao</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+Z">Zihe Zhao</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zibo Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiaqi Wang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+C">Cong Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Junliang Chen</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+Y">Yanning Dai</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shengbo Wang</a>, <a href="/search/eess?searchtype=author&query=Juan%2C+R">Ruoyu Juan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiaoying Li</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+R">Ruimou Xie</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xuhang Chen</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+X">Xinkai Zhou</a>, <a href="/search/eess?searchtype=author&query=Xia%2C+Y">Yunjia Xia</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jianan Chen</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+F">Fanghao Lu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xin Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+N">Ninglli Wang</a>, <a href="/search/eess?searchtype=author&query=Smielewski%2C+P">Peter Smielewski</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+Y">Yu Pan</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+H">Hubin Zhao</a>, <a href="/search/eess?searchtype=author&query=Occhipinti%2C+L+G">Luigi G. Occhipinti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.19000v1-abstract-short" style="display: inline;"> At-home rehabilitation for post-stroke patients presents significant challenges, as continuous, personalized care is often limited outside clinical settings. Additionally, the absence of comprehensive solutions addressing diverse rehabilitation needs in home environments complicates recovery efforts. Here, we introduce a smart home platform that integrates wearable sensors, ambient monitoring, and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.19000v1-abstract-full').style.display = 'inline'; document.getElementById('2411.19000v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.19000v1-abstract-full" style="display: none;"> At-home rehabilitation for post-stroke patients presents significant challenges, as continuous, personalized care is often limited outside clinical settings. Additionally, the absence of comprehensive solutions addressing diverse rehabilitation needs in home environments complicates recovery efforts. Here, we introduce a smart home platform that integrates wearable sensors, ambient monitoring, and large language model (LLM)-powered assistance to provide seamless health monitoring and intelligent support. The system leverages machine learning enabled plantar pressure arrays for motor recovery assessment (94% classification accuracy), a wearable eye-tracking module for cognitive evaluation, and ambient sensors for precise smart home control (100% operational success, <1 s latency). Additionally, the LLM-powered agent, Auto-Care, offers real-time interventions, such as health reminders and environmental adjustments, enhancing user satisfaction by 29%. This work establishes a fully integrated platform for long-term, personalized rehabilitation, offering new possibilities for managing chronic conditions and supporting aging populations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.19000v1-abstract-full').style.display = 'none'; document.getElementById('2411.19000v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 figures, 35 references</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.13602">arXiv:2411.13602</a> <span> [<a href="https://arxiv.org/pdf/2411.13602">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Large-scale cross-modality pretrained model enhances cardiovascular state estimation and cardiomyopathy detection from electrocardiograms: An AI system development and multi-center validation study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ding%2C+Z">Zhengyao Ding</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Y">Yujian Hu</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Youyao Xu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+C">Chengchen Zhao</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Ziyu Li</a>, <a href="/search/eess?searchtype=author&query=Mao%2C+Y">Yiheng Mao</a>, <a href="/search/eess?searchtype=author&query=Li%2C+H">Haitao Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qian Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jing Wang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yue Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+M">Mengjia Chen</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+L">Longbo Wang</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+X">Xuesen Chu</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+W">Weichao Pan</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Ziyi Liu</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+F">Fei Wu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hongkun Zhang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+T">Ting Chen</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Z">Zhengxing Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.13602v1-abstract-short" style="display: inline;"> Cardiovascular diseases (CVDs) present significant challenges for early and accurate diagnosis. While cardiac magnetic resonance imaging (CMR) is the gold standard for assessing cardiac function and diagnosing CVDs, its high cost and technical complexity limit accessibility. In contrast, electrocardiography (ECG) offers promise for large-scale early screening. This study introduces CardiacNets, an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13602v1-abstract-full').style.display = 'inline'; document.getElementById('2411.13602v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13602v1-abstract-full" style="display: none;"> Cardiovascular diseases (CVDs) present significant challenges for early and accurate diagnosis. While cardiac magnetic resonance imaging (CMR) is the gold standard for assessing cardiac function and diagnosing CVDs, its high cost and technical complexity limit accessibility. In contrast, electrocardiography (ECG) offers promise for large-scale early screening. This study introduces CardiacNets, an innovative model that enhances ECG analysis by leveraging the diagnostic strengths of CMR through cross-modal contrastive learning and generative pretraining. CardiacNets serves two primary functions: (1) it evaluates detailed cardiac function indicators and screens for potential CVDs, including coronary artery disease, cardiomyopathy, pericarditis, heart failure and pulmonary hypertension, using ECG input; and (2) it enhances interpretability by generating high-quality CMR images from ECG data. We train and validate the proposed CardiacNets on two large-scale public datasets (the UK Biobank with 41,519 individuals and the MIMIC-IV-ECG comprising 501,172 samples) as well as three private datasets (FAHZU with 410 individuals, SAHZU with 464 individuals, and QPH with 338 individuals), and the findings demonstrate that CardiacNets consistently outperforms traditional ECG-only models, substantially improving screening accuracy. Furthermore, the generated CMR images provide valuable diagnostic support for physicians of all experience levels. This proof-of-concept study highlights how ECG can facilitate cross-modal insights into cardiac function assessment, paving the way for enhanced CVD screening and diagnosis at a population level. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13602v1-abstract-full').style.display = 'none'; document.getElementById('2411.13602v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">23 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.03636">arXiv:2411.03636</a> <span> [<a href="https://arxiv.org/pdf/2411.03636">pdf</a>, <a href="https://arxiv.org/format/2411.03636">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Domain Generalization for Cross-Receiver Radio Frequency Fingerprint Identification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Ying Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiang Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Hongli Liu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+L">Liu Yang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jian Yang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.03636v1-abstract-short" style="display: inline;"> Radio Frequency Fingerprint Identification (RFFI) technology uniquely identifies emitters by analyzing unique distortions in the transmitted signal caused by non-ideal hardware. Recently, RFFI based on deep learning methods has gained popularity and is seen as a promising way to address the device authentication problem for Internet of Things (IoT) systems. However, in cross-receiver scenarios, wh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03636v1-abstract-full').style.display = 'inline'; document.getElementById('2411.03636v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.03636v1-abstract-full" style="display: none;"> Radio Frequency Fingerprint Identification (RFFI) technology uniquely identifies emitters by analyzing unique distortions in the transmitted signal caused by non-ideal hardware. Recently, RFFI based on deep learning methods has gained popularity and is seen as a promising way to address the device authentication problem for Internet of Things (IoT) systems. However, in cross-receiver scenarios, where the RFFI model is trained over RF signals from some receivers but deployed at a new receiver, the alteration of receivers' characteristics would lead to data distribution shift and cause significant performance degradation at the new receiver. To address this problem, we first perform a theoretical analysis of the cross-receiver generalization error bound and propose a sufficient condition, named Separable Condition (SC), to minimize the classification error probability on the new receiver. Guided by the SC, a Receiver-Independent Emitter Identification (RIEI)model is devised to decouple the received signals into emitter-related features and receiver-related features and only the emitter-related features are used for identification. Furthermore, by leveraging federated learning, we also develop a FedRIEI model to eliminate the need for centralized collection of raw data from multiple receivers. Experiments on two real-world datasets demonstrate the superiority of our proposed methods over some baseline methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.03636v1-abstract-full').style.display = 'none'; document.getElementById('2411.03636v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Internet of Things Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18400">arXiv:2410.18400</a> <span> [<a href="https://arxiv.org/pdf/2410.18400">pdf</a>, <a href="https://arxiv.org/format/2410.18400">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> DMVC: Multi-Camera Video Compression Network aimed at Improving Deep Learning Accuracy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cui%2C+H">Huan Cui</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qing Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+H">Hanling Wang</a>, <a href="/search/eess?searchtype=author&query=jiang%2C+Y">Yong jiang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18400v1-abstract-short" style="display: inline;"> We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception, our innovative approach focuses on preserving semantic information critical for deep learning accuracy, while efficiently reducing data size. The framework ope… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18400v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18400v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18400v1-abstract-full" style="display: none;"> We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception, our innovative approach focuses on preserving semantic information critical for deep learning accuracy, while efficiently reducing data size. The framework operates on a batch basis, capable of handling multiple video streams simultaneously, thereby enhancing scalability and processing efficiency. It features a dual reconstruction mode: lightweight for real-time applications requiring swift responses, and high-precision for scenarios where accuracy is crucial. Based on a designed deep learning algorithms, it adeptly segregates essential information from redundancy, ensuring machine learning tasks are fed with data of the highest relevance. Our experimental results, derived from diverse datasets including urban surveillance and autonomous vehicle navigation, showcase DMVC's superiority in maintaining or improving machine learning task accuracy, while achieving significant data compression. This breakthrough paves the way for smarter, scalable video analysis systems, promising immense potential across various applications from smart city infrastructure to autonomous systems, establishing a new benchmark for integrating video compression with machine learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18400v1-abstract-full').style.display = 'none'; document.getElementById('2410.18400v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.17690">arXiv:2410.17690</a> <span> [<a href="https://arxiv.org/pdf/2410.17690">pdf</a>, <a href="https://arxiv.org/format/2410.17690">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Science and Game Theory">cs.GT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multiagent Systems">cs.MA</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Markov Potential Game with Final-time Reach-Avoid Objectives </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+S+H+Q">Sarah H. Q. Li</a>, <a href="/search/eess?searchtype=author&query=Vinod%2C+A+P">Abraham P. Vinod</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.17690v1-abstract-short" style="display: inline;"> We formulate a Markov potential game with final-time reach-avoid objectives by integrating potential game theory with stochastic reach-avoid control. Our focus is on multi-player trajectory