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 50 results for author: <span class="mathjax">Jin, M</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=Jin%2C+M">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="Jin, M"> </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=Jin%2C+M&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="Jin, M"> <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=Jin%2C+M&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Jin%2C+M&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Jin%2C+M&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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/2412.15843">arXiv:2412.15843</a> <span> [<a href="https://arxiv.org/pdf/2412.15843">pdf</a>, <a href="https://arxiv.org/format/2412.15843">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"> Rethinking Hardware Impairments in Multi-User Systems: Can FAS Make a Difference? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+L">Liaoshi Zhou</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+C">Cunhua Pan</a>, <a href="/search/eess?searchtype=author&query=Elkashlan%2C+M">Maged Elkashlan</a>, <a href="/search/eess?searchtype=author&query=Adachi%2C+F">Fumiyuki Adachi</a>, <a href="/search/eess?searchtype=author&query=Karagiannidis%2C+G+K">George K. Karagiannidis</a>, <a href="/search/eess?searchtype=author&query=Al-Dhahir%2C+N">Naofal Al-Dhahir</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2412.15843v1-abstract-short" style="display: inline;"> In this paper, we analyze the role of fluid antenna systems (FAS) in multi-user systems with hardware impairments (HIs). Specifically, we investigate a scenario where a base station (BS) equipped with multiple fluid antennas communicates with multiple users (CUs), each equipped with a single fluid antenna. Our objective is to maximize the minimum communication rate among all users by jointly optim… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15843v1-abstract-full').style.display = 'inline'; document.getElementById('2412.15843v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.15843v1-abstract-full" style="display: none;"> In this paper, we analyze the role of fluid antenna systems (FAS) in multi-user systems with hardware impairments (HIs). Specifically, we investigate a scenario where a base station (BS) equipped with multiple fluid antennas communicates with multiple users (CUs), each equipped with a single fluid antenna. Our objective is to maximize the minimum communication rate among all users by jointly optimizing the BS's transmit beamforming, the positions of its transmit fluid antennas, and the positions of the CUs' receive fluid antennas. To address this non-convex problem, we propose a block coordinate descent (BCD) algorithm integrating semidefinite relaxation (SDR), rank-one constraint relaxation (SRCR), successive convex approximation (SCA), and majorization-minimization (MM). Simulation results demonstrate that FAS significantly enhances system performance and robustness, with notable gains when both the BS and CUs are equipped with fluid antennas. Even under low transmit power conditions, deploying FAS at the BS alone yields substantial performance gains. However, the effectiveness of FAS depends on the availability of sufficient movement space, as space constraints may limit its benefits compared to fixed antenna strategies. Our findings highlight the potential of FAS to mitigate HIs and enhance multi-user system performance, while emphasizing the need for practical deployment considerations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15843v1-abstract-full').style.display = 'none'; document.getElementById('2412.15843v1-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 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/2412.00319">arXiv:2412.00319</a> <span> [<a href="https://arxiv.org/pdf/2412.00319">pdf</a>, <a href="https://arxiv.org/format/2412.00319">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"> Improving speaker verification robustness with synthetic emotional utterances </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Koditala%2C+N+K">Nikhil Kumar Koditala</a>, <a href="/search/eess?searchtype=author&query=Ju%2C+C+J">Chelsea Jui-Ting Ju</a>, <a href="/search/eess?searchtype=author&query=Li%2C+R">Ruirui Li</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Minho Jin</a>, <a href="/search/eess?searchtype=author&query=Chadha%2C+A">Aman Chadha</a>, <a href="/search/eess?searchtype=author&query=Stolcke%2C+A">Andreas Stolcke</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="2412.00319v1-abstract-short" style="display: inline;"> A speaker verification (SV) system offers an authentication service designed to confirm whether a given speech sample originates from a specific speaker. This technology has paved the way for various personalized applications that cater to individual preferences. A noteworthy challenge faced by SV systems is their ability to perform consistently across a range of emotional spectra. Most existing m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00319v1-abstract-full').style.display = 'inline'; document.getElementById('2412.00319v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.00319v1-abstract-full" style="display: none;"> A speaker verification (SV) system offers an authentication service designed to confirm whether a given speech sample originates from a specific speaker. This technology has paved the way for various personalized applications that cater to individual preferences. A noteworthy challenge faced by SV systems is their ability to perform consistently across a range of emotional spectra. Most existing models exhibit high error rates when dealing with emotional utterances compared to neutral ones. Consequently, this phenomenon often leads to missing out on speech of interest. This issue primarily stems from the limited availability of labeled emotional speech data, impeding the development of robust speaker representations that encompass diverse emotional states. To address this concern, we propose a novel approach employing the CycleGAN framework to serve as a data augmentation method. This technique synthesizes emotional speech segments for each specific speaker while preserving the unique vocal identity. Our experimental findings underscore the effectiveness of incorporating synthetic emotional data into the training process. The models trained using this augmented dataset consistently outperform the baseline models on the task of verifying speakers in emotional speech scenarios, reducing equal error rate by as much as 3.64% relative. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.00319v1-abstract-full').style.display = 'none'; document.getElementById('2412.00319v1-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> 29 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/2411.09235">arXiv:2411.09235</a> <span> [<a href="https://arxiv.org/pdf/2411.09235">pdf</a>, <a href="https://arxiv.org/ps/2411.09235">ps</a>, <a href="https://arxiv.org/format/2411.09235">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"> FAS for Secure and Covert Communications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Xin%2C+L">Liangxiao Xin</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/eess?searchtype=author&query=Shin%2C+H">Hyundong Shin</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="2411.09235v1-abstract-short" style="display: inline;"> This letter considers a fluid antenna system (FAS)-aided secure and covert communication system, where the transmitter adjusts multiple fluid antennas' positions to achieve secure and covert transmission under the threat of an eavesdropper and the detection of a warden. This letter aims to maximize the secrecy rate while satisfying the covertness constraint. Unfortunately, the optimization problem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09235v1-abstract-full').style.display = 'inline'; document.getElementById('2411.09235v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.09235v1-abstract-full" style="display: none;"> This letter considers a fluid antenna system (FAS)-aided secure and covert communication system, where the transmitter adjusts multiple fluid antennas' positions to achieve secure and covert transmission under the threat of an eavesdropper and the detection of a warden. This letter aims to maximize the secrecy rate while satisfying the covertness constraint. Unfortunately, the optimization problem is non-convex due to the coupled variables. To tackle this, we propose an alternating optimization (AO) algorithm to alternatively optimize the optimization variables in an iterative manner. In particular, we use a penalty-based method and the majorization-minimization (MM) algorithm to optimize the transmit beamforming and fluid antennas' positions, respectively. Simulation results show that FAS can significantly improve the performance of secrecy and covertness compared to the fixed-position antenna (FPA)-based schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.09235v1-abstract-full').style.display = 'none'; document.getElementById('2411.09235v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.08383">arXiv:2411.08383</a> <span> [<a href="https://arxiv.org/pdf/2411.08383">pdf</a>, <a href="https://arxiv.org/format/2411.08383">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"> FAS-Driven Spectrum Sensing for Cognitive Radio Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Elkashlan%2C+M">Maged Elkashlan</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</a>, <a href="/search/eess?searchtype=author&query=Karagiannidis%2C+G+K">George K. Karagiannidis</a>, <a href="/search/eess?searchtype=author&query=Shin%2C+H">Hyundong Shin</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="2411.08383v1-abstract-short" style="display: inline;"> Cognitive radio (CR) networks face significant challenges in spectrum sensing, especially under spectrum scarcity. Fluid antenna systems (FAS) can offer an unorthodox solution due to their ability to dynamically adjust antenna positions for improved channel gain. In this letter, we study a FAS-driven CR setup where a secondary user (SU) adjusts the positions of fluid antennas to detect signals fro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08383v1-abstract-full').style.display = 'inline'; document.getElementById('2411.08383v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.08383v1-abstract-full" style="display: none;"> Cognitive radio (CR) networks face significant challenges in spectrum sensing, especially under spectrum scarcity. Fluid antenna systems (FAS) can offer an unorthodox solution due to their ability to dynamically adjust antenna positions for improved channel gain. In this letter, we study a FAS-driven CR setup where a secondary user (SU) adjusts the positions of fluid antennas to detect signals from the primary user (PU). We aim to maximize the detection probability under the constraints of the false alarm probability and the received beamforming of the SU. To address this problem, we first derive a closed-form expression for the optimal detection threshold and reformulate the problem to find its solution. Then an alternating optimization (AO) scheme is proposed to decompose the problem into several sub-problems, addressing both the received beamforming and the antenna positions at the SU. The beamforming subproblem is addressed using a closed-form solution, while the fluid antenna positions are solved by successive convex approximation (SCA). Simulation results reveal that the proposed algorithm provides significant improvements over traditional fixed-position antenna (FPA) schemes in terms of spectrum sensing performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.08383v1-abstract-full').style.display = 'none'; document.getElementById('2411.08383v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.16020">arXiv:2409.16020</a> <span> [<a href="https://arxiv.org/pdf/2409.16020">pdf</a>, <a href="https://arxiv.org/ps/2409.16020">ps</a>, <a href="https://arxiv.org/format/2409.16020">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"> BCRLB Under the Fusion Extended Kalman Filter </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lin%2C+M">Mushen Lin</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+F">Fenggang Yan</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+L">Lingda Ren</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+X">Xiangtian Meng</a>, <a href="/search/eess?searchtype=author&query=Greco%2C+M">Maria Greco</a>, <a href="/search/eess?searchtype=author&query=Gini%2C+F">Fulvio Gini</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2409.16020v1-abstract-short" style="display: inline;"> In the process of tracking multiple point targets in space using radar, since the targets are spatially well separated, the data between them will not be confused. Therefore, the multi-target tracking problem can be transformed into a single-target tracking problem. However, the data measured by radar nodes contains noise, clutter, and false targets, making it difficult for the fusion center to di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16020v1-abstract-full').style.display = 'inline'; document.getElementById('2409.16020v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.16020v1-abstract-full" style="display: none;"> In the process of tracking multiple point targets in space using radar, since the targets are spatially well separated, the data between them will not be confused. Therefore, the multi-target tracking problem can be transformed into a single-target tracking problem. However, the data measured by radar nodes contains noise, clutter, and false targets, making it difficult for the fusion center to directly establish the association between radar measurements and real targets. To address this issue, the Probabilistic Data Association (PDA) algorithm is used to calculate the association probability between each radar measurement and the target, and the measurements are fused based on these probabilities. Finally, an extended Kalman filter (EKF) is used to predict the target states. Additionally, we derive the Bayesian Cram茅r-Rao Lower Bound (BCRLB) under the PDA fusion framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.16020v1-abstract-full').style.display = 'none'; document.getElementById('2409.16020v1-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">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/2409.00099">arXiv:2409.00099</a> <span> [<a href="https://arxiv.org/pdf/2409.00099">pdf</a>, <a href="https://arxiv.org/format/2409.00099">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</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="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"> Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhenyu Wang</a>, <a href="/search/eess?searchtype=author&query=Kong%2C+S">Shuyu Kong</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+L">Li Wan</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+B">Biqiao Zhang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Y">Yiteng Huang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mumin Jin</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+M">Ming Sun</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+X">Xin Lei</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Z">Zhaojun 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="2409.00099v2-abstract-short" style="display: inline;"> Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, we present a novel Query-by-Example (QbyE) KWS system that employs spectral-temporal graph attentive pooling and multi-task learning. This framework aims to effectively learn speake… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00099v2-abstract-full').style.display = 'inline'; document.getElementById('2409.00099v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.00099v2-abstract-full" style="display: none;"> Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions with intelligent devices. In this paper, we present a novel Query-by-Example (QbyE) KWS system that employs spectral-temporal graph attentive pooling and multi-task learning. This framework aims to effectively learn speaker-invariant and linguistic-informative embeddings for QbyE KWS tasks. Within this framework, we investigate three distinct network architectures for encoder modeling: LiCoNet, Conformer and ECAPA_TDNN. The experimental results on a substantial internal dataset of $629$ speakers have demonstrated the effectiveness of the proposed QbyE framework in maximizing the potential of simpler models such as LiCoNet. Particularly, LiCoNet, which is 13x more efficient, achieves comparable performance to the computationally intensive Conformer model (1.98% vs. 1.63\% FRR at 0.3 FAs/Hr). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.00099v2-abstract-full').style.display = 'none'; document.getElementById('2409.00099v2-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 26 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">Journal ref:</span> INTERSPEECH 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.16251">arXiv:2408.16251</a> <span> [<a href="https://arxiv.org/pdf/2408.16251">pdf</a>, <a href="https://arxiv.org/format/2408.16251">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"> Neural Network-Assisted Hybrid Model Based Message Passing for Parametric Holographic MIMO Near Field Channel Estimation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yuan%2C+Z">Zhengdao Yuan</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Y">Yabo Guo</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+D">Dawei Gao</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Q">Qinghua Guo</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhongyong Wang</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+C">Chongwen Huang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</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="2408.16251v1-abstract-short" style="display: inline;"> Holographic multiple-input and multiple-output (HMIMO) is a promising technology with the potential to achieve high energy and spectral efficiencies, enhance system capacity and diversity, etc. In this work, we address the challenge of HMIMO near field (NF) channel estimation, which is complicated by the intricate model introduced by the dyadic Green's function. Despite its complexity, the channel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16251v1-abstract-full').style.display = 'inline'; document.getElementById('2408.16251v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16251v1-abstract-full" style="display: none;"> Holographic multiple-input and multiple-output (HMIMO) is a promising technology with the potential to achieve high energy and spectral efficiencies, enhance system capacity and diversity, etc. In this work, we address the challenge of HMIMO near field (NF) channel estimation, which is complicated by the intricate model introduced by the dyadic Green's function. Despite its complexity, the channel model is governed by a limited set of parameters. This makes parametric channel estimation highly attractive, offering substantial performance enhancements and enabling the extraction of valuable sensing parameters, such as user locations, which are particularly beneficial in mobile networks. However, the relationship between these parameters and channel gains is nonlinear and compounded by integration, making the estimation a formidable task. To tackle this problem, we propose a novel neural network (NN) assisted hybrid method. With the assistance of NNs, we first develop a novel hybrid channel model with a significantly simplified expression compared to the original one, thereby enabling parametric channel estimation. Using the readily available training data derived from the original channel model, the NNs in the hybrid channel model can be effectively trained offline. Then, building upon this hybrid channel model, we formulate the parametric channel estimation problem with a probabilistic framework and design a factor graph representation for Bayesian estimation. Leveraging the factor graph representation and unitary approximate message passing (UAMP), we develop an effective message passing-based Bayesian channel estimation algorithm. Extensive simulations demonstrate the superior performance of the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16251v1-abstract-full').style.display = 'none'; document.getElementById('2408.16251v1-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> 29 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/2408.15368">arXiv:2408.15368</a> <span> [<a href="https://arxiv.org/pdf/2408.15368">pdf</a>, <a href="https://arxiv.org/format/2408.15368">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> </div> </div> <p class="title is-5 mathjax"> Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Khattar%2C+V">Vanshaj Khattar</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2408.15368v1-abstract-short" style="display: inline;"> Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC) framework that employs optimization solution functions as a deterministic policy (actor) and a monotone function over the optimal value of optimization as a critic. By… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15368v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15368v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15368v1-abstract-full" style="display: none;"> Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC) framework that employs optimization solution functions as a deterministic policy (actor) and a monotone function over the optimal value of optimization as a critic. By encoding optimality in the actor policy, we show that the learned policies are robust to the suboptimality of the learned actor parameters via the exponentially decaying sensitivity (EDS) property. We obtain performance guarantees for the proposed iAC framework and show its benefits over general function approximation schemes. Finally, we validate the proposed framework on two real-world applications and show a significant improvement over state-of-the-art (SOTA) offline RL methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15368v1-abstract-full').style.display = 'none'; document.getElementById('2408.15368v1-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 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">American Control Conference 2024</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> American Control Conference 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13447">arXiv:2408.13447</a> <span> [<a href="https://arxiv.org/pdf/2408.13447">pdf</a>, <a href="https://arxiv.org/ps/2408.13447">ps</a>, <a href="https://arxiv.org/format/2408.13447">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"> FAS-RIS Communication: Model, Analysis, and Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+J">Jianchao Zheng</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</a>, <a href="/search/eess?searchtype=author&query=Adachi%2C+F">Fumiyuki Adachi</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="2408.13447v1-abstract-short" style="display: inline;"> This correspondence investigates the novel fluid antenna system (FAS) technology, combining with reconfigurable intelligent surface (RIS) for wireless communications, where a base station (BS) communicates with a FAS-enabled user with the assistance of a RIS. To analyze this technology, we derive the outage probability based on the block-diagonal matrix approximation (BDMA) model. With this, we ob… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13447v1-abstract-full').style.display = 'inline'; document.getElementById('2408.13447v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13447v1-abstract-full" style="display: none;"> This correspondence investigates the novel fluid antenna system (FAS) technology, combining with reconfigurable intelligent surface (RIS) for wireless communications, where a base station (BS) communicates with a FAS-enabled user with the assistance of a RIS. To analyze this technology, we derive the outage probability based on the block-diagonal matrix approximation (BDMA) model. With this, we obtain the upper bound, lower bound, and asymptotic approximation of the outage probability to gain more insights. Moreover, we design the phase shift matrix of the RIS in order to minimize the system outage probability. Simulation results confirm the accuracy of our approximations and that the proposed schemes outperform benchmarks significantly. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13447v1-abstract-full').style.display = 'none'; document.getElementById('2408.13447v1-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 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/2408.11329">arXiv:2408.11329</a> <span> [<a href="https://arxiv.org/pdf/2408.11329">pdf</a>, <a href="https://arxiv.org/ps/2408.11329">ps</a>, <a href="https://arxiv.org/format/2408.11329">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"> Full-Duplex ISAC-Enabled D2D Underlaid Cellular Networks: Joint Transceiver Beamforming and Power Allocation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jiang%2C+T">Tao Jiang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Q">Qinghua Guo</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yinhong Liu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yaming 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="2408.11329v2-abstract-short" style="display: inline;"> Integrating device-to-device (D2D) communication into cellular networks can significantly reduce the transmission burden on base stations (BSs). Besides, integrated sensing and communication (ISAC) is envisioned as a key feature in future wireless networks. In this work, we consider a full-duplex ISAC- based D2D underlaid system, and propose a joint beamforming and power allocation scheme to impro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11329v2-abstract-full').style.display = 'inline'; document.getElementById('2408.11329v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.11329v2-abstract-full" style="display: none;"> Integrating device-to-device (D2D) communication into cellular networks can significantly reduce the transmission burden on base stations (BSs). Besides, integrated sensing and communication (ISAC) is envisioned as a key feature in future wireless networks. In this work, we consider a full-duplex ISAC- based D2D underlaid system, and propose a joint beamforming and power allocation scheme to improve the performance of the coexisting ISAC and D2D networks. To enhance spectral efficiency, a sum rate maximization problem is formulated for the full-duplex ISAC-based D2D underlaid system, which is non-convex. To solve the non-convex optimization problem, we propose a successive convex approximation (SCA)-based iterative algorithm and prove its convergence. Numerical results are provided to validate the effectiveness of the proposed scheme with the iterative algorithm, demonstrating that the proposed scheme outperforms state-of-the-art ones in both communication and sensing performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.11329v2-abstract-full').style.display = 'none'; document.getElementById('2408.11329v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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 work has been submitted to IEEE Transactions on Wireless Communications on 7 June,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/2408.09067">arXiv:2408.09067</a> <span> [<a href="https://arxiv.org/pdf/2408.09067">pdf</a>, <a href="https://arxiv.org/ps/2408.09067">ps</a>, <a href="https://arxiv.org/format/2408.09067">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"> FAS vs. ARIS: Which Is More Important for FAS-ARIS Communication Systems? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+L">Liaoshi Zhou</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+C">Chongwen Huang</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</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="2408.09067v1-abstract-short" style="display: inline;"> In this paper, we investigate the question of which technology, fluid antenna systems (FAS) or active reconfigurable intelligent surfaces (ARIS), plays a more crucial role in FAS-ARIS wireless communication systems. To address this, we develop a comprehensive system model and explore the problem from an optimization perspective. We introduce an alternating optimization (AO) algorithm incorporating… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09067v1-abstract-full').style.display = 'inline'; document.getElementById('2408.09067v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.09067v1-abstract-full" style="display: none;"> In this paper, we investigate the question of which technology, fluid antenna systems (FAS) or active reconfigurable intelligent surfaces (ARIS), plays a more crucial role in FAS-ARIS wireless communication systems. To address this, we develop a comprehensive system model and explore the problem from an optimization perspective. We introduce an alternating optimization (AO) algorithm incorporating majorization-minimization (MM), successive convex approximation (SCA), and sequential rank-one constraint relaxation (SRCR) to tackle the non-convex challenges inherent in these systems. Specifically, for the transmit beamforming of the BS optimization, we propose a closed-form rank-one solution with low-complexity. For the optimization the positions of fluid antennas (FAs) of the BS, the Taylor expansions and MM algorithm are utilized to construct the effective lower bounds and upper bounds of the objective function and constraints, transforming the non-convex optimization problem into a convex one. Furthermore, we use the SCA and SRCR to optimize the reflection coefficient matrix of the ARIS and effectively solve the rank-one constraint. Simulation results reveal that the relative importance of FAS and ARIS varies depending on the scenario: FAS proves more critical in simpler models with fewer reflecting elements or limited transmission paths, while ARIS becomes more significant in complex scenarios with a higher number of reflecting elements or transmission paths. Ultimately, the integration of both FAS and ARIS creates a win-win scenario, resulting in a more robust and efficient communication system. This study underscores the importance of combining FAS with ARIS, as their complementary use provides the most substantial benefits across different communication environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09067v1-abstract-full').style.display = 'none'; document.getElementById('2408.09067v1-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 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/2407.11307">arXiv:2407.11307</a> <span> [<a href="https://arxiv.org/pdf/2407.11307">pdf</a>, <a href="https://arxiv.org/ps/2407.11307">ps</a>, <a href="https://arxiv.org/format/2407.11307">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"> Fluid Antenna-Assisted Simultaneous Wireless Information and Power Transfer Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+L">Liaoshi Zhou</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/eess?searchtype=author&query=Adachi%2C+F">Fumiyuki Adachi</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="2407.11307v2-abstract-short" style="display: inline;"> This paper examines a fluid antenna (FA)-assisted simultaneous wireless information and power transfer (SWIPT) system. Unlike traditional SWIPT systems with fixed-position antennas (FPAs), our FA-assisted system enables dynamic reconfiguration of the radio propagation environment by adjusting the positions of FAs. This capability enhances both energy harvesting and communication performance. The s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11307v2-abstract-full').style.display = 'inline'; document.getElementById('2407.11307v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.11307v2-abstract-full" style="display: none;"> This paper examines a fluid antenna (FA)-assisted simultaneous wireless information and power transfer (SWIPT) system. Unlike traditional SWIPT systems with fixed-position antennas (FPAs), our FA-assisted system enables dynamic reconfiguration of the radio propagation environment by adjusting the positions of FAs. This capability enhances both energy harvesting and communication performance. The system comprises a base station (BS) equipped with multiple FAs that transmit signals to an energy receiver (ER) and an information receiver (IR), both equipped with a single FA. Our objective is to maximize the communication rate between the BS and the IR while satisfying the harvested power requirement of the ER. This involves jointly optimizing the BS's transmit beamforming and the positions of all FAs. To address this complex convex optimization problem, we employ an alternating optimization (AO) approach, decomposing it into three sub-problems and solving them iteratively using first and second-order Taylor expansions. Simulation results validate the effectiveness of our proposed FA-assisted SWIPT system, demonstrating significant performance improvements over traditional FPA-based systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11307v2-abstract-full').style.display = 'none'; document.getElementById('2407.11307v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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/2407.08141">arXiv:2407.08141</a> <span> [<a href="https://arxiv.org/pdf/2407.08141">pdf</a>, <a href="https://arxiv.org/ps/2407.08141">ps</a>, <a href="https://arxiv.org/format/2407.08141">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"> A Framework of FAS-RIS Systems: Performance Analysis and Throughput Optimization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Lai%2C+X">Xiazhi Lai</a>, <a href="/search/eess?searchtype=author&query=Zhi%2C+K">Kangda Zhi</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+C">Cunhua Pan</a>, <a href="/search/eess?searchtype=author&query=Elkashlan%2C+M">Maged Elkashlan</a>, <a href="/search/eess?searchtype=author&query=Yuen%2C+C">Chau Yuen</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</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="2407.08141v1-abstract-short" style="display: inline;"> In this paper, we investigate reconfigurable intelligent surface (RIS)-assisted communication systems which involve a fixed-antenna base station (BS) and a mobile user (MU) that is equipped with fluid antenna system (FAS). Specifically, the RIS is utilized to enable communication for the user whose direct link from the base station is blocked by obstacles. We propose a comprehensive framework that… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08141v1-abstract-full').style.display = 'inline'; document.getElementById('2407.08141v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08141v1-abstract-full" style="display: none;"> In this paper, we investigate reconfigurable intelligent surface (RIS)-assisted communication systems which involve a fixed-antenna base station (BS) and a mobile user (MU) that is equipped with fluid antenna system (FAS). Specifically, the RIS is utilized to enable communication for the user whose direct link from the base station is blocked by obstacles. We propose a comprehensive framework that provides transmission design for both static scenarios with the knowledge of channel state information (CSI) and harsh environments where CSI is hard to acquire. It leads to two approaches: a CSI-based scheme where CSI is available, and a CSI-free scheme when CSI is inaccessible. Given the complex spatial correlations in FAS, we employ block-diagonal matrix approximation and independent antenna equivalent models to simplify the derivation of outage probabilities in both cases. Based on the derived outage probabilities, we then optimize the throughput of the FAS-RIS system. For the CSI-based scheme, we first propose a gradient ascent-based algorithm to obtain a near-optimal solution. Then, to address the possible high computational complexity in the gradient algorithm, we approximate the objective function and confirm a unique optimal solution accessible through a bisection search method. For the CSI-free scheme, we apply the partial gradient ascent algorithm, reducing complexity further than full gradient algorithms. We also approximate the objective function and derive a locally optimal closed-form solution to maximize throughput. Simulation results validate the effectiveness of the proposed framework for the transmission design in FAS-RIS systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08141v1-abstract-full').style.display = 'none'; document.getElementById('2407.08141v1-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 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">submitted to IEEE journal 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/2405.11397">arXiv:2405.11397</a> <span> [<a href="https://arxiv.org/pdf/2405.11397">pdf</a>, <a href="https://arxiv.org/format/2405.11397">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="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"> Preparing for Black Swans: The Antifragility Imperative for Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2405.11397v1-abstract-short" style="display: inline;"> Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications. This paper builds upon the transformative concept of ``antifragility'' introduced by (Taleb, 2014) as a constructive design paradigm to not just withstand but benefit from volatility. We formally define antifragility in the context of online decision making as dynamic regret'… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.11397v1-abstract-full').style.display = 'inline'; document.getElementById('2405.11397v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.11397v1-abstract-full" style="display: none;"> Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications. This paper builds upon the transformative concept of ``antifragility'' introduced by (Taleb, 2014) as a constructive design paradigm to not just withstand but benefit from volatility. We formally define antifragility in the context of online decision making as dynamic regret's strictly concave response to environmental variability, revealing limitations of current approaches focused on resisting rather than benefiting from nonstationarity. Our contribution lies in proposing potential computational pathways for engineering antifragility, grounding the concept in online learning theory and drawing connections to recent advancements in areas such as meta-learning, safe exploration, continual learning, multi-objective/quality-diversity optimization, and foundation models. By identifying promising mechanisms and future research directions, we aim to put antifragility on a rigorous theoretical foundation in machine learning. We further emphasize the need for clear guidelines, risk assessment frameworks, and interdisciplinary collaboration to ensure responsible application. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.11397v1-abstract-full').style.display = 'none'; document.getElementById('2405.11397v1-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 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/2405.02989">arXiv:2405.02989</a> <span> [<a href="https://arxiv.org/pdf/2405.02989">pdf</a>, <a href="https://arxiv.org/format/2405.02989">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"> Defense against Joint Poison and Evasion Attacks: A Case Study of DERMS </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Abdeen%2C+Z+u">Zain ul Abdeen</a>, <a href="/search/eess?searchtype=author&query=Roy%2C+P">Padmaksha Roy</a>, <a href="/search/eess?searchtype=author&query=Al-Tawaha%2C+A">Ahmad Al-Tawaha</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+R">Rouxi Jia</a>, <a href="/search/eess?searchtype=author&query=Freeman%2C+L">Laura Freeman</a>, <a href="/search/eess?searchtype=author&query=Beling%2C+P">Peter Beling</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+C">Chen-Ching Liu</a>, <a href="/search/eess?searchtype=author&query=Sangiovanni-Vincentelli%2C+A">Alberto Sangiovanni-Vincentelli</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2405.02989v1-abstract-short" style="display: inline;"> There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact operational reliability. While a data-driven intrusion detection system (IDS) can potentially thwart attacks during deployment, also known as the evasion attack, the tra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02989v1-abstract-full').style.display = 'inline'; document.getElementById('2405.02989v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.02989v1-abstract-full" style="display: none;"> There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact operational reliability. While a data-driven intrusion detection system (IDS) can potentially thwart attacks during deployment, also known as the evasion attack, the training of the detection algorithm may be corrupted by adversarial data injected into the database, also known as the poisoning attack. In this paper, we propose the first framework of IDS that is robust against joint poisoning and evasion attacks. We formulate the defense mechanism as a bilevel optimization, where the inner and outer levels deal with attacks that occur during training time and testing time, respectively. We verify the robustness of our method on the IEEE-13 bus feeder model against a diverse set of poisoning and evasion attack scenarios. The results indicate that our proposed method outperforms the baseline technique in terms of accuracy, precision, and recall for intrusion detection. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02989v1-abstract-full').style.display = 'none'; document.getElementById('2405.02989v1-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 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/2403.10323">arXiv:2403.10323</a> <span> [<a href="https://arxiv.org/pdf/2403.10323">pdf</a>, <a href="https://arxiv.org/ps/2403.10323">ps</a>, <a href="https://arxiv.org/format/2403.10323">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"> Joint Optimization for Achieving Covertness in MIMO Over-the-Air Computation Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+C">Cunhua Pan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzhong Li</a>, <a href="/search/eess?searchtype=author&query=Yuan%2C+J">Jinhong Yuan</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="2403.10323v1-abstract-short" style="display: inline;"> This paper investigates covert data transmission within a multiple-input multiple-output (MIMO) over-the-air computation (AirComp) network, where sensors transmit data to the access point (AP) while guaranteeing covertness to the warden (Willie). Simultaneously, the AP introduces artificial noise (AN) to confuse Willie, meeting the covert requirement. We address the challenge of minimizing mean-sq… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10323v1-abstract-full').style.display = 'inline'; document.getElementById('2403.10323v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.10323v1-abstract-full" style="display: none;"> This paper investigates covert data transmission within a multiple-input multiple-output (MIMO) over-the-air computation (AirComp) network, where sensors transmit data to the access point (AP) while guaranteeing covertness to the warden (Willie). Simultaneously, the AP introduces artificial noise (AN) to confuse Willie, meeting the covert requirement. We address the challenge of minimizing mean-square-error (MSE) of the AP, while considering transmit power constraints at both the AP and the sensors, as well as ensuring the covert transmission to Willie with a low detection error probability (DEP). However, obtaining globally optimal solutions for the investigated non-convex problem is challenging due to the interdependence of optimization variables. To tackle this problem, we introduce an exact penalty algorithm and transform the optimization problem into a difference-of-convex (DC) form problem to find a locally optimal solution. Simulation results showcase the superior performance in terms of our proposed scheme in comparison to the benchmark schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.10323v1-abstract-full').style.display = 'none'; document.getElementById('2403.10323v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.00453">arXiv:2403.00453</a> <span> [<a href="https://arxiv.org/pdf/2403.00453">pdf</a>, <a href="https://arxiv.org/ps/2403.00453">ps</a>, <a href="https://arxiv.org/format/2403.00453">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"> Exploring Fairness for FAS-assisted Communication Systems: from NOMA to OMA </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+L">Liaoshi Zhou</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+C">Cunhua Pan</a>, <a href="/search/eess?searchtype=author&query=Elkashlan%2C+M">Maged Elkashlan</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</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="2403.00453v1-abstract-short" style="display: inline;"> This paper addresses the fairness issue within fluid antenna system (FAS)-assisted non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) systems, where a single fixed-antenna base station (BS) transmits superposition-coded signals to two users, each with a single fluid antenna. We define fairness through the minimization of the maximum outage probability for the two users, und… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.00453v1-abstract-full').style.display = 'inline'; document.getElementById('2403.00453v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.00453v1-abstract-full" style="display: none;"> This paper addresses the fairness issue within fluid antenna system (FAS)-assisted non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) systems, where a single fixed-antenna base station (BS) transmits superposition-coded signals to two users, each with a single fluid antenna. We define fairness through the minimization of the maximum outage probability for the two users, under total resource constraints for both FAS-assisted NOMA and OMA systems. Specifically, in the FAS-assisted NOMA systems, we study both a special case and the general case, deriving a closed-form solution for the former and applying a bisection search method to find the optimal solution for the latter. Moreover, for the general case, we derive a locally optimal closed-form solution to achieve fairness. In the FAS-assisted OMA systems, to deal with the non-convex optimization problem with coupling of the variables in the objective function, we employ an approximation strategy to facilitate a successive convex approximation (SCA)-based algorithm, achieving locally optimal solutions for both cases. Empirical analysis validates that our proposed solutions outperform conventional NOMA and OMA benchmarks in terms of fairness. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.00453v1-abstract-full').style.display = 'none'; document.getElementById('2403.00453v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.07550">arXiv:2310.07550</a> <span> [<a href="https://arxiv.org/pdf/2310.07550">pdf</a>, <a href="https://arxiv.org/format/2310.07550">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"> Proactive Monitoring via Jamming in Fluid Antenna Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yao%2C+J">Junteng Yao</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+T">Tuo Wu</a>, <a href="/search/eess?searchtype=author&query=Lai%2C+X">Xiazhi Lai</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+C">Cunhua Pan</a>, <a href="/search/eess?searchtype=author&query=Elkashlan%2C+M">Maged Elkashlan</a>, <a href="/search/eess?searchtype=author&query=Wong%2C+K">Kai-Kit Wong</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="2310.07550v1-abstract-short" style="display: inline;"> This paper investigates the efficacy of utilizing fluid antenna system (FAS) at a legitimate monitor to oversee suspicious communication. The monitor switches the antenna position to minimize its outage probability for enhancing the monitoring performance. Our objective is to maximize the average monitoring rate, whose expression involves the integral of the first-order Marcum $Q$ function. The op… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.07550v1-abstract-full').style.display = 'inline'; document.getElementById('2310.07550v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.07550v1-abstract-full" style="display: none;"> This paper investigates the efficacy of utilizing fluid antenna system (FAS) at a legitimate monitor to oversee suspicious communication. The monitor switches the antenna position to minimize its outage probability for enhancing the monitoring performance. Our objective is to maximize the average monitoring rate, whose expression involves the integral of the first-order Marcum $Q$ function. The optimization problem, as initially posed, is non-convex owing to its objective function. Nevertheless, upon substituting with an upper bound, we provide a theoretical foundation confirming the existence of a unique optimal solution for the modified problem, achievable efficiently by the bisection search method. Furthermore, we also introduce a locally closed-form optimal resolution for maximizing the average monitoring rate. Empirical evaluations confirm that the proposed schemes outperform conventional benchmarks considerably. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.07550v1-abstract-full').style.display = 'none'; document.getElementById('2310.07550v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </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">3 figs, submitted to IEEE 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/2309.00313">arXiv:2309.00313</a> <span> [<a href="https://arxiv.org/pdf/2309.00313">pdf</a>, <a href="https://arxiv.org/format/2309.00313">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"> Message Passing Based Block Sparse Signal Recovery for DOA Estimation Using Large Arrays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Mao%2C+Y">Yiwen Mao</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+D">Dawei Gao</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Q">Qinghua Guo</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2309.00313v1-abstract-short" style="display: inline;"> This work deals with directional of arrival (DOA) estimation with a large antenna array. We first develop a novel signal model with a sparse system transfer matrix using an inverse discrete Fourier transform (DFT) operation, which leads to the formulation of a structured block sparse signal recovery problem with a sparse sensing matrix. This enables the development of a low complexity message pass… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.00313v1-abstract-full').style.display = 'inline'; document.getElementById('2309.00313v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.00313v1-abstract-full" style="display: none;"> This work deals with directional of arrival (DOA) estimation with a large antenna array. We first develop a novel signal model with a sparse system transfer matrix using an inverse discrete Fourier transform (DFT) operation, which leads to the formulation of a structured block sparse signal recovery problem with a sparse sensing matrix. This enables the development of a low complexity message passing based Bayesian algorithm with a factor graph representation. Simulation results demonstrate the superior performance of the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.00313v1-abstract-full').style.display = 'none'; document.getElementById('2309.00313v1-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.00291">arXiv:2308.00291</a> <span> [<a href="https://arxiv.org/pdf/2308.00291">pdf</a>, <a href="https://arxiv.org/format/2308.00291">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"> Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+L">Lehan Wang</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+W">Weihang Dai</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mei Jin</a>, <a href="/search/eess?searchtype=author&query=Ou%2C+C">Chubin Ou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiaomeng 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="2308.00291v1-abstract-short" style="display: inline;"> Optical Coherence Tomography (OCT) is a novel and effective screening tool for ophthalmic examination. Since collecting OCT images is relatively more expensive than fundus photographs, existing methods use multi-modal learning to complement limited OCT data with additional context from fundus images. However, the multi-modal framework requires eye-paired datasets of both modalities, which is impra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.00291v1-abstract-full').style.display = 'inline'; document.getElementById('2308.00291v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.00291v1-abstract-full" style="display: none;"> Optical Coherence Tomography (OCT) is a novel and effective screening tool for ophthalmic examination. Since collecting OCT images is relatively more expensive than fundus photographs, existing methods use multi-modal learning to complement limited OCT data with additional context from fundus images. However, the multi-modal framework requires eye-paired datasets of both modalities, which is impractical for clinical use. To address this problem, we propose a novel fundus-enhanced disease-aware distillation model (FDDM), for retinal disease classification from OCT images. Our framework enhances the OCT model during training by utilizing unpaired fundus images and does not require the use of fundus images during testing, which greatly improves the practicality and efficiency of our method for clinical use. Specifically, we propose a novel class prototype matching to distill disease-related information from the fundus model to the OCT model and a novel class similarity alignment to enforce consistency between disease distribution of both modalities. Experimental results show that our proposed approach outperforms single-modal, multi-modal, and state-of-the-art distillation methods for retinal disease classification. Code is available at https://github.com/xmed-lab/FDDM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.00291v1-abstract-full').style.display = 'none'; document.getElementById('2308.00291v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </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 as a conference paper at MICCAI 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.10125">arXiv:2306.10125</a> <span> [<a href="https://arxiv.org/pdf/2306.10125">pdf</a>, <a href="https://arxiv.org/format/2306.10125">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</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"> Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+K">Kexin Zhang</a>, <a href="/search/eess?searchtype=author&query=Wen%2C+Q">Qingsong Wen</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+C">Chaoli Zhang</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+R">Rongyao Cai</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yong Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">James Zhang</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+Y">Yuxuan Liang</a>, <a href="/search/eess?searchtype=author&query=Pang%2C+G">Guansong Pang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+D">Dongjin Song</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+S">Shirui Pan</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="2306.10125v4-abstract-short" style="display: inline;"> Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural langu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.10125v4-abstract-full').style.display = 'inline'; document.getElementById('2306.10125v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.10125v4-abstract-full" style="display: none;"> Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review current state-of-the-art SSL methods for time series data in this article. To this end, we first comprehensively review existing surveys related to SSL and time series, and then provide a new taxonomy of existing time series SSL methods by summarizing them from three perspectives: generative-based, contrastive-based, and adversarial-based. These methods are further divided into ten subcategories with detailed reviews and discussions about their key intuitions, main frameworks, advantages and disadvantages. To facilitate the experiments and validation of time series SSL methods, we also summarize datasets commonly used in time series forecasting, classification, anomaly detection, and clustering tasks. Finally, we present the future directions of SSL for time series analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.10125v4-abstract-full').style.display = 'none'; document.getElementById('2306.10125v4-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </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 Transactions on Pattern Analysis and Machine Intelligence (TPAMI); 26 pages, 200+ references; the first work to comprehensively and systematically summarize self-supervised learning for time series analysis (SSL4TS). The GitHub repository is https://github.com/qingsongedu/Awesome-SSL4TS</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.20006">arXiv:2305.20006</a> <span> [<a href="https://arxiv.org/pdf/2305.20006">pdf</a>, <a href="https://arxiv.org/format/2305.20006">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"> Physics-Informed Ensemble Representation for Light-Field Image Super-Resolution </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+M">Manchang Jin</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+G">Gaosheng Liu</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+K">Kunshu Hu</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+X">Xin Luo</a>, <a href="/search/eess?searchtype=author&query=Li%2C+K">Kun Li</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+J">Jingyu 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="2305.20006v1-abstract-short" style="display: inline;"> Recent learning-based approaches have achieved significant progress in light field (LF) image super-resolution (SR) by exploring convolution-based or transformer-based network structures. However, LF imaging has many intrinsic physical priors that have not been fully exploited. In this paper, we analyze the coordinate transformation of the LF imaging process to reveal the geometric relationship in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.20006v1-abstract-full').style.display = 'inline'; document.getElementById('2305.20006v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.20006v1-abstract-full" style="display: none;"> Recent learning-based approaches have achieved significant progress in light field (LF) image super-resolution (SR) by exploring convolution-based or transformer-based network structures. However, LF imaging has many intrinsic physical priors that have not been fully exploited. In this paper, we analyze the coordinate transformation of the LF imaging process to reveal the geometric relationship in the LF images. Based on such geometric priors, we introduce a new LF subspace of virtual-slit images (VSI) that provide sub-pixel information complementary to sub-aperture images. To leverage the abundant correlation across the four-dimensional data with manageable complexity, we propose learning ensemble representation of all $C_4^2$ LF subspaces for more effective feature extraction. To super-resolve image structures from undersampled LF data, we propose a geometry-aware decoder, named EPIXformer, which constrains the transformer's operational searching regions with a LF physical prior. Experimental results on both spatial and angular SR tasks demonstrate that the proposed method outperforms other state-of-the-art schemes, especially in handling various disparities. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.20006v1-abstract-full').style.display = 'none'; document.getElementById('2305.20006v1-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> 31 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.03546">arXiv:2305.03546</a> <span> [<a href="https://arxiv.org/pdf/2305.03546">pdf</a>, <a href="https://arxiv.org/format/2305.03546">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"> Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chuang Zhu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shengjie Liu</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+Z">Zekuan Yu</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+F">Feng Xu</a>, <a href="/search/eess?searchtype=author&query=Aggarwal%2C+A">Arpit Aggarwal</a>, <a href="/search/eess?searchtype=author&query=Corredor%2C+G">Germ谩n Corredor</a>, <a href="/search/eess?searchtype=author&query=Madabhushi%2C+A">Anant Madabhushi</a>, <a href="/search/eess?searchtype=author&query=Qu%2C+Q">Qixun Qu</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+H">Hongwei Fan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+F">Fangda Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yueheng Li</a>, <a href="/search/eess?searchtype=author&query=Guan%2C+X">Xianchao Guan</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yongbing Zhang</a>, <a href="/search/eess?searchtype=author&query=Singh%2C+V+K">Vivek Kumar Singh</a>, <a href="/search/eess?searchtype=author&query=Akram%2C+F">Farhan Akram</a>, <a href="/search/eess?searchtype=author&query=Sarker%2C+M+M+K">Md. Mostafa Kamal Sarker</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Z">Zhongyue Shi</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mulan Jin</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="2305.03546v2-abstract-short" style="display: inline;"> For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in breast tissue to formulate a precise treatment plan. From the perspective of saving manpower, material and time costs, directly generating IHC-stained images from Hematoxylin and Eosin (H&E) stained images is a valuable research direct… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.03546v2-abstract-full').style.display = 'inline'; document.getElementById('2305.03546v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.03546v2-abstract-full" style="display: none;"> For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in breast tissue to formulate a precise treatment plan. From the perspective of saving manpower, material and time costs, directly generating IHC-stained images from Hematoxylin and Eosin (H&E) stained images is a valuable research direction. Therefore, we held the breast cancer immunohistochemical image generation challenge, aiming to explore novel ideas of deep learning technology in pathological image generation and promote research in this field. The challenge provided registered H&E and IHC-stained image pairs, and participants were required to use these images to train a model that can directly generate IHC-stained images from corresponding H&E-stained images. We selected and reviewed the five highest-ranking methods based on their PSNR and SSIM metrics, while also providing overviews of the corresponding pipelines and implementations. In this paper, we further analyze the current limitations in the field of breast cancer immunohistochemical image generation and forecast the future development of this field. We hope that the released dataset and the challenge will inspire more scholars to jointly study higher-quality IHC-stained image generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.03546v2-abstract-full').style.display = 'none'; document.getElementById('2305.03546v2-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 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </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, 2tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.10949">arXiv:2303.10949</a> <span> [<a href="https://arxiv.org/pdf/2303.10949">pdf</a>, <a href="https://arxiv.org/format/2303.10949">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="Computation and Language">cs.CL</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"> Code-Switching Text Generation and Injection in Mandarin-English ASR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+H">Haibin Yu</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Y">Yuxuan Hu</a>, <a href="/search/eess?searchtype=author&query=Qian%2C+Y">Yao Qian</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ma Jin</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Linquan Liu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shujie Liu</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Y">Yu Shi</a>, <a href="/search/eess?searchtype=author&query=Qian%2C+Y">Yanmin Qian</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+E">Edward Lin</a>, <a href="/search/eess?searchtype=author&query=Zeng%2C+M">Michael Zeng</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="2303.10949v1-abstract-short" style="display: inline;"> Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transd… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.10949v1-abstract-full').style.display = 'inline'; document.getElementById('2303.10949v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.10949v1-abstract-full" style="display: none;"> Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T), in Mandarin-English code-switching speech recognition. We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models, i.e., 16% relative Token-based Error Rate (TER) reduction averaged on three evaluation sets, and the approach of tying speech and text latent spaces is superior to that of TTS conversion on the evaluation set which contains more homogeneous data with the training set. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.10949v1-abstract-full').style.display = 'none'; document.getElementById('2303.10949v1-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 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </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 ICASSP 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.06200">arXiv:2303.06200</a> <span> [<a href="https://arxiv.org/pdf/2303.06200">pdf</a>, <a href="https://arxiv.org/format/2303.06200">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"> Monte Carlo Grid Dynamic Programming: Almost Sure Convergence and Probability Constraints </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ramadan%2C+M+S">Mohammad S. Ramadan</a>, <a href="/search/eess?searchtype=author&query=Al-Tawaha%2C+A">Ahmad Al-Tawaha</a>, <a href="/search/eess?searchtype=author&query=Shouman%2C+M">Mohamed Shouman</a>, <a href="/search/eess?searchtype=author&query=Atallah%2C+A">Ahmed Atallah</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2303.06200v3-abstract-short" style="display: inline;"> Dynamic Programming (DP) suffers from the well-known ``curse of dimensionality'', further exacerbated by the need to compute expectations over process noise in stochastic models. This paper presents a Monte Carlo-based sampling approach for the state space and an interpolation procedure for the resulting value function, dependent on the process noise density, in a "self-approximating" fashion, eli… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06200v3-abstract-full').style.display = 'inline'; document.getElementById('2303.06200v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.06200v3-abstract-full" style="display: none;"> Dynamic Programming (DP) suffers from the well-known ``curse of dimensionality'', further exacerbated by the need to compute expectations over process noise in stochastic models. This paper presents a Monte Carlo-based sampling approach for the state space and an interpolation procedure for the resulting value function, dependent on the process noise density, in a "self-approximating" fashion, eliminating the need for ordering or set-membership tests. We provide proof of almost sure convergence for the value iteration (and consequently, policy iteration) procedure. The proposed meshless sampling and interpolation algorithm alleviates the burden of gridding the state space, traditionally required in DP, and avoids constructing a piecewise constant value function over a grid. Moreover, we demonstrate that the proposed interpolation procedure is well-suited for handling probabilistic constraints by sampling both infeasible and feasible regions. The curse of dimensionality cannot be avoided, however, this approach offers a practical framework for addressing lower-order stochastic nonlinear systems with probabilistic constraints, while eliminating the need for linear interpolations and set membership tests. Numerical examples are presented to further explain and illustrate the convenience of the proposed algorithms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.06200v3-abstract-full').style.display = 'none'; document.getElementById('2303.06200v3-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </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, 1 figure</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2302.07844">arXiv:2302.07844</a> <span> [<a href="https://arxiv.org/pdf/2302.07844">pdf</a>, <a href="https://arxiv.org/format/2302.07844">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> </div> </div> <p class="title is-5 mathjax"> Deep Learning for Detection and Localization of B-Lines in Lung Ultrasound </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Lucassen%2C+R+T">Ruben T. Lucassen</a>, <a href="/search/eess?searchtype=author&query=Jafari%2C+M+H">Mohammad H. Jafari</a>, <a href="/search/eess?searchtype=author&query=Duggan%2C+N+M">Nicole M. Duggan</a>, <a href="/search/eess?searchtype=author&query=Jowkar%2C+N">Nick Jowkar</a>, <a href="/search/eess?searchtype=author&query=Mehrtash%2C+A">Alireza Mehrtash</a>, <a href="/search/eess?searchtype=author&query=Fischetti%2C+C">Chanel Fischetti</a>, <a href="/search/eess?searchtype=author&query=Bernier%2C+D">Denie Bernier</a>, <a href="/search/eess?searchtype=author&query=Prentice%2C+K">Kira Prentice</a>, <a href="/search/eess?searchtype=author&query=Duhaime%2C+E+P">Erik P. Duhaime</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mike Jin</a>, <a href="/search/eess?searchtype=author&query=Abolmaesumi%2C+P">Purang Abolmaesumi</a>, <a href="/search/eess?searchtype=author&query=Heslinga%2C+F+G">Friso G. Heslinga</a>, <a href="/search/eess?searchtype=author&query=Veta%2C+M">Mitko Veta</a>, <a href="/search/eess?searchtype=author&query=Duran-Mendicuti%2C+M+A">Maria A. Duran-Mendicuti</a>, <a href="/search/eess?searchtype=author&query=Frisken%2C+S">Sarah Frisken</a>, <a href="/search/eess?searchtype=author&query=Shyn%2C+P+B">Paul B. Shyn</a>, <a href="/search/eess?searchtype=author&query=Golby%2C+A+J">Alexandra J. Golby</a>, <a href="/search/eess?searchtype=author&query=Boyer%2C+E">Edward Boyer</a>, <a href="/search/eess?searchtype=author&query=Wells%2C+W+M">William M. Wells</a>, <a href="/search/eess?searchtype=author&query=Goldsmith%2C+A+J">Andrew J. Goldsmith</a>, <a href="/search/eess?searchtype=author&query=Kapur%2C+T">Tina Kapur</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="2302.07844v1-abstract-short" style="display: inline;"> Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we inve… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.07844v1-abstract-full').style.display = 'inline'; document.getElementById('2302.07844v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2302.07844v1-abstract-full" style="display: none;"> Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish, BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel "single-point" approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F1-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2302.07844v1-abstract-full').style.display = 'none'; document.getElementById('2302.07844v1-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 February, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2023. </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">10 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/2212.01939">arXiv:2212.01939</a> <span> [<a href="https://arxiv.org/pdf/2212.01939">pdf</a>, <a href="https://arxiv.org/format/2212.01939">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> </div> </div> <p class="title is-5 mathjax"> Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Khattar%2C+V">Vanshaj Khattar</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2212.01939v1-abstract-short" style="display: inline;"> Modern power systems will have to face difficult challenges in the years to come: frequent blackouts in urban areas caused by high power demand peaks, grid instability exacerbated by intermittent renewable generation, and global climate change amplified by rising carbon emissions. While current practices are growingly inadequate, the path to widespread adoption of artificial intelligence (AI) meth… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.01939v1-abstract-full').style.display = 'inline'; document.getElementById('2212.01939v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2212.01939v1-abstract-full" style="display: none;"> Modern power systems will have to face difficult challenges in the years to come: frequent blackouts in urban areas caused by high power demand peaks, grid instability exacerbated by intermittent renewable generation, and global climate change amplified by rising carbon emissions. While current practices are growingly inadequate, the path to widespread adoption of artificial intelligence (AI) methods is hindered by missing aspects of trustworthiness. The CityLearn Challenge is an exemplary opportunity for researchers from multiple disciplines to investigate the potential of AI to tackle these pressing issues in the energy domain, collectively modeled as a reinforcement learning (RL) task. Multiple real-world challenges faced by contemporary RL techniques are embodied in the problem formulation. In this paper, we present a novel method using the solution function of optimization as policies to compute actions for sequential decision-making, while notably adapting the parameters of the optimization model from online observations. Algorithmically, this is achieved by an evolutionary algorithm under a novel trajectory-based guidance scheme. Formally, the global convergence property is established. Our agent ranked first in the latest 2021 CityLearn Challenge, being able to achieve superior performance in almost all metrics while maintaining some key aspects of interpretability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2212.01939v1-abstract-full').style.display = 'none'; document.getElementById('2212.01939v1-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> 4 December, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.13282">arXiv:2211.13282</a> <span> [<a href="https://arxiv.org/pdf/2211.13282">pdf</a>, <a href="https://arxiv.org/format/2211.13282">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"> Voice-preserving Zero-shot Multiple Accent Conversion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mumin Jin</a>, <a href="/search/eess?searchtype=author&query=Serai%2C+P">Prashant Serai</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+J">Jilong Wu</a>, <a href="/search/eess?searchtype=author&query=Tjandra%2C+A">Andros Tjandra</a>, <a href="/search/eess?searchtype=author&query=Manohar%2C+V">Vimal Manohar</a>, <a href="/search/eess?searchtype=author&query=He%2C+Q">Qing He</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="2211.13282v2-abstract-short" style="display: inline;"> Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent. For native speakers, understanding or speaking a new accent is likewise a difficult task. An accent conversion system that changes a speaker's accent but preserves that speaker's voice identity, such as timbre and pitch, has the potential for a range… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.13282v2-abstract-full').style.display = 'inline'; document.getElementById('2211.13282v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.13282v2-abstract-full" style="display: none;"> Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent. For native speakers, understanding or speaking a new accent is likewise a difficult task. An accent conversion system that changes a speaker's accent but preserves that speaker's voice identity, such as timbre and pitch, has the potential for a range of applications, such as communication, language learning, and entertainment. Existing accent conversion models tend to change the speaker identity and accent at the same time. Here, we use adversarial learning to disentangle accent dependent features while retaining other acoustic characteristics. What sets our work apart from existing accent conversion models is the capability to convert an unseen speaker's utterance to multiple accents while preserving its original voice identity. Subjective evaluations show that our model generates audio that sound closer to the target accent and like the original speaker. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.13282v2-abstract-full').style.display = 'none'; document.getElementById('2211.13282v2-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </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 IEEE ICASSP 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.04847">arXiv:2211.04847</a> <span> [<a href="https://arxiv.org/pdf/2211.04847">pdf</a>, <a href="https://arxiv.org/format/2211.04847">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"> Hyper-Parameter Auto-Tuning for Sparse Bayesian Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gao%2C+D">Dawei Gao</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Q">Qinghua Guo</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Liao%2C+G">Guisheng Liao</a>, <a href="/search/eess?searchtype=author&query=Eldar%2C+Y+C">Yonina C. Eldar</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="2211.04847v1-abstract-short" style="display: inline;"> Choosing the values of hyper-parameters in sparse Bayesian learning (SBL) can significantly impact performance. However, the hyper-parameters are normally tuned manually, which is often a difficult task. Most recently, effective automatic hyper-parameter tuning was achieved by using an empirical auto-tuner. In this work, we address the issue of hyper-parameter auto-tuning using neural network (NN)… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.04847v1-abstract-full').style.display = 'inline'; document.getElementById('2211.04847v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.04847v1-abstract-full" style="display: none;"> Choosing the values of hyper-parameters in sparse Bayesian learning (SBL) can significantly impact performance. However, the hyper-parameters are normally tuned manually, which is often a difficult task. Most recently, effective automatic hyper-parameter tuning was achieved by using an empirical auto-tuner. In this work, we address the issue of hyper-parameter auto-tuning using neural network (NN)-based learning. Inspired by the empirical auto-tuner, we design and learn a NN-based auto-tuner, and show that considerable improvement in convergence rate and recovery performance can be achieved. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.04847v1-abstract-full').style.display = 'none'; document.getElementById('2211.04847v1-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 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2211.04687">arXiv:2211.04687</a> <span> [<a href="https://arxiv.org/pdf/2211.04687">pdf</a>, <a href="https://arxiv.org/format/2211.04687">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"> Lightweight network towards real-time image denoising on mobile devices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zhuoqun Liu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Meiguang Jin</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Ying Chen</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Huaida Liu</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+C">Canqian Yang</a>, <a href="/search/eess?searchtype=author&query=Xiong%2C+H">Hongkai Xiong</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="2211.04687v2-abstract-short" style="display: inline;"> Deep convolutional neural networks have achieved great progress in image denoising tasks. However, their complicated architectures and heavy computational cost hinder their deployments on mobile devices. Some recent efforts in designing lightweight denoising networks focus on reducing either FLOPs (floating-point operations) or the number of parameters. However, these metrics are not directly corr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.04687v2-abstract-full').style.display = 'inline'; document.getElementById('2211.04687v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2211.04687v2-abstract-full" style="display: none;"> Deep convolutional neural networks have achieved great progress in image denoising tasks. However, their complicated architectures and heavy computational cost hinder their deployments on mobile devices. Some recent efforts in designing lightweight denoising networks focus on reducing either FLOPs (floating-point operations) or the number of parameters. However, these metrics are not directly correlated with the on-device latency. In this paper, we identify the real bottlenecks that affect the CNN-based models' run-time performance on mobile devices: memory access cost and NPU-incompatible operations, and build the model based on these. To further improve the denoising performance, the mobile-friendly attention module MFA and the model reparameterization module RepConv are proposed, which enjoy both low latency and excellent denoising performance. To this end, we propose a mobile-friendly denoising network, namely MFDNet. The experiments show that MFDNet achieves state-of-the-art performance on real-world denoising benchmarks SIDD and DND under real-time latency on mobile devices. The code and pre-trained models will be released. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2211.04687v2-abstract-full').style.display = 'none'; document.getElementById('2211.04687v2-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> 25 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 November, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2022. </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">Under review at the 2023 IEEE International Conference on Image Processing (ICIP 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2210.13773">arXiv:2210.13773</a> <span> [<a href="https://arxiv.org/pdf/2210.13773">pdf</a>, <a href="https://arxiv.org/format/2210.13773">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="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Variational Bayesian Inference Clustering Based Joint User Activity and Data Detection for Grant-Free Random Access in mMTC </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zhaoji Zhang</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Q">Qinghua Guo</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Ying Li</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+C">Chongwen 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="2210.13773v1-abstract-short" style="display: inline;"> Tailor-made for massive connectivity and sporadic access, grant-free random access has become a promising candidate access protocol for massive machine-type communications (mMTC). Compared with conventional grant-based protocols, grant-free random access skips the exchange of scheduling information to reduce the signaling overhead, and facilitates sharing of access resources to enhance access effi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13773v1-abstract-full').style.display = 'inline'; document.getElementById('2210.13773v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2210.13773v1-abstract-full" style="display: none;"> Tailor-made for massive connectivity and sporadic access, grant-free random access has become a promising candidate access protocol for massive machine-type communications (mMTC). Compared with conventional grant-based protocols, grant-free random access skips the exchange of scheduling information to reduce the signaling overhead, and facilitates sharing of access resources to enhance access efficiency. However, some challenges remain to be addressed in the receiver design, such as unknown identity of active users and multi-user interference (MUI) on shared access resources. In this work, we deal with the problem of joint user activity and data detection for grant-free random access. Specifically, the approximate message passing (AMP) algorithm is first employed to mitigate MUI and decouple the signals of different users. Then, we extend the data symbol alphabet to incorporate the null symbols from inactive users. In this way, the joint user activity and data detection problem is formulated as a clustering problem under the Gaussian mixture model. Furthermore, in conjunction with the AMP algorithm, a variational Bayesian inference based clustering (VBIC) algorithm is developed to solve this clustering problem. Simulation results show that, compared with state-of-art solutions, the proposed AMP-combined VBIC (AMP-VBIC) algorithm achieves a significant performance gain in detection accuracy. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2210.13773v1-abstract-full').style.display = 'none'; document.getElementById('2210.13773v1-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> 25 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2022. </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">10 pages, 5 figures, submitted to 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/2209.15334">arXiv:2209.15334</a> <span> [<a href="https://arxiv.org/pdf/2209.15334">pdf</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="Networking and Internet Architecture">cs.NI</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"> ChordMics: Acoustic Signal Purification with Distributed Microphones </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+W">Weiguo Wang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jinming Li</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Meng Jin</a>, <a href="/search/eess?searchtype=author&query=He%2C+Y">Yuan He</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="2209.15334v1-abstract-short" style="display: inline;"> Acoustic signal acts as an essential input to many systems. However, the pure acoustic signal is very difficult to extract, especially in noisy environments. Existing beamforming systems are able to extract the signal transmitted from certain directions. However, since microphones are centrally deployed, these systems have limited coverage and low spatial resolution. We overcome the above limitati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.15334v1-abstract-full').style.display = 'inline'; document.getElementById('2209.15334v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2209.15334v1-abstract-full" style="display: none;"> Acoustic signal acts as an essential input to many systems. However, the pure acoustic signal is very difficult to extract, especially in noisy environments. Existing beamforming systems are able to extract the signal transmitted from certain directions. However, since microphones are centrally deployed, these systems have limited coverage and low spatial resolution. We overcome the above limitations and present ChordMics, a distributed beamforming system. By leveraging the spatial diversity of the distributed microphones, ChordMics is able to extract the acoustic signal from arbitrary points. To realize such a system, we further address the fundamental challenge in distributed beamforming: aligning the signals captured by distributed and unsynchronized microphones. We implement ChordMics and evaluate its performance under both LOS and NLOS scenarios. The evaluation results tell that ChordMics can deliver higher SINR than the centralized microphone array. The average performance gain is up to 15dB. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2209.15334v1-abstract-full').style.display = 'none'; document.getElementById('2209.15334v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.08351">arXiv:2207.08351</a> <span> [<a href="https://arxiv.org/pdf/2207.08351">pdf</a>, <a href="https://arxiv.org/format/2207.08351">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"> SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yang%2C+C">Canqian Yang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Meiguang Jin</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yi Xu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rui Zhang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Y">Ying Chen</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Huaida Liu</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="2207.08351v1-abstract-short" style="display: inline;"> Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms. However, they embed the complete transform, including the color component-independent and the component-correlated parts, into only a single type of LUTs, either 1D or 3D, in a coupled manner. This scheme raises a dilemma of improving mode… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.08351v1-abstract-full').style.display = 'inline'; document.getElementById('2207.08351v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.08351v1-abstract-full" style="display: none;"> Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms. However, they embed the complete transform, including the color component-independent and the component-correlated parts, into only a single type of LUTs, either 1D or 3D, in a coupled manner. This scheme raises a dilemma of improving model expressiveness or efficiency due to two factors. On the one hand, the 1D LUTs provide high computational efficiency but lack the critical capability of color components interaction. On the other, the 3D LUTs present enhanced component-correlated transform capability but suffer from heavy memory footprint, high training difficulty, and limited cell utilization. Inspired by the conventional divide-and-conquer practice in the image signal processor, we present SepLUT (separable image-adaptive lookup table) to tackle the above limitations. Specifically, we separate a single color transform into a cascade of component-independent and component-correlated sub-transforms instantiated as 1D and 3D LUTs, respectively. In this way, the capabilities of two sub-transforms can facilitate each other, where the 3D LUT complements the ability to mix up color components, and the 1D LUT redistributes the input colors to increase the cell utilization of the 3D LUT and thus enable the use of a more lightweight 3D LUT. Experiments demonstrate that the proposed method presents enhanced performance on photo retouching benchmark datasets than the current state-of-the-art and achieves real-time processing on both GPUs and CPUs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.08351v1-abstract-full').style.display = 'none'; document.getElementById('2207.08351v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </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 ECCV 2022</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.07776">arXiv:2207.07776</a> <span> [<a href="https://arxiv.org/pdf/2207.07776">pdf</a>, <a href="https://arxiv.org/format/2207.07776">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 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/10.21437/Interspeech.2022-10948">10.21437/Interspeech.2022-10948 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Adversarial Reweighting for Speaker Verification Fairness </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+M">Minho Jin</a>, <a href="/search/eess?searchtype=author&query=Ju%2C+C+J+-">Chelsea J. -T. Ju</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zeya Chen</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yi-Chieh Liu</a>, <a href="/search/eess?searchtype=author&query=Droppo%2C+J">Jasha Droppo</a>, <a href="/search/eess?searchtype=author&query=Stolcke%2C+A">Andreas Stolcke</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="2207.07776v1-abstract-short" style="display: inline;"> We address performance fairness for speaker verification using the adversarial reweighting (ARW) method. ARW is reformulated for speaker verification with metric learning, and shown to improve results across different subgroups of gender and nationality, without requiring annotation of subgroups in the training data. An adversarial network learns a weight for each training sample in the batch so t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.07776v1-abstract-full').style.display = 'inline'; document.getElementById('2207.07776v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.07776v1-abstract-full" style="display: none;"> We address performance fairness for speaker verification using the adversarial reweighting (ARW) method. ARW is reformulated for speaker verification with metric learning, and shown to improve results across different subgroups of gender and nationality, without requiring annotation of subgroups in the training data. An adversarial network learns a weight for each training sample in the batch so that the main learner is forced to focus on poorly performing instances. Using a min-max optimization algorithm, this method improves overall speaker verification fairness. We present three different ARWformulations: accumulated pairwise similarity, pseudo-labeling, and pairwise weighting, and measure their performance in terms of equal error rate (EER) on the VoxCeleb corpus. Results show that the pairwise weighting method can achieve 1.08% overall EER, 1.25% for male and 0.67% for female speakers, with relative EER reductions of 7.7%, 10.1% and 3.0%, respectively. For nationality subgroups, the proposed algorithm showed 1.04% EER for US speakers, 0.76% for UK speakers, and 1.22% for all others. The absolute EER gap between gender groups was reduced from 0.70% to 0.58%, while the standard deviation over nationality groups decreased from 0.21 to 0.19. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.07776v1-abstract-full').style.display = 'none'; document.getElementById('2207.07776v1-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, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proc. Interspeech, Sept. 2022, pp. 4800-4804 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.09703">arXiv:2205.09703</a> <span> [<a href="https://arxiv.org/pdf/2205.09703">pdf</a>, <a href="https://arxiv.org/format/2205.09703">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="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Performance">cs.PF</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="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Extract Dynamic Information To Improve Time Series Modeling: a Case Study with Scientific Workflow </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Kim%2C+J">Jeeyung Kim</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mengtian Jin</a>, <a href="/search/eess?searchtype=author&query=Homma%2C+Y">Youkow Homma</a>, <a href="/search/eess?searchtype=author&query=Sim%2C+A">Alex Sim</a>, <a href="/search/eess?searchtype=author&query=Kroeger%2C+W">Wilko Kroeger</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+K">Kesheng 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="2205.09703v1-abstract-short" style="display: inline;"> In modeling time series data, we often need to augment the existing data records to increase the modeling accuracy. In this work, we describe a number of techniques to extract dynamic information about the current state of a large scientific workflow, which could be generalized to other types of applications. The specific task to be modeled is the time needed for transferring a file from an experi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.09703v1-abstract-full').style.display = 'inline'; document.getElementById('2205.09703v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.09703v1-abstract-full" style="display: none;"> In modeling time series data, we often need to augment the existing data records to increase the modeling accuracy. In this work, we describe a number of techniques to extract dynamic information about the current state of a large scientific workflow, which could be generalized to other types of applications. The specific task to be modeled is the time needed for transferring a file from an experimental facility to a data center. The key idea of our approach is to find recent past data transfer events that match the current event in some ways. Tests showed that we could identify recent events matching some recorded properties and reduce the prediction error by about 12% compared to the similar models with only static features. We additionally explored an application specific technique to extract information about the data production process, and was able to reduce the average prediction error by 44%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.09703v1-abstract-full').style.display = 'none'; document.getElementById('2205.09703v1-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.05675">arXiv:2205.05675</a> <span> [<a href="https://arxiv.org/pdf/2205.05675">pdf</a>, <a href="https://arxiv.org/format/2205.05675">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"> NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yawei Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/eess?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/eess?searchtype=author&query=Van+Gool%2C+L">Luc Van Gool</a>, <a href="/search/eess?searchtype=author&query=Kong%2C+F">Fangyuan Kong</a>, <a href="/search/eess?searchtype=author&query=Li%2C+M">Mingxi Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+S">Songwei Liu</a>, <a href="/search/eess?searchtype=author&query=Du%2C+Z">Zongcai Du</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+D">Ding Liu</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+C">Chenhui Zhou</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+J">Jingyi Chen</a>, <a href="/search/eess?searchtype=author&query=Han%2C+Q">Qingrui Han</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zheyuan Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yingqi Liu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xiangyu Chen</a>, <a href="/search/eess?searchtype=author&query=Cai%2C+H">Haoming Cai</a>, <a href="/search/eess?searchtype=author&query=Qiao%2C+Y">Yu Qiao</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+C">Chao Dong</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+L">Long Sun</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+J">Jinshan Pan</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+Y">Yi Zhu</a>, <a href="/search/eess?searchtype=author&query=Zong%2C+Z">Zhikai Zong</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+X">Xiaoxiao Liu</a>, <a href="/search/eess?searchtype=author&query=Hui%2C+Z">Zheng Hui</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+T">Tao Yang</a> , et al. (86 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="2205.05675v1-abstract-short" style="display: inline;"> This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of e… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.05675v1-abstract-full').style.display = 'inline'; document.getElementById('2205.05675v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.05675v1-abstract-full" style="display: none;"> This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.05675v1-abstract-full').style.display = 'none'; document.getElementById('2205.05675v1-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </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">Validation code of the baseline model is available at https://github.com/ofsoundof/IMDN. Validation of all submitted models is available at https://github.com/ofsoundof/NTIRE2022_ESR</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2204.11425">arXiv:2204.11425</a> <span> [<a href="https://arxiv.org/pdf/2204.11425">pdf</a>, <a href="https://arxiv.org/format/2204.11425">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"> BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+S">Shengjie Liu</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chuang Zhu</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+F">Feng Xu</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+X">Xinyu Jia</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Z">Zhongyue Shi</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mulan Jin</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="2204.11425v2-abstract-short" style="display: inline;"> The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer. The routine evaluation of HER2 is conducted with immunohistochemical techniques (IHC), which is very expensive. Therefore, for the first time, we propose a breast cancer immunohistochemical (BCI) benchmark attempting to synthesize IHC data directly with the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.11425v2-abstract-full').style.display = 'inline'; document.getElementById('2204.11425v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2204.11425v2-abstract-full" style="display: none;"> The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer. The routine evaluation of HER2 is conducted with immunohistochemical techniques (IHC), which is very expensive. Therefore, for the first time, we propose a breast cancer immunohistochemical (BCI) benchmark attempting to synthesize IHC data directly with the paired hematoxylin and eosin (HE) stained images. The dataset contains 4870 registered image pairs, covering a variety of HER2 expression levels. Based on BCI, as a minor contribution, we further build a pyramid pix2pix image generation method, which achieves better HE to IHC translation results than the other current popular algorithms. Extensive experiments demonstrate that BCI poses new challenges to the existing image translation research. Besides, BCI also opens the door for future pathology studies in HER2 expression evaluation based on the synthesized IHC images. BCI dataset can be downloaded from https://bupt-ai-cz.github.io/BCI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2204.11425v2-abstract-full').style.display = 'none'; document.getElementById('2204.11425v2-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 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 April, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2022. </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 CVPR2022 Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.12349">arXiv:2202.12349</a> <span> [<a href="https://arxiv.org/pdf/2202.12349">pdf</a>, <a href="https://arxiv.org/format/2202.12349">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> </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/10.1109/ICASSP43922.2022.9747613">10.1109/ICASSP43922.2022.9747613 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=C%2C+K+K">Kishan K C</a>, <a href="/search/eess?searchtype=author&query=Tan%2C+Z">Zhenning Tan</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+L">Long Chen</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Minho Jin</a>, <a href="/search/eess?searchtype=author&query=Han%2C+E">Eunjung Han</a>, <a href="/search/eess?searchtype=author&query=Stolcke%2C+A">Andreas Stolcke</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+C">Chul Lee</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="2202.12349v1-abstract-short" style="display: inline;"> Household speaker identification with few enrollment utterances is an important yet challenging problem, especially when household members share similar voice characteristics and room acoustics. A common embedding space learned from a large number of speakers is not universally applicable for the optimal identification of every speaker in a household. In this work, we first formulate household spe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12349v1-abstract-full').style.display = 'inline'; document.getElementById('2202.12349v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.12349v1-abstract-full" style="display: none;"> Household speaker identification with few enrollment utterances is an important yet challenging problem, especially when household members share similar voice characteristics and room acoustics. A common embedding space learned from a large number of speakers is not universally applicable for the optimal identification of every speaker in a household. In this work, we first formulate household speaker identification as a few-shot open-set recognition task and then propose a novel embedding adaptation framework to adapt speaker representations from the given universal embedding space to a household-specific embedding space using a set-to-set function, yielding better household speaker identification performance. With our algorithm, Open-set Few-shot Embedding Adaptation with Transformer (openFEAT), we observe that the speaker identification equal error rate (IEER) on simulated households with 2 to 7 hard-to-discriminate speakers is reduced by 23% to 31% relative. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.12349v1-abstract-full').style.display = 'none'; document.getElementById('2202.12349v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </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 Proc. IEEE ICASSP 2022</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proc. IEEE ICASSP, May 2022, pp. 7062-7066 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.11246">arXiv:2202.11246</a> <span> [<a href="https://arxiv.org/pdf/2202.11246">pdf</a>, <a href="https://arxiv.org/format/2202.11246">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Learning Neural Networks under Input-Output Specifications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Abdeen%2C+Z+u">Zain ul Abdeen</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+H">He Yin</a>, <a href="/search/eess?searchtype=author&query=Kekatos%2C+V">Vassilis Kekatos</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2202.11246v1-abstract-short" style="display: inline;"> In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors. Our strategy is to find an inner approximation of the set of admissible policy parameters, which is convex in a transformed space. To this end, we address the key technical challenge of convexifying the verification condition for neural networks, which… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11246v1-abstract-full').style.display = 'inline'; document.getElementById('2202.11246v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.11246v1-abstract-full" style="display: none;"> In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors. Our strategy is to find an inner approximation of the set of admissible policy parameters, which is convex in a transformed space. To this end, we address the key technical challenge of convexifying the verification condition for neural networks, which is derived by abstracting the nonlinear specifications and activation functions with quadratic constraints. In particular, we propose a reparametrization scheme of the original neural network based on loop transformation, which leads to a convex condition that can be enforced during learning. This theoretical construction is validated in an experiment that specifies reachable sets for different regions of inputs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.11246v1-abstract-full').style.display = 'none'; document.getElementById('2202.11246v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2202.10672">arXiv:2202.10672</a> <span> [<a href="https://arxiv.org/pdf/2202.10672">pdf</a>, <a href="https://arxiv.org/format/2202.10672">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</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/10.1109/ICASSP43922.2022.9746411">10.1109/ICASSP43922.2022.9746411 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Contrastive-mixup learning for improved speaker verification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xin Zhang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Minho Jin</a>, <a href="/search/eess?searchtype=author&query=Cheng%2C+R">Roger Cheng</a>, <a href="/search/eess?searchtype=author&query=Li%2C+R">Ruirui Li</a>, <a href="/search/eess?searchtype=author&query=Han%2C+E">Eunjung Han</a>, <a href="/search/eess?searchtype=author&query=Stolcke%2C+A">Andreas Stolcke</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="2202.10672v1-abstract-short" style="display: inline;"> This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for deep neural network training. Mixup has attracted increasing attention due to its ability to improve robustness and generalization of deep neural networks. Althou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.10672v1-abstract-full').style.display = 'inline'; document.getElementById('2202.10672v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2202.10672v1-abstract-full" style="display: none;"> This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for deep neural network training. Mixup has attracted increasing attention due to its ability to improve robustness and generalization of deep neural networks. Although mixup has shown success in diverse domains, most applications have centered around closed-set classification tasks. In this work, we propose contrastive-mixup, a novel augmentation strategy that learns distinguishing representations based on a distance metric. During training, mixup operations generate convex interpolations of both inputs and virtual labels. Moreover, we have reformulated the prototypical loss function such that mixup is enabled on metric learning objectives. To demonstrate its generalization given limited training data, we conduct experiments by varying the number of available utterances from each speaker in the VoxCeleb database. Experimental results show that applying contrastive-mixup outperforms the existing baseline, reducing error rate by 16% relatively, especially when the number of training utterances per speaker is limited. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2202.10672v1-abstract-full').style.display = 'none'; document.getElementById('2202.10672v1-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 February, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2022. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Proc. IEEE ICASSP, May 2022, pp. 7652-7656 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.03694">arXiv:2112.03694</a> <span> [<a href="https://arxiv.org/pdf/2112.03694">pdf</a>, <a href="https://arxiv.org/format/2112.03694">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> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</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/10.1109/TMI.2021.3125459">10.1109/TMI.2021.3125459 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Hard Sample Aware Noise Robust Learning for Histopathology Image Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chuang Zhu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+W">Wenkai Chen</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+T">Ting Peng</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Ying Wang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mulan Jin</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="2112.03694v1-abstract-short" style="display: inline;"> Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopatho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.03694v1-abstract-full').style.display = 'inline'; document.getElementById('2112.03694v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.03694v1-abstract-full" style="display: none;"> Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model by using the sample training history. Then we integrate the EHN into a self-training architecture to lower the noise rate through gradually label correction. With the obtained almost clean dataset, we further propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model. Compared with the previous works, our method can save more clean samples and can be directly applied to the real-world noisy dataset scenario without using a clean subset. Experimental results demonstrate that the proposed scheme outperforms the current state-of-the-art methods in both the synthetic and real-world noisy datasets. The source code and data are available at https://github.com/bupt-ai-cz/HSA-NRL/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.03694v1-abstract-full').style.display = 'none'; document.getElementById('2112.03694v1-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </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, 20figures, IEEE Transactions on Medical Imaging</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.0 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.02222">arXiv:2112.02222</a> <span> [<a href="https://arxiv.org/pdf/2112.02222">pdf</a>, <a href="https://arxiv.org/format/2112.02222">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="Medical Physics">physics.med-ph</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/10.3389/fonc.2021.759007">10.3389/fonc.2021.759007 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+F">Feng Xu</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chuang Zhu</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+W">Wenqi Tang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Ying Wang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yu Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jie Li</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+H">Hongchuan Jiang</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Z">Zhongyue Shi</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jun Liu</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mulan Jin</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="2112.02222v4-abstract-short" style="display: inline;"> Objectives: To develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN. Methods: A total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was bu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.02222v4-abstract-full').style.display = 'inline'; document.getElementById('2112.02222v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.02222v4-abstract-full" style="display: none;"> Objectives: To develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN. Methods: A total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was built on the attention-based multiple instance-learning (AMIL) framework to predict ALN status utilizing the DL features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) were analyzed to evaluate our model. Results: The best-performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nucleus features including density ($p$ = 0.015), circumference ($p$ = 0.009), circularity ($p$ = 0.010), and orientation ($p$ = 0.012). Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC. The codes and dataset are available at https://github.com/bupt-ai-cz/BALNMP <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.02222v4-abstract-full').style.display = 'none'; document.getElementById('2112.02222v4-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 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </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">Update Table 1 and corresponding descriptions</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Frontiers in Oncology, 11(2021), 4133 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.03861">arXiv:2109.03861</a> <span> [<a href="https://arxiv.org/pdf/2109.03861">pdf</a>, <a href="https://arxiv.org/format/2109.03861">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="Artificial Intelligence">cs.AI</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"> Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Gu%2C+F">Fangda Gu</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+H">He Yin</a>, <a href="/search/eess?searchtype=author&query=Ghaoui%2C+L+E">Laurent El Ghaoui</a>, <a href="/search/eess?searchtype=author&query=Arcak%2C+M">Murat Arcak</a>, <a href="/search/eess?searchtype=author&query=Seiler%2C+P">Peter Seiler</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</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="2109.03861v2-abstract-short" style="display: inline;"> Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed systems, in many cases, requires controllers to retain and process long-term memories of the past. We consider the important class of recurrent neural networks (RNN) as dynamic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.03861v2-abstract-full').style.display = 'inline'; document.getElementById('2109.03861v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.03861v2-abstract-full" style="display: none;"> Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed systems, in many cases, requires controllers to retain and process long-term memories of the past. We consider the important class of recurrent neural networks (RNN) as dynamic controllers for nonlinear uncertain partially-observed systems, and derive convex stability conditions based on integral quadratic constraints, S-lemma and sequential convexification. To ensure stability during the learning and control process, we propose a projected policy gradient method that iteratively enforces the stability conditions in the reparametrized space taking advantage of mild additional information on system dynamics. Numerical experiments show that our method learns stabilizing controllers while using fewer samples and achieving higher final performance compared with policy gradient. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.03861v2-abstract-full').style.display = 'none'; document.getElementById('2109.03861v2-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 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.06909">arXiv:2106.06909</a> <span> [<a href="https://arxiv.org/pdf/2106.06909">pdf</a>, <a href="https://arxiv.org/format/2106.06909">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="Computation and Language">cs.CL</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"> GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+G">Guoguo Chen</a>, <a href="/search/eess?searchtype=author&query=Chai%2C+S">Shuzhou Chai</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+G">Guanbo Wang</a>, <a href="/search/eess?searchtype=author&query=Du%2C+J">Jiayu Du</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wei-Qiang Zhang</a>, <a href="/search/eess?searchtype=author&query=Weng%2C+C">Chao Weng</a>, <a href="/search/eess?searchtype=author&query=Su%2C+D">Dan Su</a>, <a href="/search/eess?searchtype=author&query=Povey%2C+D">Daniel Povey</a>, <a href="/search/eess?searchtype=author&query=Trmal%2C+J">Jan Trmal</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Junbo Zhang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mingjie Jin</a>, <a href="/search/eess?searchtype=author&query=Khudanpur%2C+S">Sanjeev Khudanpur</a>, <a href="/search/eess?searchtype=author&query=Watanabe%2C+S">Shinji Watanabe</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+S">Shuaijiang Zhao</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+W">Wei Zou</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiangang Li</a>, <a href="/search/eess?searchtype=author&query=Yao%2C+X">Xuchen Yao</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yongqing Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yujun Wang</a>, <a href="/search/eess?searchtype=author&query=You%2C+Z">Zhao You</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+Z">Zhiyong Yan</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="2106.06909v1-abstract-short" style="display: inline;"> This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous sp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.06909v1-abstract-full').style.display = 'inline'; document.getElementById('2106.06909v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.06909v1-abstract-full" style="display: none;"> This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.06909v1-abstract-full').style.display = 'none'; document.getElementById('2106.06909v1-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 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.09049">arXiv:2102.09049</a> <span> [<a href="https://arxiv.org/pdf/2102.09049">pdf</a>, <a href="https://arxiv.org/format/2102.09049">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"> Efficient Reservoir Computing using Field Programmable Gate Array and Electro-optic Modulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Kumar%2C+P">Prajnesh Kumar</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mingwei Jin</a>, <a href="/search/eess?searchtype=author&query=Bu%2C+T">Ting Bu</a>, <a href="/search/eess?searchtype=author&query=Kumar%2C+S">Santosh Kumar</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Y">Yu-Ping 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="2102.09049v1-abstract-short" style="display: inline;"> We experimentally demonstrate a hybrid reservoir computing system consisting of an electro-optic modulator and field programmable gate array (FPGA). It implements delay lines and filters digitally for flexible dynamics and high connectivity, while supporting a large number of reservoir nodes. To evaluate the system's performance and versatility, three benchmark tests are performed. The first is th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.09049v1-abstract-full').style.display = 'inline'; document.getElementById('2102.09049v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.09049v1-abstract-full" style="display: none;"> We experimentally demonstrate a hybrid reservoir computing system consisting of an electro-optic modulator and field programmable gate array (FPGA). It implements delay lines and filters digitally for flexible dynamics and high connectivity, while supporting a large number of reservoir nodes. To evaluate the system's performance and versatility, three benchmark tests are performed. The first is the 10th order Nonlinear Auto-Regressive Moving Average test (NARMA-10), where the predictions of 1000 and 25,000 steps yield impressively low normalized root mean square errors (NRMSE's) of 0.142 and 0.148, respectively. Such accurate predictions over into the far future speak to its capability of large sample size processing, as enabled by the present hybrid design. The second is the Santa Fe laser data prediction, where a normalized mean square error (NMSE) of 6.73x10-3 is demonstrated. The third is the isolate spoken digit recognition, with a word error rate close to 0.34%. Accurate, versatile, flexibly reconfigurable, and capable of long-term prediction, this reservoir computing system could find a wealth of impactful applications in real-time information processing, weather forecasting, and financial analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.09049v1-abstract-full').style.display = 'none'; document.getElementById('2102.09049v1-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 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </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, 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/2101.09954">arXiv:2101.09954</a> <span> [<a href="https://arxiv.org/pdf/2101.09954">pdf</a>, <a href="https://arxiv.org/format/2101.09954">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 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/10.1109/TSP.2021.3114985">10.1109/TSP.2021.3114985 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Unitary Approximate Message Passing for Sparse Bayesian Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Luo%2C+M">Man Luo</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Q">Qinghua Guo</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Eldar%2C+Y+C">Yonina C. Eldar</a>, <a href="/search/eess?searchtype=author&query=Defeng"> Defeng</a>, <a href="/search/eess?searchtype=author&query=Huang"> Huang</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+X">Xiangming Meng</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="2101.09954v2-abstract-short" style="display: inline;"> Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm. However, it does not work well for a generic measurement matrix, which may cause AMP to diverge. Damped AMP has been used for SBL to alleviate the problem at the cost of reducing convergence speed. In this work, we propose a new SBL algorithm based on structured variation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.09954v2-abstract-full').style.display = 'inline'; document.getElementById('2101.09954v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2101.09954v2-abstract-full" style="display: none;"> Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm. However, it does not work well for a generic measurement matrix, which may cause AMP to diverge. Damped AMP has been used for SBL to alleviate the problem at the cost of reducing convergence speed. In this work, we propose a new SBL algorithm based on structured variational inference, leveraging AMP with a unitary transformation (UAMP). Both single measurement vector and multiple measurement vector problems are investigated. It is shown that, compared to state-of-the-art AMP-based SBL algorithms, the proposed UAMP-SBL is more robust and efficient, leading to remarkably better performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2101.09954v2-abstract-full').style.display = 'none'; document.getElementById('2101.09954v2-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 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 25 January, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2012.09293">arXiv:2012.09293</a> <span> [<a href="https://arxiv.org/pdf/2012.09293">pdf</a>, <a href="https://arxiv.org/format/2012.09293">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"> Imitation Learning with Stability and Safety Guarantees </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yin%2C+H">He Yin</a>, <a href="/search/eess?searchtype=author&query=Seiler%2C+P">Peter Seiler</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Arcak%2C+M">Murat Arcak</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="2012.09293v2-abstract-short" style="display: inline;"> A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL). Convex stability and safety conditions are derived for linear time-invariant plant dynamics with NN controllers by merging Lyapunov theory with local quadratic constraints to bound the nonlinear activation functions in the NN. These conditions are incorporated in the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.09293v2-abstract-full').style.display = 'inline'; document.getElementById('2012.09293v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2012.09293v2-abstract-full" style="display: none;"> A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL). Convex stability and safety conditions are derived for linear time-invariant plant dynamics with NN controllers by merging Lyapunov theory with local quadratic constraints to bound the nonlinear activation functions in the NN. These conditions are incorporated in the IL process, which minimizes the IL loss, and maximizes the volume of the region of attraction associated with the NN controller simultaneously. An alternating direction method of multipliers based algorithm is proposed to solve the IL problem. The method is illustrated on an inverted pendulum system, aircraft longitudinal dynamics, and vehicle lateral dynamics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2012.09293v2-abstract-full').style.display = 'none'; document.getElementById('2012.09293v2-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 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2020. </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, 9 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/2006.15954">arXiv:2006.15954</a> <span> [<a href="https://arxiv.org/pdf/2006.15954">pdf</a>, <a href="https://arxiv.org/format/2006.15954">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"> Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhu%2C+C">Chuang Zhu</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+K">Ke Mei</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+T">Ting Peng</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+Y">Yihao Luo</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jun Liu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Ying Wang</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+M">Mulan Jin</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="2006.15954v2-abstract-short" style="display: inline;"> The automatic and objective medical diagnostic model can be valuable to achieve early cancer detection, and thus reducing the mortality rate. In this paper, we propose a highly efficient multi-level malignant tissue detection through the designed adversarial CAC-UNet. A patch-level model with a pre-prediction strategy and a malignancy area guided label smoothing is adopted to remove the negative W… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.15954v2-abstract-full').style.display = 'inline'; document.getElementById('2006.15954v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.15954v2-abstract-full" style="display: none;"> The automatic and objective medical diagnostic model can be valuable to achieve early cancer detection, and thus reducing the mortality rate. In this paper, we propose a highly efficient multi-level malignant tissue detection through the designed adversarial CAC-UNet. A patch-level model with a pre-prediction strategy and a malignancy area guided label smoothing is adopted to remove the negative WSIs, with which to lower the risk of false positive detection. For the selected key patches by multi-model ensemble, an adversarial context-aware and appearance consistency UNet (CAC-UNet) is designed to achieve robust segmentation. In CAC-UNet, mirror designed discriminators are able to seamlessly fuse the whole feature maps of the skillfully designed powerful backbone network without any information loss. Besides, a mask prior is further added to guide the accurate segmentation mask prediction through an extra mask-domain discriminator. The proposed scheme achieves the best results in MICCAI DigestPath2019 challenge on colonoscopy tissue segmentation and classification task. The full implementation details and the trained models are available at https://github.com/Raykoooo/CAC-UNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.15954v2-abstract-full').style.display = 'none'; document.getElementById('2006.15954v2-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 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 June, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2020. </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 Neurocomputing; winner of the MICCAI DigestPath 2019 challenge on colonoscopy tissue segmentation and classification task</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1908.10315">arXiv:1908.10315</a> <span> [<a href="https://arxiv.org/pdf/1908.10315">pdf</a>, <a href="https://arxiv.org/format/1908.10315">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="Applications">stat.AP</span> </div> </div> <p class="title is-5 mathjax"> Boundary Defense against Cyber Threat for Power System Operation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Lavaei%2C+J">Javad Lavaei</a>, <a href="/search/eess?searchtype=author&query=Sojoudi%2C+S">Somayeh Sojoudi</a>, <a href="/search/eess?searchtype=author&query=Baldick%2C+R">Ross Baldick</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="1908.10315v1-abstract-short" style="display: inline;"> The operation of power grids is becoming increasingly data-centric. While the abundance of data could improve the efficiency of the system, it poses major reliability challenges. In particular, state estimation aims to learn the behavior of the network from data but an undetected attack on this problem could lead to a large-scale blackout. Nevertheless, understanding vulnerability of state estimat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.10315v1-abstract-full').style.display = 'inline'; document.getElementById('1908.10315v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1908.10315v1-abstract-full" style="display: none;"> The operation of power grids is becoming increasingly data-centric. While the abundance of data could improve the efficiency of the system, it poses major reliability challenges. In particular, state estimation aims to learn the behavior of the network from data but an undetected attack on this problem could lead to a large-scale blackout. Nevertheless, understanding vulnerability of state estimation against cyber attacks has been hindered by the lack of tools studying the topological and data-analytic aspects of the network. Algorithmic robustness is of critical need to extract reliable information from abundant but untrusted grid data. We propose a robust state estimation framework that leverages network sparsity and data abundance. For a large-scale power grid, we quantify, analyze, and visualize the regions of the network prone to cyber attacks. We also propose an optimization-based graphical boundary defense mechanism to identify the border of the geographical area whose data has been manipulated. The proposed method does not allow a local attack to have a global effect on the data analysis of the entire network, which enhances the situational awareness of the grid especially in the face of adversity. The developed mathematical framework reveals key geometric and algebraic factors that can affect algorithmic robustness and is used to study the vulnerability of the U.S. power grid in this paper. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.10315v1-abstract-full').style.display = 'none'; document.getElementById('1908.10315v1-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> 4 August, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2019. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1810.11505">arXiv:1810.11505</a> <span> [<a href="https://arxiv.org/pdf/1810.11505">pdf</a>, <a href="https://arxiv.org/format/1810.11505">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Stability-certified reinforcement learning: A control-theoretic perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jin%2C+M">Ming Jin</a>, <a href="/search/eess?searchtype=author&query=Lavaei%2C+J">Javad Lavaei</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="1810.11505v1-abstract-short" style="display: inline;"> We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing contro… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.11505v1-abstract-full').style.display = 'inline'; document.getElementById('1810.11505v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1810.11505v1-abstract-full" style="display: none;"> We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation and power system frequency regulation, demonstrate that the reinforcement learning agents can have high performance within the stability-certified parameter space, and also exhibit stable learning behaviors in the long run. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1810.11505v1-abstract-full').style.display = 'none'; document.getElementById('1810.11505v1-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, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2018. </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=Jin%2C+M&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Jin%2C+M&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Jin%2C+M&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </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