planning where players maximize the same multi-player reach-avoid objective: the probability of all participants reaching their designated target states by a specified time, while avoiding collisions with one a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17690v1-abstract-full').style.display = 'inline'; document.getElementById('2410.17690v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.17690v1-abstract-full" style="display: none;"> We formulate a Markov potential game with final-time reach-avoid objectives by integrating potential game theory with stochastic reach-avoid control. Our focus is on multi-player trajectory planning where players maximize the same multi-player reach-avoid objective: the probability of all participants reaching their designated target states by a specified time, while avoiding collisions with one another. Existing approaches require centralized computation of actions via a global policy, which may have prohibitively expensive communication costs. Instead, we focus on approximations of the global policy via local state feedback policies. First, we adapt the recursive single player reach-avoid value iteration to the multi-player framework with local policies, and show that the same recursion holds on the joint state space. To find each player's optimal local policy, the multi-player reach-avoid value function is projected from the joint state to the local state using the other players' occupancy measures. Then, we propose an iterative best response scheme for the multi-player value iteration to converge to a pure Nash equilibrium. We demonstrate the utility of our approach in finding collision-free policies for multi-player motion planning in simulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.17690v1-abstract-full').style.display = 'none'; document.getElementById('2410.17690v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03143">arXiv:2410.03143</a> <span> [<a href="https://arxiv.org/pdf/2410.03143">pdf</a>, <a href="https://arxiv.org/format/2410.03143">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> ECHOPulse: ECG controlled echocardio-grams video generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yiwei Li</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+S">Sekeun Kim</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Z">Zihao Wu</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+H">Hanqi Jiang</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+Y">Yi Pan</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Pengfei Jin</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sifan Song</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Y">Yucheng Shi</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+T">Tianming Liu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03143v2-abstract-short" style="display: inline;"> Echocardiography (ECHO) is essential for cardiac assessments, but its video quality and interpretation heavily relies on manual expertise, leading to inconsistent results from clinical and portable devices. ECHO video generation offers a solution by improving automated monitoring through synthetic data and generating high-quality videos from routine health data. However, existing models often face… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03143v2-abstract-full').style.display = 'inline'; document.getElementById('2410.03143v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03143v2-abstract-full" style="display: none;"> Echocardiography (ECHO) is essential for cardiac assessments, but its video quality and interpretation heavily relies on manual expertise, leading to inconsistent results from clinical and portable devices. ECHO video generation offers a solution by improving automated monitoring through synthetic data and generating high-quality videos from routine health data. However, existing models often face high computational costs, slow inference, and rely on complex conditional prompts that require experts' annotations. To address these challenges, we propose ECHOPULSE, an ECG-conditioned ECHO video generation model. ECHOPULSE introduces two key advancements: (1) it accelerates ECHO video generation by leveraging VQ-VAE tokenization and masked visual token modeling for fast decoding, and (2) it conditions on readily accessible ECG signals, which are highly coherent with ECHO videos, bypassing complex conditional prompts. To the best of our knowledge, this is the first work to use time-series prompts like ECG signals for ECHO video generation. ECHOPULSE not only enables controllable synthetic ECHO data generation but also provides updated cardiac function information for disease monitoring and prediction beyond ECG alone. Evaluations on three public and private datasets demonstrate state-of-the-art performance in ECHO video generation across both qualitative and quantitative measures. Additionally, ECHOPULSE can be easily generalized to other modality generation tasks, such as cardiac MRI, fMRI, and 3D CT generation. Demo can seen from \url{https://github.com/levyisthebest/ECHOPulse_Prelease}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03143v2-abstract-full').style.display = 'none'; document.getElementById('2410.03143v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00184">arXiv:2410.00184</a> <span> [<a href="https://arxiv.org/pdf/2410.00184">pdf</a>, <a href="https://arxiv.org/format/2410.00184">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Volumetric Conditional Score-based Residual Diffusion Model for PET/MR Denoising </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yoon%2C+S">Siyeop Yoon</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+R">Rui Hu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuang Wang</a>, <a href="/search/eess?searchtype=author&query=Tivnan%2C+M">Matthew Tivnan</a>, <a href="/search/eess?searchtype=author&query=Son%2C+Y">Young-don Son</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+D">Dufan Wu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+K">Kyungsang Kim</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.00184v1-abstract-short" style="display: inline;"> PET imaging is a powerful modality offering quantitative assessments of molecular and physiological processes. The necessity for PET denoising arises from the intrinsic high noise levels in PET imaging, which can significantly hinder the accurate interpretation and quantitative analysis of the scans. With advances in deep learning techniques, diffusion model-based PET denoising techniques have sho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00184v1-abstract-full').style.display = 'inline'; document.getElementById('2410.00184v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00184v1-abstract-full" style="display: none;"> PET imaging is a powerful modality offering quantitative assessments of molecular and physiological processes. The necessity for PET denoising arises from the intrinsic high noise levels in PET imaging, which can significantly hinder the accurate interpretation and quantitative analysis of the scans. With advances in deep learning techniques, diffusion model-based PET denoising techniques have shown remarkable performance improvement. However, these models often face limitations when applied to volumetric data. Additionally, many existing diffusion models do not adequately consider the unique characteristics of PET imaging, such as its 3D volumetric nature, leading to the potential loss of anatomic consistency. Our Conditional Score-based Residual Diffusion (CSRD) model addresses these issues by incorporating a refined score function and 3D patch-wise training strategy, optimizing the model for efficient volumetric PET denoising. The CSRD model significantly lowers computational demands and expedites the denoising process. By effectively integrating volumetric data from PET and MRI scans, the CSRD model maintains spatial coherence and anatomical detail. Lastly, we demonstrate that the CSRD model achieves superior denoising performance in both qualitative and quantitative evaluations while maintaining image details and outperforms existing state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00184v1-abstract-full').style.display = 'none'; document.getElementById('2410.00184v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 30 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to MICCAI 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.00046">arXiv:2410.00046</a> <span> [<a href="https://arxiv.org/pdf/2410.00046">pdf</a>, <a href="https://arxiv.org/format/2410.00046">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Mixture of Multicenter Experts in Multimodal Generative AI for Advanced Radiotherapy Target Delineation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Oh%2C+Y">Yujin Oh</a>, <a href="/search/eess?searchtype=author&query=Park%2C+S">Sangjoon Park</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/eess?searchtype=author&query=Yi%2C+W">Wang Yi</a>, <a href="/search/eess?searchtype=author&query=Paly%2C+J">Jonathan Paly</a>, <a href="/search/eess?searchtype=author&query=Efstathiou%2C+J">Jason Efstathiou</a>, <a href="/search/eess?searchtype=author&query=Chan%2C+A">Annie Chan</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+J+W">Jun Won Kim</a>, <a href="/search/eess?searchtype=author&query=Byun%2C+H+K">Hwa Kyung Byun</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+I+J">Ik Jae Lee</a>, <a href="/search/eess?searchtype=author&query=Cho%2C+J">Jaeho Cho</a>, <a href="/search/eess?searchtype=author&query=Wee%2C+C+W">Chan Woo Wee</a>, <a href="/search/eess?searchtype=author&query=Shu%2C+P">Peng Shu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+P">Peilong Wang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+N">Nathan Yu</a>, <a href="/search/eess?searchtype=author&query=Holmes%2C+J">Jason Holmes</a>, <a href="/search/eess?searchtype=author&query=Ye%2C+J+C">Jong Chul Ye</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+W">Wei Liu</a>, <a href="/search/eess?searchtype=author&query=Koom%2C+W+S">Woong Sub Koom</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+J+S">Jin Sung Kim</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+K">Kyungsang Kim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.00046v2-abstract-short" style="display: inline;"> Clinical experts employ diverse philosophies and strategies in patient care, influenced by regional patient populations. However, existing medical artificial intelligence (AI) models are often trained on data distributions that disproportionately reflect highly prevalent patterns, reinforcing biases and overlooking the diverse expertise of clinicians. To overcome this limitation, we introduce the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00046v2-abstract-full').style.display = 'inline'; document.getElementById('2410.00046v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00046v2-abstract-full" style="display: none;"> Clinical experts employ diverse philosophies and strategies in patient care, influenced by regional patient populations. However, existing medical artificial intelligence (AI) models are often trained on data distributions that disproportionately reflect highly prevalent patterns, reinforcing biases and overlooking the diverse expertise of clinicians. To overcome this limitation, we introduce the Mixture of Multicenter Experts (MoME) approach. This method strategically integrates specialized expertise from diverse clinical strategies, enhancing the AI model's ability to generalize and adapt across multiple medical centers. The MoME-based multimodal target volume delineation model, trained with few-shot samples including images and clinical notes from each medical center, outperformed baseline methods in prostate cancer radiotherapy target delineation. The advantages of MoME were most pronounced when data characteristics varied across centers or when data availability was limited, demonstrating its potential for broader clinical applications. Therefore, the MoME framework enables the deployment of AI-based target volume delineation models in resource-constrained medical facilities by adapting to specific preferences of each medical center only using a few sample data, without the need for data sharing between institutions. Expanding the number of multicenter experts within the MoME framework will significantly enhance the generalizability, while also improving the usability and adaptability of clinical AI applications in the field of precision radiation oncology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00046v2-abstract-full').style.display = 'none'; document.getElementById('2410.00046v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">39 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.17010">arXiv:2409.17010</a> <span> [<a href="https://arxiv.org/pdf/2409.17010">pdf</a>, <a href="https://arxiv.org/format/2409.17010">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+X">Xiaoyu Yang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiujia Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+C">Chao Zhang</a>, <a href="/search/eess?searchtype=author&query=Woodland%2C+P">Phil Woodland</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.17010v4-abstract-short" style="display: inline;"> With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high performance on multiple tasks, since different speech and audio processing tasks usually require different training data, input features, or model architectures to achiev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17010v4-abstract-full').style.display = 'inline'; document.getElementById('2409.17010v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.17010v4-abstract-full" style="display: none;"> With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high performance on multiple tasks, since different speech and audio processing tasks usually require different training data, input features, or model architectures to achieve optimal performance. In this work, MT2KD, a novel two-stage multi-task learning framework is proposed to build a general-purpose speech and audio encoder that jointly performs three fundamental tasks: automatic speech recognition (ASR), audio tagging (AT) and speaker verification (SV). In the first stage, multi-teacher knowledge distillation (KD) is applied to align the feature spaces of three single-task high-performance teacher encoders into a single student encoder using the same unlabelled data. In the second stage, multi-task supervised fine-tuning is carried out by initialising the model from the first stage and training on the separate labelled data of each single task. Experiments demonstrate that the proposed multi-task training pipeline significantly outperforms a baseline model trained with multi-task learning from scratch. The final system achieves good performance on ASR, AT and SV: with less than 4% relative word-error-rate increase on ASR, only 1.9 lower mean averaged precision on AT and 0.23% absolute higher equal error rate on SV compared to the best-performing single-task encoders, using only a 66M total model parameters. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.17010v4-abstract-full').style.display = 'none'; document.getElementById('2409.17010v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16308">arXiv:2409.16308</a> <span> [<a href="https://arxiv.org/pdf/2409.16308">pdf</a>, <a href="https://arxiv.org/format/2409.16308">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Atmospheric and Oceanic Physics">physics.ao-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Analysis, Statistics and Probability">physics.data-an</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Probabilistic Spatiotemporal Modeling of Day-Ahead Wind Power Generation with Input-Warped Gaussian Processes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiqi Li</a>, <a href="/search/eess?searchtype=author&query=Ludkovski%2C+M">Mike Ludkovski</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.16308v1-abstract-short" style="display: inline;"> We design a Gaussian Process (GP) spatiotemporal model to capture features of day-ahead wind power forecasts. We work with hourly-scale day-ahead forecasts across hundreds of wind farm locations, with the main aim of constructing a fully probabilistic joint model across space and hours of the day. To this end, we design a separable space-time kernel, implementing both temporal and spatial input wa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16308v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16308v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16308v1-abstract-full" style="display: none;"> We design a Gaussian Process (GP) spatiotemporal model to capture features of day-ahead wind power forecasts. We work with hourly-scale day-ahead forecasts across hundreds of wind farm locations, with the main aim of constructing a fully probabilistic joint model across space and hours of the day. To this end, we design a separable space-time kernel, implementing both temporal and spatial input warping to capture the non-stationarity in the covariance of wind power. We conduct synthetic experiments to validate our choice of the spatial kernel and to demonstrate the effectiveness of warping in addressing nonstationarity. The second half of the paper is devoted to a detailed case study using a realistic, fully calibrated dataset representing wind farms in the ERCOT region of Texas. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16308v1-abstract-full').style.display = 'none'; document.getElementById('2409.16308v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">29 pages, 12 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.14874">arXiv:2409.14874</a> <span> [<a href="https://arxiv.org/pdf/2409.14874">pdf</a>, <a href="https://arxiv.org/format/2409.14874">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Towards Ground-truth-free Evaluation of Any Segmentation in Medical Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Senbi%2C+A">Ahjol Senbi</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+T">Tianyu Huang</a>, <a href="/search/eess?searchtype=author&query=Lyu%2C+F">Fei Lyu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qing Li</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+Y">Yuhui Tao</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+W">Wei Shao</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Q">Qiang Chen</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Chengyan Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shuo Wang</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+T">Tao Zhou</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yizhe Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.14874v2-abstract-short" style="display: inline;"> We explore the feasibility and potential of building a ground-truth-free evaluation model to assess the quality of segmentations generated by the Segment Anything Model (SAM) and its variants in medical imaging. This evaluation model estimates segmentation quality scores by analyzing the coherence and consistency between the input images and their corresponding segmentation predictions. Based on p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14874v2-abstract-full').style.display = 'inline'; document.getElementById('2409.14874v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.14874v2-abstract-full" style="display: none;"> We explore the feasibility and potential of building a ground-truth-free evaluation model to assess the quality of segmentations generated by the Segment Anything Model (SAM) and its variants in medical imaging. This evaluation model estimates segmentation quality scores by analyzing the coherence and consistency between the input images and their corresponding segmentation predictions. Based on prior research, we frame the task of training this model as a regression problem within a supervised learning framework, using Dice scores (and optionally other metrics) along with mean squared error to compute the training loss. The model is trained utilizing a large collection of public datasets of medical images with segmentation predictions from SAM and its variants. We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images). Our exploration of convolution-based models (e.g., ResNet) and transformer-based models (e.g., ViT) suggested that ViT yields better performance for this task. EvanySeg can be employed for various tasks, including: (1) identifying poorly segmented samples by detecting low-percentile segmentation quality scores; (2) benchmarking segmentation models without ground truth by averaging quality scores across test samples; (3) alerting human experts to poor-quality segmentation predictions during human-AI collaboration by applying a threshold within the score space; and (4) selecting the best segmentation prediction for each test sample at test time when multiple segmentation models are available, by choosing the prediction with the highest quality score. Models and code will be made available at https://github.com/ahjolsenbics/EvanySeg. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.14874v2-abstract-full').style.display = 'none'; document.getElementById('2409.14874v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">17 pages, 15 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.10226">arXiv:2409.10226</a> <span> [<a href="https://arxiv.org/pdf/2409.10226">pdf</a>, <a href="https://arxiv.org/format/2409.10226">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Privacy-Preserving Distributed Maximum Consensus Without Accuracy Loss </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+W">Wenrui Yu</a>, <a href="/search/eess?searchtype=author&query=Heusdens%2C+R">Richard Heusdens</a>, <a href="/search/eess?searchtype=author&query=Pang%2C+J">Jun Pang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiongxiu Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.10226v1-abstract-short" style="display: inline;"> In distributed networks, calculating the maximum element is a fundamental task in data analysis, known as the distributed maximum consensus problem. However, the sensitive nature of the data involved makes privacy protection essential. Despite its importance, privacy in distributed maximum consensus has received limited attention in the literature. Traditional privacy-preserving methods typically… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10226v1-abstract-full').style.display = 'inline'; document.getElementById('2409.10226v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.10226v1-abstract-full" style="display: none;"> In distributed networks, calculating the maximum element is a fundamental task in data analysis, known as the distributed maximum consensus problem. However, the sensitive nature of the data involved makes privacy protection essential. Despite its importance, privacy in distributed maximum consensus has received limited attention in the literature. Traditional privacy-preserving methods typically add noise to updates, degrading the accuracy of the final result. To overcome these limitations, we propose a novel distributed optimization-based approach that preserves privacy without sacrificing accuracy. Our method introduces virtual nodes to form an augmented graph and leverages a carefully designed initialization process to ensure the privacy of honest participants, even when all their neighboring nodes are dishonest. Through a comprehensive information-theoretical analysis, we derive a sufficient condition to protect private data against both passive and eavesdropping adversaries. Extensive experiments validate the effectiveness of our approach, demonstrating that it not only preserves perfect privacy but also maintains accuracy, outperforming existing noise-based methods that typically suffer from accuracy loss. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.10226v1-abstract-full').style.display = 'none'; document.getElementById('2409.10226v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07482">arXiv:2409.07482</a> <span> [<a href="https://arxiv.org/pdf/2409.07482">pdf</a>, <a href="https://arxiv.org/format/2409.07482">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> VSLLaVA: a pipeline of large multimodal foundation model for industrial vibration signal analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+J">Jinfeng Huang</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hongliang He</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xinran Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+F">Feibin Zhang</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+Z">Zhaoye Qin</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+F">Fulei Chu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.07482v1-abstract-short" style="display: inline;"> Large multimodal foundation models have been extensively utilized for image recognition tasks guided by instructions, yet there remains a scarcity of domain expertise in industrial vibration signal analysis. This paper presents a pipeline named VSLLaVA that leverages a large language model to integrate expert knowledge for identification of signal parameters and diagnosis of faults. Within this pi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07482v1-abstract-full').style.display = 'inline'; document.getElementById('2409.07482v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07482v1-abstract-full" style="display: none;"> Large multimodal foundation models have been extensively utilized for image recognition tasks guided by instructions, yet there remains a scarcity of domain expertise in industrial vibration signal analysis. This paper presents a pipeline named VSLLaVA that leverages a large language model to integrate expert knowledge for identification of signal parameters and diagnosis of faults. Within this pipeline, we first introduce an expert rule-assisted signal generator. The generator merges signal provided by vibration analysis experts with domain-specific parameter identification and fault diagnosis question-answer pairs to build signal-question-answer triplets. Then we use these triplets to apply low-rank adaptation methods for fine-tuning the linear layers of the Contrastive Language-Image Pretraining (CLIP) and large language model, injecting multimodal signal processing knowledge. Finally, the fine-tuned model is assessed through the combined efforts of large language model and expert rules to evaluate answer accuracy and relevance, which showcases enhanced performance in identifying, analyzing various signal parameters, and diagnosing faults. These enhancements indicate the potential of this pipeline to build a foundational model for future industrial signal analysis and monitoring. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07482v1-abstract-full').style.display = 'none'; document.getElementById('2409.07482v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.07020">arXiv:2409.07020</a> <span> [<a href="https://arxiv.org/pdf/2409.07020">pdf</a>, <a href="https://arxiv.org/format/2409.07020">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> DDEvENet: Evidence-based Ensemble Learning for Uncertainty-aware Brain Parcellation Using Diffusion MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+C">Chenjun Li</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+D">Dian Yang</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+S">Shun Yao</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shuyue Wang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Y">Ye Wu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Le Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiannuo Li</a>, <a href="/search/eess?searchtype=author&query=Cho%2C+K+I+K">Kang Ik Kevin Cho</a>, <a href="/search/eess?searchtype=author&query=Seitz-Holland%2C+J">Johanna Seitz-Holland</a>, <a href="/search/eess?searchtype=author&query=Ning%2C+L">Lipeng Ning</a>, <a href="/search/eess?searchtype=author&query=Legarreta%2C+J+H">Jon Haitz Legarreta</a>, <a href="/search/eess?searchtype=author&query=Rathi%2C+Y">Yogesh Rathi</a>, <a href="/search/eess?searchtype=author&query=Westin%2C+C">Carl-Fredrik Westin</a>, <a href="/search/eess?searchtype=author&query=O%27Donnell%2C+L+J">Lauren J. O'Donnell</a>, <a href="/search/eess?searchtype=author&query=Sochen%2C+N+A">Nir A. Sochen</a>, <a href="/search/eess?searchtype=author&query=Pasternak%2C+O">Ofer Pasternak</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+F">Fan Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.07020v2-abstract-short" style="display: inline;"> In this study, we developed an Evidence-based Ensemble Neural Network, namely EVENet, for anatomical brain parcellation using diffusion MRI. The key innovation of EVENet is the design of an evidential deep learning framework to quantify predictive uncertainty at each voxel during a single inference. To do so, we design an evidence-based ensemble learning framework for uncertainty-aware parcellatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07020v2-abstract-full').style.display = 'inline'; document.getElementById('2409.07020v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.07020v2-abstract-full" style="display: none;"> In this study, we developed an Evidence-based Ensemble Neural Network, namely EVENet, for anatomical brain parcellation using diffusion MRI. The key innovation of EVENet is the design of an evidential deep learning framework to quantify predictive uncertainty at each voxel during a single inference. To do so, we design an evidence-based ensemble learning framework for uncertainty-aware parcellation to leverage the multiple dMRI parameters derived from diffusion MRI. Using EVENet, we obtained accurate parcellation and uncertainty estimates across different datasets from healthy and clinical populations and with different imaging acquisitions. The overall network includes five parallel subnetworks, where each is dedicated to learning the FreeSurfer parcellation for a certain diffusion MRI parameter. An evidence-based ensemble methodology is then proposed to fuse the individual outputs. We perform experimental evaluations on large-scale datasets from multiple imaging sources, including high-quality diffusion MRI data from healthy adults and clinically diffusion MRI data from participants with various brain diseases (schizophrenia, bipolar disorder, attention-deficit/hyperactivity disorder, Parkinson's disease, cerebral small vessel disease, and neurosurgical patients with brain tumors). Compared to several state-of-the-art methods, our experimental results demonstrate highly improved parcellation accuracy across the multiple testing datasets despite the differences in dMRI acquisition protocols and health conditions. Furthermore, thanks to the uncertainty estimation, our EVENet approach demonstrates a good ability to detect abnormal brain regions in patients with lesions, enhancing the interpretability and reliability of the segmentation results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.07020v2-abstract-full').style.display = 'none'; document.getElementById('2409.07020v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.00204">arXiv:2409.00204</a> <span> [<a href="https://arxiv.org/pdf/2409.00204">pdf</a>, <a href="https://arxiv.org/format/2409.00204">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zeyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Yi%2C+N">Nengmin Yi</a>, <a href="/search/eess?searchtype=author&query=Tan%2C+S">Shengbo Tan</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+Y">Ying Cai</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Y">Yi Yang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+L">Lei Xu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingtai Li</a>, <a href="/search/eess?searchtype=author&query=Yi%2C+Z">Zhang Yi</a>, <a href="/search/eess?searchtype=author&query=Ergu%2C+D">Daji Ergu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+Y">Yang Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.00204v2-abstract-short" style="display: inline;"> Cervical disc herniation (CDH) is a prevalent musculoskeletal disorder that significantly impacts health and requires labor-intensive analysis from experts. Despite advancements in automated detection of medical imaging, two significant challenges hinder the real-world application of these methods. First, the computational complexity and resource demands present a significant gap for real-time app… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00204v2-abstract-full').style.display = 'inline'; document.getElementById('2409.00204v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00204v2-abstract-full" style="display: none;"> Cervical disc herniation (CDH) is a prevalent musculoskeletal disorder that significantly impacts health and requires labor-intensive analysis from experts. Despite advancements in automated detection of medical imaging, two significant challenges hinder the real-world application of these methods. First, the computational complexity and resource demands present a significant gap for real-time application. Second, noise in MRI reduces the effectiveness of existing methods by distorting feature extraction. To address these challenges, we propose three key contributions: Firstly, we introduced MedDet, which leverages the multi-teacher single-student knowledge distillation for model compression and efficiency, meanwhile integrating generative adversarial training to enhance performance. Additionally, we customize the second-order nmODE to improve the model's resistance to noise in MRI. Lastly, we conducted comprehensive experiments on the CDH-1848 dataset, achieving up to a 5% improvement in mAP compared to previous methods. Our approach also delivers over 5 times faster inference speed, with approximately 67.8% reduction in parameters and 36.9% reduction in FLOPs compared to the teacher model. These advancements significantly enhance the performance and efficiency of automated CDH detection, demonstrating promising potential for future application in clinical practice. See project website https://steve-zeyu-zhang.github.io/MedDet <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00204v2-abstract-full').style.display = 'none'; document.getElementById('2409.00204v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to BIBM 2024 Oral</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13689">arXiv:2408.13689</a> <span> [<a href="https://arxiv.org/pdf/2408.13689">pdf</a>, <a href="https://arxiv.org/format/2408.13689">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Decentralised Variational Inference Frameworks for Multi-object Tracking on Sensor Networks: Additional Notes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qing Li</a>, <a href="/search/eess?searchtype=author&query=Gan%2C+R">Runze Gan</a>, <a href="/search/eess?searchtype=author&query=Godsill%2C+S">Simon Godsill</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.13689v4-abstract-short" style="display: inline;"> This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges among neighboring sensors. We first establish a centralised VI sensor fusion scheme as a benchmark and analyse the limitations of its decentralised counterpart,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13689v4-abstract-full').style.display = 'inline'; document.getElementById('2408.13689v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13689v4-abstract-full" style="display: none;"> This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges among neighboring sensors. We first establish a centralised VI sensor fusion scheme as a benchmark and analyse the limitations of its decentralised counterpart, which requires sensors to await consensus at each VI iteration. Therefore, we propose a decentralised gradient-based VI framework that optimises the Locally Maximised Evidence Lower Bound (LM-ELBO) instead of the standard ELBO, which reduces the parameter search space and enables faster convergence, making it particularly beneficial for decentralised tracking. This proposed framework is inherently self-evolving, improving with advancements in decentralised optimisation techniques for convergence guarantees and efficiency. Further, we enhance the convergence speed of proposed decentralised schemes using natural gradients and gradient tracking strategies. Results verify that our decentralised VI schemes are empirically equivalent to centralised fusion in tracking performance. Notably, the decentralised natural gradient VI method is the most communication-efficient, with communication costs comparable to suboptimal decentralised strategies while delivering notably higher tracking accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13689v4-abstract-full').style.display = 'none'; document.getElementById('2408.13689v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.12813">arXiv:2408.12813</a> <span> [<a href="https://arxiv.org/pdf/2408.12813">pdf</a>, <a href="https://arxiv.org/ps/2408.12813">ps</a>, <a href="https://arxiv.org/format/2408.12813">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Minimizing Movement Delay for Movable Antennas via Trajectory Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingliang Li</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+W">Weidong Mei</a>, <a href="/search/eess?searchtype=author&query=Ning%2C+B">Boyu Ning</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rui Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.12813v1-abstract-short" style="display: inline;"> Movable antennas (MAs) have received increasing attention in wireless communications due to their capability of antenna position adjustment to reconfigure wireless channels. However, moving MAs results in non-negligible delay, which may decrease the effective data transmission time. To reduce the movement delay, we study in this paper a new MA trajectory optimization problem. In particular, given… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12813v1-abstract-full').style.display = 'inline'; document.getElementById('2408.12813v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.12813v1-abstract-full" style="display: none;"> Movable antennas (MAs) have received increasing attention in wireless communications due to their capability of antenna position adjustment to reconfigure wireless channels. However, moving MAs results in non-negligible delay, which may decrease the effective data transmission time. To reduce the movement delay, we study in this paper a new MA trajectory optimization problem. In particular, given the desired destination positions of multiple MAs, we aim to jointly optimize their associations with the initial MA positions and the trajectories for moving them from their respective initial to destination positions within a given two-dimensional (2D) region, such that the delay of antenna movement is minimized, subject to the inter-MA minimum distance constraints in the movement. However, this problem is a continuous-time mixed-integer linear programming (MILP) problem that is challenging to solve. To tackle this challenge, we propose a two-stage optimization framework that sequentially optimizes the MAs' position associations and trajectories, respectively. First, we relax the inter-MA distance constraints and optimally solve the resulted delay minimization problem. Next, we check if the obtained MA association and trajectory solutions satisfy the inter-MA distance constraints. If not satisfied, we then employ a successive convex approximation (SCA) algorithm to adjust the MAs' trajectories until they satisfy the given constraints. Simulation results are provided to show the effectiveness of our proposed trajectory optimization method in reducing the movement delay as well as draw useful insights. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.12813v1-abstract-full').style.display = 'none'; document.getElementById('2408.12813v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages,6 figures, submit to GLOBECOM 2024 Workshop - IRAFWCC</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.04283">arXiv:2408.04283</a> <span> [<a href="https://arxiv.org/pdf/2408.04283">pdf</a>, <a href="https://arxiv.org/format/2408.04283">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Prompt-Assisted Semantic Interference Cancellation on Moderate Interference Channels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Meng%2C+Z">Zian Meng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiang Li</a>, <a href="/search/eess?searchtype=author&query=Pandharipande%2C+A">Ashish Pandharipande</a>, <a href="/search/eess?searchtype=author&query=Ge%2C+X">Xiaohu Ge</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.04283v1-abstract-short" style="display: inline;"> The performance of conventional interference management strategies degrades when interference power is comparable to signal power. We consider a new perspective on interference management using semantic communication. Specifically, a multi-user semantic communication system is considered on moderate interference channels (ICs), for which a novel framework of deep learning-based prompt-assisted sem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04283v1-abstract-full').style.display = 'inline'; document.getElementById('2408.04283v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.04283v1-abstract-full" style="display: none;"> The performance of conventional interference management strategies degrades when interference power is comparable to signal power. We consider a new perspective on interference management using semantic communication. Specifically, a multi-user semantic communication system is considered on moderate interference channels (ICs), for which a novel framework of deep learning-based prompt-assisted semantic interference cancellation (DeepPASIC) is proposed. Each transmitted signal is partitioned into common and private parts. The common parts of different users are transmitted simultaneously in a shared medium, resulting in superposition. The private part, on the other hand, serves as a prompt to assist in canceling the interference suffered by the common part at the semantic level. Simulation results demonstrate that the proposed DeepPASIC outperforms conventional interference management strategies under moderate interference conditions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.04283v1-abstract-full').style.display = 'none'; document.getElementById('2408.04283v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.02765">arXiv:2408.02765</a> <span> [<a href="https://arxiv.org/pdf/2408.02765">pdf</a>, <a href="https://arxiv.org/format/2408.02765">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Learning with Adaptive Conservativeness for Distributionally Robust Optimization: Incentive Design for Voltage Regulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liang%2C+Z">Zhirui Liang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Comden%2C+J">Joshua Comden</a>, <a href="/search/eess?searchtype=author&query=Bernstein%2C+A">Andrey Bernstein</a>, <a href="/search/eess?searchtype=author&query=Dvorkin%2C+Y">Yury Dvorkin</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.02765v1-abstract-short" style="display: inline;"> Information asymmetry between the Distribution System Operator (DSO) and Distributed Energy Resource Aggregators (DERAs) obstructs designing effective incentives for voltage regulation. To capture this effect, we employ a Stackelberg game-theoretic framework, where the DSO seeks to overcome the information asymmetry and refine its incentive strategies by learning from DERA behavior over multiple i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02765v1-abstract-full').style.display = 'inline'; document.getElementById('2408.02765v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02765v1-abstract-full" style="display: none;"> Information asymmetry between the Distribution System Operator (DSO) and Distributed Energy Resource Aggregators (DERAs) obstructs designing effective incentives for voltage regulation. To capture this effect, we employ a Stackelberg game-theoretic framework, where the DSO seeks to overcome the information asymmetry and refine its incentive strategies by learning from DERA behavior over multiple iterations. We introduce a model-based online learning algorithm for the DSO, aimed at inferring the relationship between incentives and DERA responses. Given the uncertain nature of these responses, we also propose a distributionally robust incentive design model to control the probability of voltage regulation failure and then reformulate it into a convex problem. This model allows the DSO to periodically revise distribution assumptions on uncertain parameters in the decision model of the DERA. Finally, we present a gradient-based method that permits the DSO to adaptively modify its conservativeness level, measured by the size of a Wasserstein metric-based ambiguity set, according to historical voltage regulation performance. The effectiveness of our proposed method is demonstrated through numerical experiments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02765v1-abstract-full').style.display = 'none'; document.getElementById('2408.02765v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper was accepted for publication and presentation in the Proceedings of the IEEE Control and Decision Conference in Milano, Italy 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.12780">arXiv:2407.12780</a> <span> [<a href="https://arxiv.org/pdf/2407.12780">pdf</a>, <a href="https://arxiv.org/format/2407.12780">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Hallucination Index: An Image Quality Metric for Generative Reconstruction Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Tivnan%2C+M">Matthew Tivnan</a>, <a href="/search/eess?searchtype=author&query=Yoon%2C+S">Siyeop Yoon</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhennong Chen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+D">Dufan Wu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.12780v1-abstract-short" style="display: inline;"> Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful models can transform low signal-to-noise ratio (SNR) inputs into outputs with the appearance of high SNR. However, the outputs can have a new type of error called hallucinations. In medical imaging, these hallucinations may not be obvi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12780v1-abstract-full').style.display = 'inline'; document.getElementById('2407.12780v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.12780v1-abstract-full" style="display: none;"> Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful models can transform low signal-to-noise ratio (SNR) inputs into outputs with the appearance of high SNR. However, the outputs can have a new type of error called hallucinations. In medical imaging, these hallucinations may not be obvious to a Radiologist but could cause diagnostic errors. Generally, hallucination refers to error in estimation of object structure caused by a machine learning model, but there is no widely accepted method to evaluate hallucination magnitude. In this work, we propose a new image quality metric called the hallucination index. Our approach is to compute the Hellinger distance from the distribution of reconstructed images to a zero hallucination reference distribution. To evaluate our approach, we conducted a numerical experiment with electron microscopy images, simulated noisy measurements, and applied diffusion based reconstructions. We sampled the measurements and the generative reconstructions repeatedly to compute the sample mean and covariance. For the zero hallucination reference, we used the forward diffusion process applied to ground truth. Our results show that higher measurement SNR leads to lower hallucination index for the same apparent image quality. We also evaluated the impact of early stopping in the reverse diffusion process and found that more modest denoising strengths can reduce hallucination. We believe this metric could be useful for evaluation of generative image reconstructions or as a warning label to inform radiologists about the degree of hallucinations in medical images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.12780v1-abstract-full').style.display = 'none'; document.getElementById('2407.12780v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.11705">arXiv:2407.11705</a> <span> [<a href="https://arxiv.org/pdf/2407.11705">pdf</a>, <a href="https://arxiv.org/format/2407.11705">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Snail-Radar: A large-scale diverse dataset for the evaluation of 4D-radar-based SLAM systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huai%2C+J">Jianzhu Huai</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+B">Binliang Wang</a>, <a href="/search/eess?searchtype=author&query=Zhuang%2C+Y">Yuan Zhuang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Yiwen Chen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qipeng Li</a>, <a href="/search/eess?searchtype=author&query=Han%2C+Y">Yulong Han</a>, <a href="/search/eess?searchtype=author&query=Toth%2C+C">Charles Toth</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.11705v2-abstract-short" style="display: inline;"> 4D radars are increasingly favored for odometry and mapping of autonomous systems due to their robustness in harsh weather and dynamic environments. Existing datasets, however, often cover limited areas and are typically captured using a single platform. To address this gap, we present a diverse large-scale dataset specifically designed for 4D radar-based localization and mapping. This dataset was… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11705v2-abstract-full').style.display = 'inline'; document.getElementById('2407.11705v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.11705v2-abstract-full" style="display: none;"> 4D radars are increasingly favored for odometry and mapping of autonomous systems due to their robustness in harsh weather and dynamic environments. Existing datasets, however, often cover limited areas and are typically captured using a single platform. To address this gap, we present a diverse large-scale dataset specifically designed for 4D radar-based localization and mapping. This dataset was gathered using three different platforms: a handheld device, an e-bike, and an SUV, under a variety of environmental conditions, including clear days, nighttime, and heavy rain. The data collection occurred from September 2023 to February 2024, encompassing diverse settings such as roads in a vegetated campus and tunnels on highways. Each route was traversed multiple times to facilitate place recognition evaluations. The sensor suite included a 3D lidar, 4D radars, stereo cameras, consumer-grade IMUs, and a GNSS/INS system. Sensor data packets were synchronized to GNSS time using a two-step process: a convex hull algorithm was applied to smooth host time jitter, and then odometry and correlation algorithms were used to correct constant time offsets. Extrinsic calibration between sensors was achieved through manual measurements and subsequent nonlinear optimization. The reference motion for the platforms was generated by registering lidar scans to a terrestrial laser scanner (TLS) point cloud map using a lidar inertial odometry (LIO) method in localization mode. Additionally, a data reversion technique was introduced to enable backward LIO processing. We believe this dataset will boost research in radar-based point cloud registration, odometry, mapping, and place recognition. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11705v2-abstract-full').style.display = 'none'; document.getElementById('2407.11705v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 4 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.09540">arXiv:2407.09540</a> <span> [<a href="https://arxiv.org/pdf/2407.09540">pdf</a>, <a href="https://arxiv.org/format/2407.09540">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> Prompting Whole Slide Image Based Genetic Biomarker Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Ling Zhang</a>, <a href="/search/eess?searchtype=author&query=Yun%2C+B">Boxiang Yun</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+X">Xingran Xie</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingli Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xinxing Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.09540v1-abstract-short" style="display: inline;"> Prediction of genetic biomarkers, e.g., microsatellite instability and BRAF in colorectal cancer is crucial for clinical decision making. In this paper, we propose a whole slide image (WSI) based genetic biomarker prediction method via prompting techniques. Our work aims at addressing the following challenges: (1) extracting foreground instances related to genetic biomarkers from gigapixel WSIs, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09540v1-abstract-full').style.display = 'inline'; document.getElementById('2407.09540v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.09540v1-abstract-full" style="display: none;"> Prediction of genetic biomarkers, e.g., microsatellite instability and BRAF in colorectal cancer is crucial for clinical decision making. In this paper, we propose a whole slide image (WSI) based genetic biomarker prediction method via prompting techniques. Our work aims at addressing the following challenges: (1) extracting foreground instances related to genetic biomarkers from gigapixel WSIs, and (2) the interaction among the fine-grained pathological components in WSIs.Specifically, we leverage large language models to generate medical prompts that serve as prior knowledge in extracting instances associated with genetic biomarkers. We adopt a coarse-to-fine approach to mine biomarker information within the tumor microenvironment. This involves extracting instances related to genetic biomarkers using coarse medical prior knowledge, grouping pathology instances into fine-grained pathological components and mining their interactions. Experimental results on two colorectal cancer datasets show the superiority of our method, achieving 91.49% in AUC for MSI classification. The analysis further shows the clinical interpretability of our method. Code is publicly available at https://github.com/DeepMed-Lab-ECNU/PromptBio. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09540v1-abstract-full').style.display = 'none'; document.getElementById('2407.09540v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 3 figures, MICCAI2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.08944">arXiv:2407.08944</a> <span> [<a href="https://arxiv.org/pdf/2407.08944">pdf</a>, <a href="https://arxiv.org/format/2407.08944">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Bora: Biomedical Generalist Video Generation Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+W">Weixiang Sun</a>, <a href="/search/eess?searchtype=author&query=You%2C+X">Xiaocao You</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+R">Ruizhe Zheng</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+Z">Zhengqing Yuan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a>, <a href="/search/eess?searchtype=author&query=He%2C+L">Lifang He</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+L">Lichao Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.08944v2-abstract-short" style="display: inline;"> Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for medical AI development. Diffusion models can now generate realistic images from text prompts, while recent advancements have demonstrated their ability to create diverse, high-quality videos. However, these models often struggle with generating accurate representations of medical… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08944v2-abstract-full').style.display = 'inline'; document.getElementById('2407.08944v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08944v2-abstract-full" style="display: none;"> Generative models hold promise for revolutionizing medical education, robot-assisted surgery, and data augmentation for medical AI development. Diffusion models can now generate realistic images from text prompts, while recent advancements have demonstrated their ability to create diverse, high-quality videos. However, these models often struggle with generating accurate representations of medical procedures and detailed anatomical structures. This paper introduces Bora, the first spatio-temporal diffusion probabilistic model designed for text-guided biomedical video generation. Bora leverages Transformer architecture and is pre-trained on general-purpose video generation tasks. It is fine-tuned through model alignment and instruction tuning using a newly established medical video corpus, which includes paired text-video data from various biomedical fields. To the best of our knowledge, this is the first attempt to establish such a comprehensive annotated biomedical video dataset. Bora is capable of generating high-quality video data across four distinct biomedical domains, adhering to medical expert standards and demonstrating consistency and diversity. This generalist video generative model holds significant potential for enhancing medical consultation and decision-making, particularly in resource-limited settings. Additionally, Bora could pave the way for immersive medical training and procedure planning. Extensive experiments on distinct medical modalities such as endoscopy, ultrasound, MRI, and cell tracking validate the effectiveness of our model in understanding biomedical instructions and its superior performance across subjects compared to state-of-the-art generation models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08944v2-abstract-full').style.display = 'none'; document.getElementById('2407.08944v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.08252">arXiv:2407.08252</a> <span> [<a href="https://arxiv.org/pdf/2407.08252">pdf</a>, <a href="https://arxiv.org/format/2407.08252">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Spatially-Variant Degradation Model for Dataset-free Super-resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+S">Shaojie Guo</a>, <a href="/search/eess?searchtype=author&query=Song%2C+H">Haofei Song</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingli Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.08252v1-abstract-short" style="display: inline;"> This paper focuses on the dataset-free Blind Image Super-Resolution (BISR). Unlike existing dataset-free BISR methods that focus on obtaining a degradation kernel for the entire image, we are the first to explicitly design a spatially-variant degradation model for each pixel. Our method also benefits from having a significantly smaller number of learnable parameters compared to data-driven spatial… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08252v1-abstract-full').style.display = 'inline'; document.getElementById('2407.08252v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08252v1-abstract-full" style="display: none;"> This paper focuses on the dataset-free Blind Image Super-Resolution (BISR). Unlike existing dataset-free BISR methods that focus on obtaining a degradation kernel for the entire image, we are the first to explicitly design a spatially-variant degradation model for each pixel. Our method also benefits from having a significantly smaller number of learnable parameters compared to data-driven spatially-variant BISR methods. Concretely, each pixel's degradation kernel is expressed as a linear combination of a learnable dictionary composed of a small number of spatially-variant atom kernels. The coefficient matrices of the atom degradation kernels are derived using membership functions of fuzzy set theory. We construct a novel Probabilistic BISR model with tailored likelihood function and prior terms. Subsequently, we employ the Monte Carlo EM algorithm to infer the degradation kernels for each pixel. Our method achieves a significant improvement over other state-of-the-art BISR methods, with an average improvement of 1 dB (2x).Code will be released at https://github.com/shaojieguoECNU/SVDSR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08252v1-abstract-full').style.display = 'none'; document.getElementById('2407.08252v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.05767">arXiv:2407.05767</a> <span> [<a href="https://arxiv.org/pdf/2407.05767">pdf</a>, <a href="https://arxiv.org/format/2407.05767">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1007/978-3-031-72083-3_64">10.1007/978-3-031-72083-3_64 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Nonrigid Reconstruction of Freehand Ultrasound without a Tracker </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Shen%2C+Z">Ziyi Shen</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qianye Yang</a>, <a href="/search/eess?searchtype=author&query=Barratt%2C+D+C">Dean C. Barratt</a>, <a href="/search/eess?searchtype=author&query=Clarkson%2C+M+J">Matthew J. Clarkson</a>, <a href="/search/eess?searchtype=author&query=Vercauteren%2C+T">Tom Vercauteren</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Y">Yipeng Hu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.05767v2-abstract-short" style="display: inline;"> Reconstructing 2D freehand Ultrasound (US) frames into 3D space without using a tracker has recently seen advances with deep learning. Predicting good frame-to-frame rigid transformations is often accepted as the learning objective, especially when the ground-truth labels from spatial tracking devices are inherently rigid transformations. Motivated by a) the observed nonrigid deformation due to so… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05767v2-abstract-full').style.display = 'inline'; document.getElementById('2407.05767v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.05767v2-abstract-full" style="display: none;"> Reconstructing 2D freehand Ultrasound (US) frames into 3D space without using a tracker has recently seen advances with deep learning. Predicting good frame-to-frame rigid transformations is often accepted as the learning objective, especially when the ground-truth labels from spatial tracking devices are inherently rigid transformations. Motivated by a) the observed nonrigid deformation due to soft tissue motion during scanning, and b) the highly sensitive prediction of rigid transformation, this study investigates the methods and their benefits in predicting nonrigid transformations for reconstructing 3D US. We propose a novel co-optimisation algorithm for simultaneously estimating rigid transformations among US frames, supervised by ground-truth from a tracker, and a nonrigid deformation, optimised by a regularised registration network. We show that these two objectives can be either optimised using meta-learning or combined by weighting. A fast scattered data interpolation is also developed for enabling frequent reconstruction and registration of non-parallel US frames, during training. With a new data set containing over 357,000 frames in 720 scans, acquired from 60 subjects, the experiments demonstrate that, due to an expanded thus easier-to-optimise solution space, the generalisation is improved with the added deformation estimation, with respect to the rigid ground-truth. The global pixel reconstruction error (assessing accumulative prediction) is lowered from 18.48 to 16.51 mm, compared with baseline rigid-transformation-predicting methods. Using manually identified landmarks, the proposed co-optimisation also shows potentials in compensating nonrigid tissue motion at inference, which is not measurable by tracker-provided ground-truth. The code and data used in this paper are made publicly available at https://github.com/QiLi111/NR-Rec-FUS. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.05767v2-abstract-full').style.display = 'none'; document.getElementById('2407.05767v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at MICCAI 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.04162">arXiv:2407.04162</a> <span> [<a href="https://arxiv.org/pdf/2407.04162">pdf</a>, <a href="https://arxiv.org/format/2407.04162">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Measurement Embedded Schr枚dinger Bridge for Inverse Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuang Wang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Pengfei Jin</a>, <a href="/search/eess?searchtype=author&query=Yoon%2C+S">Siyeop Yoon</a>, <a href="/search/eess?searchtype=author&query=Tivnan%2C+M">Matthew Tivnan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+D">Dufan Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.04162v1-abstract-short" style="display: inline;"> Score-based diffusion models are frequently employed as structural priors in inverse problems. However, their iterative denoising process, initiated from Gaussian noise, often results in slow inference speeds. The Image-to-Image Schr枚dinger Bridge (I$^2$SB), which begins with the corrupted image, presents a promising alternative as a prior for addressing inverse problems. In this work, we introduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04162v1-abstract-full').style.display = 'inline'; document.getElementById('2407.04162v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.04162v1-abstract-full" style="display: none;"> Score-based diffusion models are frequently employed as structural priors in inverse problems. However, their iterative denoising process, initiated from Gaussian noise, often results in slow inference speeds. The Image-to-Image Schr枚dinger Bridge (I$^2$SB), which begins with the corrupted image, presents a promising alternative as a prior for addressing inverse problems. In this work, we introduce the Measurement Embedded Schr枚dinger Bridge (MESB). MESB establishes Schr枚dinger Bridges between the distribution of corrupted images and the distribution of clean images given observed measurements. Based on optimal transport theory, we derive the forward and backward processes of MESB. Through validation on diverse inverse problems, our proposed approach exhibits superior performance compared to existing Schr枚dinger Bridge-based inverse problems solvers in both visual quality and quantitative metrics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04162v1-abstract-full').style.display = 'none'; document.getElementById('2407.04162v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 2 figures, Neurips preprint</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19311">arXiv:2406.19311</a> <span> [<a href="https://arxiv.org/pdf/2406.19311">pdf</a>, <a href="https://arxiv.org/format/2406.19311">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Fang%2C+Z">Zheng Fang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+T">Tao Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+L">Lingchen Zhao</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shenyi Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+B">Bowen Li</a>, <a href="/search/eess?searchtype=author&query=Ge%2C+Y">Yunjie Ge</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Shen%2C+C">Chao Shen</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Q">Qian Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.19311v1-abstract-short" style="display: inline;"> In recent years, extensive research has been conducted on the vulnerability of ASR systems, revealing that black-box adversarial example attacks pose significant threats to real-world ASR systems. However, most existing black-box attacks rely on queries to the target ASRs, which is impractical when queries are not permitted. In this paper, we propose ZQ-Attack, a transfer-based adversarial attack… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19311v1-abstract-full').style.display = 'inline'; document.getElementById('2406.19311v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19311v1-abstract-full" style="display: none;"> In recent years, extensive research has been conducted on the vulnerability of ASR systems, revealing that black-box adversarial example attacks pose significant threats to real-world ASR systems. However, most existing black-box attacks rely on queries to the target ASRs, which is impractical when queries are not permitted. In this paper, we propose ZQ-Attack, a transfer-based adversarial attack on ASR systems in the zero-query black-box setting. Through a comprehensive review and categorization of modern ASR technologies, we first meticulously select surrogate ASRs of diverse types to generate adversarial examples. Following this, ZQ-Attack initializes the adversarial perturbation with a scaled target command audio, rendering it relatively imperceptible while maintaining effectiveness. Subsequently, to achieve high transferability of adversarial perturbations, we propose a sequential ensemble optimization algorithm, which iteratively optimizes the adversarial perturbation on each surrogate model, leveraging collaborative information from other models. We conduct extensive experiments to evaluate ZQ-Attack. In the over-the-line setting, ZQ-Attack achieves a 100% success rate of attack (SRoA) with an average signal-to-noise ratio (SNR) of 21.91dB on 4 online speech recognition services, and attains an average SRoA of 100% and SNR of 19.67dB on 16 open-source ASRs. For commercial intelligent voice control devices, ZQ-Attack also achieves a 100% SRoA with an average SNR of 15.77dB in the over-the-air setting. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19311v1-abstract-full').style.display = 'none'; document.getElementById('2406.19311v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">To appear in the Proceedings of The ACM Conference on Computer and Communications Security (CCS), 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19043">arXiv:2406.19043</a> <span> [<a href="https://arxiv.org/pdf/2406.19043">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> CMRxRecon2024: A Multi-Modality, Multi-View K-Space Dataset Boosting Universal Machine Learning for Accelerated Cardiac MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zi Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+F">Fanwen Wang</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+C">Chen Qin</a>, <a href="/search/eess?searchtype=author&query=Lyu%2C+J">Jun Lyu</a>, <a href="/search/eess?searchtype=author&query=Ouyang%2C+C">Cheng Ouyang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shuo Wang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yan Li</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+M">Mengyao Yu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Haoyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+K">Kunyuan Guo</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Z">Zhang Shi</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qirong Li</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Z">Ziqiang Xu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yajing Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+H">Hao Li</a>, <a href="/search/eess?searchtype=author&query=Hua%2C+S">Sha Hua</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+B">Binghua Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+L">Longyu Sun</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+M">Mengting Sun</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qin Li</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+Y">Ying-Hua Chu</a>, <a href="/search/eess?searchtype=author&query=Bai%2C+W">Wenjia Bai</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+J">Jing Qin</a>, <a href="/search/eess?searchtype=author&query=Zhuang%2C+X">Xiahai Zhuang</a>, <a href="/search/eess?searchtype=author&query=Prieto%2C+C">Claudia Prieto</a> , et al. (7 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.19043v2-abstract-short" style="display: inline;"> Cardiac magnetic resonance imaging (MRI) has emerged as a clinically gold-standard technique for diagnosing cardiac diseases, thanks to its ability to provide diverse information with multiple modalities and anatomical views. Accelerated cardiac MRI is highly expected to achieve time-efficient and patient-friendly imaging, and then advanced image reconstruction approaches are required to recover h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19043v2-abstract-full').style.display = 'inline'; document.getElementById('2406.19043v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19043v2-abstract-full" style="display: none;"> Cardiac magnetic resonance imaging (MRI) has emerged as a clinically gold-standard technique for diagnosing cardiac diseases, thanks to its ability to provide diverse information with multiple modalities and anatomical views. Accelerated cardiac MRI is highly expected to achieve time-efficient and patient-friendly imaging, and then advanced image reconstruction approaches are required to recover high-quality, clinically interpretable images from undersampled measurements. However, the lack of publicly available cardiac MRI k-space dataset in terms of both quantity and diversity has severely hindered substantial technological progress, particularly for data-driven artificial intelligence. Here, we provide a standardized, diverse, and high-quality CMRxRecon2024 dataset to facilitate the technical development, fair evaluation, and clinical transfer of cardiac MRI reconstruction approaches, towards promoting the universal frameworks that enable fast and robust reconstructions across different cardiac MRI protocols in clinical practice. To the best of our knowledge, the CMRxRecon2024 dataset is the largest and most protocal-diverse publicly available cardiac k-space dataset. It is acquired from 330 healthy volunteers, covering commonly used modalities, anatomical views, and acquisition trajectories in clinical cardiac MRI workflows. Besides, an open platform with tutorials, benchmarks, and data processing tools is provided to facilitate data usage, advanced method development, and fair performance evaluation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19043v2-abstract-full').style.display = 'none'; document.getElementById('2406.19043v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">23 pages, 3 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.14869">arXiv:2406.14869</a> <span> [<a href="https://arxiv.org/pdf/2406.14869">pdf</a>, <a href="https://arxiv.org/format/2406.14869">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Cost-Effective RF Fingerprinting Based on Hybrid CVNN-RF Classifier with Automated Multi-Dimensional Early-Exit Strategy </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gan%2C+J">Jiayan Gan</a>, <a href="/search/eess?searchtype=author&query=Du%2C+Z">Zhixing Du</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qiang Li</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+H">Huaizong Shao</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+J">Jingran Lin</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+Y">Ye Pan</a>, <a href="/search/eess?searchtype=author&query=Wen%2C+Z">Zhongyi Wen</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shafei Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.14869v1-abstract-short" style="display: inline;"> While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical layer security technologies for IoT, radio frequency fingerprinting (RFF) is of great interest due to its difficulty in counterfeiting. Recently, many machine learning (ML)-based RFF algorithms h… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14869v1-abstract-full').style.display = 'inline'; document.getElementById('2406.14869v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.14869v1-abstract-full" style="display: none;"> While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical layer security technologies for IoT, radio frequency fingerprinting (RFF) is of great interest due to its difficulty in counterfeiting. Recently, many machine learning (ML)-based RFF algorithms have emerged. In particular, deep learning (DL) has shown great benefits in automatically extracting complex and subtle features from raw data with high classification accuracy. However, DL algorithms face the computational cost problem as the difficulty of the RFF task and the size of the DNN have increased dramatically. To address the above challenge, this paper proposes a novel costeffective early-exit neural network consisting of a complex-valued neural network (CVNN) backbone with multiple random forest branches, called hybrid CVNN-RF. Unlike conventional studies that use a single fixed DL model to process all RF samples, our hybrid CVNN-RF considers differences in the recognition difficulty of RF samples and introduces an early-exit mechanism to dynamically process the samples. When processing "easy" samples that can be well classified with high confidence, the hybrid CVNN-RF can end early at the random forest branch to reduce computational cost. Conversely, subsequent network layers will be activated to ensure accuracy. To further improve the early-exit rate, an automated multi-dimensional early-exit strategy is proposed to achieve scheduling control from multiple dimensions within the network depth and classification category. Finally, our experiments on the public ADS-B dataset show that the proposed algorithm can reduce the computational cost by 83% while improving the accuracy by 1.6% under a classification task with 100 categories. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.14869v1-abstract-full').style.display = 'none'; document.getElementById('2406.14869v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by IEEE Internet of Things Journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.12646">arXiv:2406.12646</a> <span> [<a href="https://arxiv.org/pdf/2406.12646">pdf</a>, <a href="https://arxiv.org/format/2406.12646">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> An Empirical Study on the Fairness of Foundation Models for Multi-Organ Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qin Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yizhe Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yan Li</a>, <a href="/search/eess?searchtype=author&query=Lyu%2C+J">Jun Lyu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+M">Meng Liu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+L">Longyu Sun</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+M">Mengting Sun</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qirong Li</a>, <a href="/search/eess?searchtype=author&query=Mao%2C+W">Wenyue Mao</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+X">Xinran Wu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yajing Zhang</a>, <a href="/search/eess?searchtype=author&query=Chu%2C+Y">Yinghua Chu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+S">Shuo Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Chengyan Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.12646v1-abstract-short" style="display: inline;"> The segmentation foundation model, e.g., Segment Anything Model (SAM), has attracted increasing interest in the medical image community. Early pioneering studies primarily concentrated on assessing and improving SAM's performance from the perspectives of overall accuracy and efficiency, yet little attention was given to the fairness considerations. This oversight raises questions about the potenti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.12646v1-abstract-full').style.display = 'inline'; document.getElementById('2406.12646v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.12646v1-abstract-full" style="display: none;"> The segmentation foundation model, e.g., Segment Anything Model (SAM), has attracted increasing interest in the medical image community. Early pioneering studies primarily concentrated on assessing and improving SAM's performance from the perspectives of overall accuracy and efficiency, yet little attention was given to the fairness considerations. This oversight raises questions about the potential for performance biases that could mirror those found in task-specific deep learning models like nnU-Net. In this paper, we explored the fairness dilemma concerning large segmentation foundation models. We prospectively curate a benchmark dataset of 3D MRI and CT scans of the organs including liver, kidney, spleen, lung and aorta from a total of 1056 healthy subjects with expert segmentations. Crucially, we document demographic details such as gender, age, and body mass index (BMI) for each subject to facilitate a nuanced fairness analysis. We test state-of-the-art foundation models for medical image segmentation, including the original SAM, medical SAM and SAT models, to evaluate segmentation efficacy across different demographic groups and identify disparities. Our comprehensive analysis, which accounts for various confounding factors, reveals significant fairness concerns within these foundational models. Moreover, our findings highlight not only disparities in overall segmentation metrics, such as the Dice Similarity Coefficient but also significant variations in the spatial distribution of segmentation errors, offering empirical evidence of the nuanced challenges in ensuring fairness in medical image segmentation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.12646v1-abstract-full').style.display = 'none'; document.getElementById('2406.12646v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to MICCAI-2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10358">arXiv:2406.10358</a> <span> [<a href="https://arxiv.org/pdf/2406.10358">pdf</a>, <a href="https://arxiv.org/format/2406.10358">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> I Still See You: Why Existing IoT Traffic Reshaping Fails </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+S">Su Wang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+K">Keyang Yu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+D">Dong Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.10358v1-abstract-short" style="display: inline;"> The Internet traffic data produced by the Internet of Things (IoT) devices are collected by Internet Service Providers (ISPs) and device manufacturers, and often shared with their third parties to maintain and enhance user services. Unfortunately, on-path adversaries could infer and fingerprint users' sensitive privacy information such as occupancy and user activities by analyzing these network tr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10358v1-abstract-full').style.display = 'inline'; document.getElementById('2406.10358v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10358v1-abstract-full" style="display: none;"> The Internet traffic data produced by the Internet of Things (IoT) devices are collected by Internet Service Providers (ISPs) and device manufacturers, and often shared with their third parties to maintain and enhance user services. Unfortunately, on-path adversaries could infer and fingerprint users' sensitive privacy information such as occupancy and user activities by analyzing these network traffic traces. While there's a growing body of literature on defending against this side-channel attack-malicious IoT traffic analytics (TA), there's currently no systematic method to compare and evaluate the comprehensiveness of these existing studies. To address this problem, we design a new low-cost, open-source system framework-IoT Traffic Exposure Monitoring Toolkit (ITEMTK) that enables people to comprehensively examine and validate prior attack models and their defending approaches. In particular, we also design a novel image-based attack capable of inferring sensitive user information, even when users employ the most robust preventative measures in their smart homes. Researchers could leverage our new image-based attack to systematize and understand the existing literature on IoT traffic analysis attacks and preventing studies. Our results show that current defending approaches are not sufficient to protect IoT device user privacy. IoT devices are significantly vulnerable to our new image-based user privacy inference attacks, posing a grave threat to IoT device user privacy. We also highlight potential future improvements to enhance the defending approaches. ITEMTK's flexibility allows other researchers for easy expansion by integrating new TA attack models and prevention methods to benchmark their future work. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10358v1-abstract-full').style.display = 'none'; document.getElementById('2406.10358v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">EWSN'24 paper accepted, to appear</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.07256">arXiv:2406.07256</a> <span> [<a href="https://arxiv.org/pdf/2406.07256">pdf</a>, <a href="https://arxiv.org/ps/2406.07256">ps</a>, <a href="https://arxiv.org/format/2406.07256">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gong%2C+R">Rong Gong</a>, <a href="/search/eess?searchtype=author&query=Xue%2C+H">Hongfei Xue</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+L">Lezhi Wang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+X">Xin Xu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qisheng Li</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a>, <a href="/search/eess?searchtype=author&query=Bu%2C+H">Hui Bu</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+S">Shaomei Wu</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+J">Jiaming Zhou</a>, <a href="/search/eess?searchtype=author&query=Qin%2C+Y">Yong Qin</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+B">Binbin Zhang</a>, <a href="/search/eess?searchtype=author&query=Du%2C+J">Jun Du</a>, <a href="/search/eess?searchtype=author&query=Bin%2C+J">Jia Bin</a>, <a href="/search/eess?searchtype=author&query=Li%2C+M">Ming Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.07256v1-abstract-short" style="display: inline;"> The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech. However, the efficacy of these models diminishes when applied to atypical speech, such as stuttering. This paper introduces AS-70, the first publicly available Mandarin stuttered speech dataset, which stands out as the large… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07256v1-abstract-full').style.display = 'inline'; document.getElementById('2406.07256v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.07256v1-abstract-full" style="display: none;"> The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech. However, the efficacy of these models diminishes when applied to atypical speech, such as stuttering. This paper introduces AS-70, the first publicly available Mandarin stuttered speech dataset, which stands out as the largest dataset in its category. Encompassing conversational and voice command reading speech, AS-70 includes verbatim manual transcription, rendering it suitable for various speech-related tasks. Furthermore, baseline systems are established, and experimental results are presented for ASR and stuttering event detection (SED) tasks. By incorporating this dataset into the model fine-tuning, significant improvements in the state-of-the-art ASR models, e.g., Whisper and Hubert, are observed, enhancing their inclusivity in addressing stuttered speech. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07256v1-abstract-full').style.display = 'none'; document.getElementById('2406.07256v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by Interspeech 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16765">arXiv:2405.16765</a> <span> [<a href="https://arxiv.org/pdf/2405.16765">pdf</a>, <a href="https://arxiv.org/ps/2405.16765">ps</a>, <a href="https://arxiv.org/format/2405.16765">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Study of Robust Direction Finding Based on Joint Sparse Representation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Y. Li</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+W">W. Xiao</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+L">L. Zhao</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Z">Z. Huang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Q. Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+L">L. Li</a>, <a href="/search/eess?searchtype=author&query=de+Lamare%2C+R+C">R. C. de Lamare</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.16765v1-abstract-short" style="display: inline;"> Standard Direction of Arrival (DOA) estimation methods are typically derived based on the Gaussian noise assumption, making them highly sensitive to outliers. Therefore, in the presence of impulsive noise, the performance of these methods may significantly deteriorate. In this paper, we model impulsive noise as Gaussian noise mixed with sparse outliers. By exploiting their statistical differences,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16765v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16765v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16765v1-abstract-full" style="display: none;"> Standard Direction of Arrival (DOA) estimation methods are typically derived based on the Gaussian noise assumption, making them highly sensitive to outliers. Therefore, in the presence of impulsive noise, the performance of these methods may significantly deteriorate. In this paper, we model impulsive noise as Gaussian noise mixed with sparse outliers. By exploiting their statistical differences, we propose a novel DOA estimation method based on sparse signal recovery (SSR). Furthermore, to address the issue of grid mismatch, we utilize an alternating optimization approach that relies on the estimated outlier matrix and the on-grid DOA estimates to obtain the off-grid DOA estimates. Simulation results demonstrate that the proposed method exhibits robustness against large outliers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16765v1-abstract-full').style.display = 'none'; document.getElementById('2405.16765v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.11856">arXiv:2405.11856</a> <span> [<a href="https://arxiv.org/pdf/2405.11856">pdf</a>, <a href="https://arxiv.org/format/2405.11856">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Modeling and simulation of a mechanism for suppressing the flipping problem of a jumping robot </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qi Li</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+L">Liang Peng</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Z">Zhiyuan Wu</a>, <a href="/search/eess?searchtype=author&query=Ye%2C+P">Pengda Ye</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Weitao Zhang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yi Xu</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Q">Qing Shi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.11856v1-abstract-short" style="display: inline;"> In order to solve the problem of stable jumping of micro robot, we design a special mechanism: elastic passive joint (EPJ). EPJ can assist in achieving smooth jumping through the opening-closing process when the robot jumps. First, we introduce the composition and operation principle of EPJ, and perform a dynamic modeling of the robot's jumping process. Then, in order to verify the effectiveness o… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.11856v1-abstract-full').style.display = 'inline'; document.getElementById('2405.11856v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.11856v1-abstract-full" style="display: none;"> In order to solve the problem of stable jumping of micro robot, we design a special mechanism: elastic passive joint (EPJ). EPJ can assist in achieving smooth jumping through the opening-closing process when the robot jumps. First, we introduce the composition and operation principle of EPJ, and perform a dynamic modeling of the robot's jumping process. Then, in order to verify the effectiveness of EPJ in controlling the robot's smooth jump, we design a simulation experiment based on MATLAB. Through comparative experiments, it was proved that EPJ can greatly adjust the angular velocity of the robot and increase the jump distance of the robot. Finally, we analyze each parameter in EPJ and performs parameter optimization. After optimization, EPJ achieves a completely flip-free jump of the robot, laying an important foundation for improving the mobility of micro-robot. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.11856v1-abstract-full').style.display = 'none'; document.getElementById('2405.11856v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.09753">arXiv:2405.09753</a> <span> [<a href="https://arxiv.org/pdf/2405.09753">pdf</a>, <a href="https://arxiv.org/format/2405.09753">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Stacked Intelligent Metasurfaces for Holographic MIMO Aided Cell-Free Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qingchao Li</a>, <a href="/search/eess?searchtype=author&query=El-Hajjar%2C+M">Mohammed El-Hajjar</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+C">Chao Xu</a>, <a href="/search/eess?searchtype=author&query=An%2C+J">Jiancheng An</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/eess?searchtype=author&query=Hanzo%2C+L">Lajos Hanzo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.09753v1-abstract-short" style="display: inline;"> Large-scale multiple-input and multiple-output (MIMO) systems are capable of achieving high date rate. However, given the high hardware cost and excessive power consumption of massive MIMO systems, as a remedy, intelligent metasurfaces have been designed for efficient holographic MIMO (HMIMO) systems. In this paper, we propose a HMIMO architecture based on stacked intelligent metasurfaces (SIM) fo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09753v1-abstract-full').style.display = 'inline'; document.getElementById('2405.09753v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.09753v1-abstract-full" style="display: none;"> Large-scale multiple-input and multiple-output (MIMO) systems are capable of achieving high date rate. However, given the high hardware cost and excessive power consumption of massive MIMO systems, as a remedy, intelligent metasurfaces have been designed for efficient holographic MIMO (HMIMO) systems. In this paper, we propose a HMIMO architecture based on stacked intelligent metasurfaces (SIM) for the uplink of cell-free systems, where the SIM is employed at the access points (APs) for improving the spectral- and energy-efficiency. Specifically, we conceive distributed beamforming for SIM-assisted cell-free networks, where both the SIM coefficients and the local receiver combiner vectors of each AP are optimized based on the local channel state information (CSI) for the local detection of each user equipment (UE) information. Afterward, the central processing unit (CPU) fuses the local detections gleaned from all APs to detect the aggregate multi-user signal. Specifically, to design the SIM coefficients and the combining vectors of the APs, a low-complexity layer-by-layer iterative optimization algorithm is proposed for maximizing the equivalent gain of the channel spanning from the UEs to the APs. At the CPU, the weight vector used for combining the local detections from all APs is designed based on the minimum mean square error (MMSE) criterion, where the hardware impairments (HWIs) are also taken into consideration based on their statistics. The simulation results show that the SIM-based HMIMO outperforms the conventional single-layer HMIMO in terms of the achievable rate. We demonstrate that both the HWI of the radio frequency (RF) chains at the APs and the UEs limit the achievable rate in the high signal-to-noise-ratio (SNR) region. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09753v1-abstract-full').style.display = 'none'; document.getElementById('2405.09753v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.06186">arXiv:2405.06186</a> <span> [<a href="https://arxiv.org/pdf/2405.06186">pdf</a>, <a href="https://arxiv.org/format/2405.06186">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Sensing-Assisted Adaptive Channel Contention for Mobile Delay-Sensitive Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lv%2C+B">Bojie Lv</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Qianren Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+R">Rui Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.06186v1-abstract-short" style="display: inline;"> This paper proposes an adaptive channel contention mechanism to optimize the queuing performance of a distributed millimeter wave (mmWave) uplink system with the capability of environment and mobility sensing. The mobile agents determine their back-off timer parameters according to their local knowledge of the uplink queue lengths, channel quality, and future channel statistics, where the channel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06186v1-abstract-full').style.display = 'inline'; document.getElementById('2405.06186v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.06186v1-abstract-full" style="display: none;"> This paper proposes an adaptive channel contention mechanism to optimize the queuing performance of a distributed millimeter wave (mmWave) uplink system with the capability of environment and mobility sensing. The mobile agents determine their back-off timer parameters according to their local knowledge of the uplink queue lengths, channel quality, and future channel statistics, where the channel prediction relies on the environment and mobility sensing. The optimization of queuing performance with this adaptive channel contention mechanism is formulated as a decentralized multi-agent Markov decision process (MDP). Although the channel contention actions are determined locally at the mobile agents, the optimization of local channel contention policies of all mobile agents is conducted in a centralized manner according to the system statistics before the scheduling. In the solution, the local policies are approximated by analytical models, and the optimization of their parameters becomes a stochastic optimization problem along an adaptive Markov chain. An unbiased gradient estimation is proposed so that the local policies can be optimized efficiently via the stochastic gradient descent method. It is demonstrated by simulation that the proposed gradient estimation is significantly more efficient in optimization than the existing methods, e.g., simultaneous perturbation stochastic approximation (SPSA). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06186v1-abstract-full').style.display = 'none'; document.getElementById('2405.06186v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Li%2C+Q&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </a> </li> <li> <a href="/search/?searchtype=author&query=Li%2C+Q&start=300" class="pagination-link " aria-label="Page 7" aria-current="page">7 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository