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 207 results for author: <span class="mathjax">Sun, S</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=Sun%2C+S">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="Sun, S"> </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=Sun%2C+S&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="Sun, S"> <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=Sun%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.05768">arXiv:2502.05768</a> <span> [<a href="https://arxiv.org/pdf/2502.05768">pdf</a>, <a href="https://arxiv.org/format/2502.05768">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"> Cooperative Optimization of Grid-Edge Cyber and Physical Resources for Resilient Power System Operation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Huo%2C+X">Xiang Huo</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shining Sun</a>, <a href="/search/eess?searchtype=author&query=Haque%2C+K+A">Khandaker Akramul Haque</a>, <a href="/search/eess?searchtype=author&query=Homoud%2C+L+A">Leen Al Homoud</a>, <a href="/search/eess?searchtype=author&query=Goulart%2C+A+E">Ana E. Goulart</a>, <a href="/search/eess?searchtype=author&query=Davis%2C+K+R">Katherine R. Davis</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.05768v1-abstract-short" style="display: inline;"> The cooperative operation of grid-edge power and energy resources is crucial to improving the resilience of power systems during contingencies. However, given the complex cyber-physical nature of power grids, it is hard to respond timely with limited costs for deploying additional cyber and/or phyiscal resources, such as during a high-impact low-frequency cyber-physical event. Therefore, the paper… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05768v1-abstract-full').style.display = 'inline'; document.getElementById('2502.05768v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.05768v1-abstract-full" style="display: none;"> The cooperative operation of grid-edge power and energy resources is crucial to improving the resilience of power systems during contingencies. However, given the complex cyber-physical nature of power grids, it is hard to respond timely with limited costs for deploying additional cyber and/or phyiscal resources, such as during a high-impact low-frequency cyber-physical event. Therefore, the paper examines the design of cooperative cyber-physical resource optimization solutions to control grid-tied cyber and physical resources. First, the operation of a cyber-physical power system is formulated into a constrained optimization problem, including the cyber and physical objectives and constraints. Then, a bi-level solution is provided to obtain optimal cyber and physical actions, including the reconfiguration of cyber topology (e.g., activation of communication links) in the cyber layer and the control of physical resources (e.g., energy storage systems) in the physical layer. The developed method improves grid resilience during cyberattacks and can provide guidance on the control of coupled physical side resources. Numerical simulation on a modified IEEE 14-bus system demonstrates the effectiveness of the proposed approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05768v1-abstract-full').style.display = 'none'; document.getElementById('2502.05768v1-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.00699">arXiv:2502.00699</a> <span> [<a href="https://arxiv.org/pdf/2502.00699">pdf</a>, <a href="https://arxiv.org/format/2502.00699">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="Emerging Technologies">cs.ET</span> </div> </div> <p class="title is-5 mathjax"> Measurement and Analysis of Scattering From Building Surfaces at Millimeter-Wave Frequency </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+Y">Yulu Guo</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+T">Tongjia Zhang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+R">Ruifeng Gao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.00699v1-abstract-short" style="display: inline;"> In future air-to-ground integrated networks, the scattering effects from ground-based scatterers, such as buildings, cannot be neglected in millimeter-wave and higher frequency bands, and have a significant impact on channel characteristics. However, current scattering measurement studies primarily focus on single incident angles within the incident plane, leading to insufficient characterization… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00699v1-abstract-full').style.display = 'inline'; document.getElementById('2502.00699v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.00699v1-abstract-full" style="display: none;"> In future air-to-ground integrated networks, the scattering effects from ground-based scatterers, such as buildings, cannot be neglected in millimeter-wave and higher frequency bands, and have a significant impact on channel characteristics. However, current scattering measurement studies primarily focus on single incident angles within the incident plane, leading to insufficient characterization of scattering properties. In this paper, we present scattering measurements conducted at 28 GHz on various real-world building surfaces with multiple incident angles and three-dimensional (3D) receiving angles. The measured data are analyzed in conjunction with parameterized scattering models in ray tracing and numerical simulations. Results indicate that for millimeter-wave channel modeling near building surfaces, it is crucial to account not only for surface materials but also for the scattering properties of the building surfaces with respect to the incident angle and receiving positions in 3D space. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.00699v1-abstract-full').style.display = 'none'; document.getElementById('2502.00699v1-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> 2 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 7 figures. 2025 IEEE Wireless Communications and Networking Conference Workshops (WCNC Wkshps), Milan, Italy, 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.18853">arXiv:2501.18853</a> <span> [<a href="https://arxiv.org/pdf/2501.18853">pdf</a>, <a href="https://arxiv.org/format/2501.18853">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"> Non-Asymptotic Analysis of Subspace Identification for Stochastic Systems Using Multiple Trajectories </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuai Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.18853v3-abstract-short" style="display: inline;"> This paper is concerned with the analysis of identification errors for $n$-dimensional discrete-time Linear Time-Invariant (LTI) systems with $m$ outputs and no external inputs, using Subspace Identification Methods (SIM) with finite sample data. We provide non-asymptotic high-probability upper bounds for matrices $A,C$, the Kalman filter gain $K$, and the closed loop matrix $A-KC $, based on mult… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18853v3-abstract-full').style.display = 'inline'; document.getElementById('2501.18853v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18853v3-abstract-full" style="display: none;"> This paper is concerned with the analysis of identification errors for $n$-dimensional discrete-time Linear Time-Invariant (LTI) systems with $m$ outputs and no external inputs, using Subspace Identification Methods (SIM) with finite sample data. We provide non-asymptotic high-probability upper bounds for matrices $A,C$, the Kalman filter gain $K$, and the closed loop matrix $A-KC $, based on multiple sample trajectories, and further give the first non-asymptotic high-probability upper bounds for the system poles, which cover both (marginally) stable systems and unstable systems. We show that, with high probability, the non-asymptotic estimation errors of these matrices decay at a rate of at least $ \mathcal{O}(\sqrt{1/N}) $, while the estimation error of the system poles decays at a rate of at least $ \mathcal{O}(N^{-\frac{1}{2n}}) $, where $ N $ represents the number of sample trajectories. Furthermore, we prove that SIMs become ill-conditioned when the ratio $n/m$ is large, regardless of the system parameters. Numerical experiments are conducted to validate the non-asymptotic results and the ill-conditionedness of SIM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18853v3-abstract-full').style.display = 'none'; document.getElementById('2501.18853v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">23 pages, 7 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/2501.18802">arXiv:2501.18802</a> <span> [<a href="https://arxiv.org/pdf/2501.18802">pdf</a>, <a href="https://arxiv.org/format/2501.18802">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Agile and Cooperative Aerial Manipulation of a Cable-Suspended Load </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sihao Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+X">Xuerui Wang</a>, <a href="/search/eess?searchtype=author&query=Sanalitro%2C+D">Dario Sanalitro</a>, <a href="/search/eess?searchtype=author&query=Franchi%2C+A">Antonio Franchi</a>, <a href="/search/eess?searchtype=author&query=Tognon%2C+M">Marco Tognon</a>, <a href="/search/eess?searchtype=author&query=Alonso-Mora%2C+J">Javier Alonso-Mora</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.18802v1-abstract-short" style="display: inline;"> Quadrotors can carry slung loads to hard-to-reach locations at high speed. Since a single quadrotor has limited payload capacities, using a team of quadrotors to collaboratively manipulate a heavy object is a scalable and promising solution. However, existing control algorithms for multi-lifting systems only enable low-speed and low-acceleration operations due to the complex dynamic coupling betwe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18802v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18802v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18802v1-abstract-full" style="display: none;"> Quadrotors can carry slung loads to hard-to-reach locations at high speed. Since a single quadrotor has limited payload capacities, using a team of quadrotors to collaboratively manipulate a heavy object is a scalable and promising solution. However, existing control algorithms for multi-lifting systems only enable low-speed and low-acceleration operations due to the complex dynamic coupling between quadrotors and the load, limiting their use in time-critical missions such as search and rescue. In this work, we present a solution to significantly enhance the agility of cable-suspended multi-lifting systems. Unlike traditional cascaded solutions, we introduce a trajectory-based framework that solves the whole-body kinodynamic motion planning problem online, accounting for the dynamic coupling effects and constraints between the quadrotors and the load. The planned trajectory is provided to the quadrotors as a reference in a receding-horizon fashion and is tracked by an onboard controller that observes and compensates for the cable tension. Real-world experiments demonstrate that our framework can achieve at least eight times greater acceleration than state-of-the-art methods to follow agile trajectories. Our method can even perform complex maneuvers such as flying through narrow passages at high speed. Additionally, it exhibits high robustness against load uncertainties and does not require adding any sensors to the load, demonstrating strong practicality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18802v1-abstract-full').style.display = 'none'; document.getElementById('2501.18802v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">38 pages, 11 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/2501.15207">arXiv:2501.15207</a> <span> [<a href="https://arxiv.org/pdf/2501.15207">pdf</a>, <a href="https://arxiv.org/format/2501.15207">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"> Hybrid Near/Far-Field Frequency-Dependent Beamforming via Joint Phase-Time Arrays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cai%2C+Y">Yeyue Cai</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a>, <a href="/search/eess?searchtype=author&query=Mo%2C+J">Jianhua Mo</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.15207v1-abstract-short" style="display: inline;"> Joint phase-time arrays (JPTA) emerge as a cost-effective and energy-efficient architecture for frequency-dependent beamforming in wideband communications by utilizing both true-time delay units and phase shifters. This paper exploits the potential of JPTA to simultaneously serve multiple users in both near- and far-field regions with a single radio frequency chain. The goal is to jointly optimize… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15207v1-abstract-full').style.display = 'inline'; document.getElementById('2501.15207v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.15207v1-abstract-full" style="display: none;"> Joint phase-time arrays (JPTA) emerge as a cost-effective and energy-efficient architecture for frequency-dependent beamforming in wideband communications by utilizing both true-time delay units and phase shifters. This paper exploits the potential of JPTA to simultaneously serve multiple users in both near- and far-field regions with a single radio frequency chain. The goal is to jointly optimize JPTA-based beamforming and subband allocation to maximize overall system performance. To this end, we formulate a system utility maximization problem, including sum-rate maximization and proportional fairness as special cases. We develop a 3-step alternating optimization (AO) algorithm and an efficient deep learning (DL) method for this problem. The DL approach includes a 2-layer convolutional neural network, a 3-layer graph attention network (GAT), and a normalization module for resource and beamforming optimization. The GAT efficiently captures the interactions between resource allocation and analog beamformers. Simulation results confirm that JPTA outperforms conventional phased arrays (PA) in enhancing user rate and strikes a good balance between PA and fully-digital approach in energy efficiency. Employing a logarithmic utility function for user rates ensures greater fairness than maximizing sum-rates. Furthermore, the DL network achieves comparable performance to the AO approach, while having orders of magnitude lower computational complexity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.15207v1-abstract-full').style.display = 'none'; document.getElementById('2501.15207v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.13497">arXiv:2501.13497</a> <span> [<a href="https://arxiv.org/pdf/2501.13497">pdf</a>, <a href="https://arxiv.org/format/2501.13497">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"> DQ-Data2vec: Decoupling Quantization for Multilingual Speech Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Shao%2C+Q">Qijie Shao</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+L">Linhao Dong</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+K">Kun Wei</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sining Sun</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.13497v1-abstract-short" style="display: inline;"> Data2vec is a self-supervised learning (SSL) approach that employs a teacher-student architecture for contextual representation learning via masked prediction, demonstrating remarkable performance in monolingual ASR. Previous studies have revealed that data2vec's shallow layers capture speaker and language information, middle layers encode phoneme and word features, while deep layers are responsib… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13497v1-abstract-full').style.display = 'inline'; document.getElementById('2501.13497v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.13497v1-abstract-full" style="display: none;"> Data2vec is a self-supervised learning (SSL) approach that employs a teacher-student architecture for contextual representation learning via masked prediction, demonstrating remarkable performance in monolingual ASR. Previous studies have revealed that data2vec's shallow layers capture speaker and language information, middle layers encode phoneme and word features, while deep layers are responsible for reconstruction. Language and phoneme features are crucial for multilingual ASR. However, data2vec's masked representation generation relies on multi-layer averaging, inevitably coupling these features. To address this limitation, we propose a decoupling quantization based data2vec (DQ-Data2vec) for multilingual ASR, which includes a data2vec backbone and two improved online K-means quantizers. Our core idea is using the K-means quantizer with specified cluster numbers to decouple language and phoneme information for masked prediction. Specifically, in the language quantization, considering that the number of languages is significantly different from other irrelevant features (e.g., speakers), we assign the cluster number to match the number of languages, explicitly decoupling shallow layers' language-related information from irrelevant features. This strategy is also applied to decoupling middle layers' phoneme and word features. In a self-supervised scenario, experiments on the CommonVoice dataset demonstrate that DQ-Data2vec achieves a relative reduction of 9.51% in phoneme error rate (PER) and 11.58% in word error rate (WER) compared to data2vec and UniData2vec. Moreover, in a weakly-supervised scenario incorporating language labels and high-resource language text labels, the relative reduction is 18.09% and 1.55%, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.13497v1-abstract-full').style.display = 'none'; document.getElementById('2501.13497v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to the IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.07649">arXiv:2501.07649</a> <span> [<a href="https://arxiv.org/pdf/2501.07649">pdf</a>, <a href="https://arxiv.org/format/2501.07649">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"> Signal Processing Challenges in Automotive Radar </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Rao%2C+S">Sandeep Rao</a>, <a href="/search/eess?searchtype=author&query=Narasimha%2C+R">Rajan Narasimha</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.07649v1-abstract-short" style="display: inline;"> As automotive radars continue to proliferate, there is a continuous need for improved performance and several critical problems that need to be solved. All of this is driving research across industry and academia. This paper is an overview of research areas that are centered around signal processing. We discuss opportunities in the area of modulation schemes, interference avoidance, spatial resolu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07649v1-abstract-full').style.display = 'inline'; document.getElementById('2501.07649v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07649v1-abstract-full" style="display: none;"> As automotive radars continue to proliferate, there is a continuous need for improved performance and several critical problems that need to be solved. All of this is driving research across industry and academia. This paper is an overview of research areas that are centered around signal processing. We discuss opportunities in the area of modulation schemes, interference avoidance, spatial resolution enhancement and application of deep learning. A rich list of references is provided. This paper should serve as a useful starting point for signal processing practitioners looking to work in the area of automotive radars. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07649v1-abstract-full').style.display = 'none'; document.getElementById('2501.07649v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Paper accepted by ICASSP 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.07008">arXiv:2501.07008</a> <span> [<a href="https://arxiv.org/pdf/2501.07008">pdf</a>, <a href="https://arxiv.org/format/2501.07008">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">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Advancing Single-Snapshot DOA Estimation with Siamese Neural Networks for Sparse Linear Arrays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zheng%2C+R">Ruxin Zheng</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Hongshan Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y+D">Yimin D. Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.07008v1-abstract-short" style="display: inline;"> Single-snapshot signal processing in sparse linear arrays has become increasingly vital, particularly in dynamic environments like automotive radar systems, where only limited snapshots are available. These arrays are often utilized either to cut manufacturing costs or result from unintended antenna failures, leading to challenges such as high sidelobe levels and compromised accuracy in direction-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07008v1-abstract-full').style.display = 'inline'; document.getElementById('2501.07008v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.07008v1-abstract-full" style="display: none;"> Single-snapshot signal processing in sparse linear arrays has become increasingly vital, particularly in dynamic environments like automotive radar systems, where only limited snapshots are available. These arrays are often utilized either to cut manufacturing costs or result from unintended antenna failures, leading to challenges such as high sidelobe levels and compromised accuracy in direction-of-arrival (DOA) estimation. Despite deep learning's success in tasks such as DOA estimation, the need for extensive training data to increase target numbers or improve angular resolution poses significant challenges. In response, this paper presents a novel Siamese neural network (SNN) featuring a sparse augmentation layer, which enhances signal feature embedding and DOA estimation accuracy in sparse arrays. We demonstrate the enhanced DOA estimation performance of our approach through detailed feature analysis and performance evaluation. The code for this study is available at https://github.com/ruxinzh/SNNS_SLA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.07008v1-abstract-full').style.display = 'none'; document.getElementById('2501.07008v1-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> 12 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Paper accepted by ICASSP 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.01684">arXiv:2501.01684</a> <span> [<a href="https://arxiv.org/pdf/2501.01684">pdf</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"> Millimeter-Wave Energy-Efficient Hybrid Beamforming Architecture and Algorithm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Hongpu Zhang</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Y">Yulu Guo</a>, <a href="/search/eess?searchtype=author&query=Xue%2C+L">Liuxun Xue</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+X">Xingchen Liu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+R">Ruifeng Gao</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xianghao Yu</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.01684v1-abstract-short" style="display: inline;"> This paper studies energy-efficient hybrid beamforming architectures and its algorithm design in millimeter-wave communication systems, aiming to address the challenges faced by existing hybrid beamforming due to low hardware flexibility and high power consumption. To solve the problems of existing hybrid beamforming, a novel energy-efficient hybrid beamforming architecture is proposed, where radi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01684v1-abstract-full').style.display = 'inline'; document.getElementById('2501.01684v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.01684v1-abstract-full" style="display: none;"> This paper studies energy-efficient hybrid beamforming architectures and its algorithm design in millimeter-wave communication systems, aiming to address the challenges faced by existing hybrid beamforming due to low hardware flexibility and high power consumption. To solve the problems of existing hybrid beamforming, a novel energy-efficient hybrid beamforming architecture is proposed, where radio-frequency (RF) switch networks are introduced at the front and rear ends of the phase shifter network, enabling dynamic connections between the RF chains and the phase shifter array as well as the antenna array. The system model of the proposed architecture is established, including digital precoding and analog precoding processes, and the practical hardware limitations such as quantization errors of the digital-to-analog converter (DAC) and phase shifter resolution. In order to maximize the energy efficiency, this paper derives an energy efficiency model including spectral efficiency and system power consumption, and a hybrid precoding algorithm is proposed based on block coordinate descent to iteratively optimize the digital precoding matrix, analog precoding matrix, and DAC resolution. Simulation results under the NYUSIM-generated millimeter-wave channels show that the proposed hybrid beamforming architecture and precoding algorithm have higher energy efficiency than existing representative architectures and precoding algorithms under complete and partial channel state information, while the loss of spectral efficiency compared to fully connected architecture is less than 20% <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01684v1-abstract-full').style.display = 'none'; document.getElementById('2501.01684v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">21 pages, in Chinese language, 8 figures, published to Mobile Communications</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Mobile Communications, vol. 48, no. 12, pp. 86-96, 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/2501.01034">arXiv:2501.01034</a> <span> [<a href="https://arxiv.org/pdf/2501.01034">pdf</a>, <a href="https://arxiv.org/format/2501.01034">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="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"> Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+B">Bin Wang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+X">Xunlong Zou</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuo Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wenyu Zhang</a>, <a href="/search/eess?searchtype=author&query=He%2C+Y">Yingxu He</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zhuohan Liu</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+C">Chengwei Wei</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+N+F">Nancy F. Chen</a>, <a href="/search/eess?searchtype=author&query=Aw%2C+A">AiTi Aw</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.01034v2-abstract-short" style="display: inline;"> Singlish, a Creole language rooted in English, is a key focus in linguistic research within multilingual and multicultural contexts. However, its spoken form remains underexplored, limiting insights into its linguistic structure and applications. To address this gap, we standardize and annotate the largest spoken Singlish corpus, introducing the Multitask National Speech Corpus (MNSC). These datas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01034v2-abstract-full').style.display = 'inline'; document.getElementById('2501.01034v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.01034v2-abstract-full" style="display: none;"> Singlish, a Creole language rooted in English, is a key focus in linguistic research within multilingual and multicultural contexts. However, its spoken form remains underexplored, limiting insights into its linguistic structure and applications. To address this gap, we standardize and annotate the largest spoken Singlish corpus, introducing the Multitask National Speech Corpus (MNSC). These datasets support diverse tasks, including Automatic Speech Recognition (ASR), Spoken Question Answering (SQA), Spoken Dialogue Summarization (SDS), and Paralinguistic Question Answering (PQA). We release standardized splits and a human-verified test set to facilitate further research. Additionally, we propose SingAudioLLM, a multi-task multimodal model leveraging multimodal large language models to handle these tasks concurrently. Experiments reveal our models adaptability to Singlish context, achieving state-of-the-art performance and outperforming prior models by 10-30% in comparison with other AudioLLMs and cascaded solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.01034v2-abstract-full').style.display = 'none'; document.getElementById('2501.01034v2-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Open-Source: https://github.com/AudioLLMs/Singlish</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.18983">arXiv:2412.18983</a> <span> [<a href="https://arxiv.org/pdf/2412.18983">pdf</a>, <a href="https://arxiv.org/ps/2412.18983">ps</a>, <a href="https://arxiv.org/format/2412.18983">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"> Deep Learning-Based Traffic-Aware Base Station Sleep Mode and Cell Zooming Strategy in RIS-Aided Multi-Cell Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuo Sun</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+C">Chong Huang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+G">Gaojie Chen</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+P">Pei Xiao</a>, <a href="/search/eess?searchtype=author&query=Tafazolli%2C+R">Rahim Tafazolli</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="2412.18983v1-abstract-short" style="display: inline;"> Advances in wireless technology have significantly increased the number of wireless connections, leading to higher energy consumption in networks. Among these, base stations (BSs) in radio access networks (RANs) account for over half of the total energy usage. To address this, we propose a multi-cell sleep strategy combined with adaptive cell zooming, user association, and reconfigurable intellige… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18983v1-abstract-full').style.display = 'inline'; document.getElementById('2412.18983v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.18983v1-abstract-full" style="display: none;"> Advances in wireless technology have significantly increased the number of wireless connections, leading to higher energy consumption in networks. Among these, base stations (BSs) in radio access networks (RANs) account for over half of the total energy usage. To address this, we propose a multi-cell sleep strategy combined with adaptive cell zooming, user association, and reconfigurable intelligent surface (RIS) to minimize BS energy consumption. This approach allows BSs to enter sleep during low traffic, while adaptive cell zooming and user association dynamically adjust coverage to balance traffic load and enhance data rates through RIS, minimizing the number of active BSs. However, it is important to note that the proposed method may achieve energy-savings at the cost of increased delay, requiring a trade-off between these two factors. Moreover, minimizing BS energy consumption under the delay constraint is a complicated non-convex problem. To address this issue, we model the RIS-aided multi-cell network as a Markov decision process (MDP) and use the proximal policy optimization (PPO) algorithm to optimize sleep mode (SM), cell zooming, and user association. Besides, we utilize a double cascade correlation network (DCCN) algorithm to optimize the RIS reflection coefficients. Simulation results demonstrate that PPO balances energy-savings and delay, while DCCN-optimized RIS enhances BS energy-savings. Compared to systems optimised by the benchmark DQN algorithm, energy consumption is reduced by 49.61% <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.18983v1-abstract-full').style.display = 'none'; document.getElementById('2412.18983v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 Pages, accepted for publication in IEEE Transactions on Cognitive Communications and Networking</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.16761">arXiv:2412.16761</a> <span> [<a href="https://arxiv.org/pdf/2412.16761">pdf</a>, <a href="https://arxiv.org/format/2412.16761">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"> Non-Asymptotic Error Analysis of Subspace Identification for Deterministic Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuai Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.16761v1-abstract-short" style="display: inline;"> This paper is concerned with the perturbation error analysis of the widely-used Subspace Identification Methods (SIM) for n-dimensional discrete-time Multiple-Input Multiple-Output (MIMO) Linear Time-Invariant (LTI) systems with m outputs, based on finite input/output sample data. Using a single input/output trajectory, we provide non-asymptotic upper bounds on the perturbation errors for the syst… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16761v1-abstract-full').style.display = 'inline'; document.getElementById('2412.16761v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.16761v1-abstract-full" style="display: none;"> This paper is concerned with the perturbation error analysis of the widely-used Subspace Identification Methods (SIM) for n-dimensional discrete-time Multiple-Input Multiple-Output (MIMO) Linear Time-Invariant (LTI) systems with m outputs, based on finite input/output sample data. Using a single input/output trajectory, we provide non-asymptotic upper bounds on the perturbation errors for the system matrices in state-space models as well as the system poles for two unified algorithms, offering a unified perspective across various SIM variants. Furthermore, we prove that SIMs become ill-conditioned for MIMO systems when the ratio n/m is large, regardless of system parameters. Numerical experiments are conducted to validate the ill-conditionedness of SIMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.16761v1-abstract-full').style.display = 'none'; document.getElementById('2412.16761v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 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/2412.10976">arXiv:2412.10976</a> <span> [<a href="https://arxiv.org/pdf/2412.10976">pdf</a>, <a href="https://arxiv.org/format/2412.10976">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">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Off-Grid One-Bit DOA Estimation with Learning-Based Sparse Bayesian Approach for Non-Uniform Sparse Array </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hu%2C+Y">Yunqiao Hu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y+D">Yimin D. Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.10976v1-abstract-short" style="display: inline;"> This paper tackles the challenge of one-bit off-grid direction of arrival (DOA) estimation in a single snapshot scenario based on a learning-based Bayesian approach. Firstly, we formulate the off-grid DOA estimation model, utilizing the first-order off-grid approximation, incorporating one-bit data quantization. Subsequently, we address this problem using the Sparse Bayesian based framework and so… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10976v1-abstract-full').style.display = 'inline'; document.getElementById('2412.10976v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.10976v1-abstract-full" style="display: none;"> This paper tackles the challenge of one-bit off-grid direction of arrival (DOA) estimation in a single snapshot scenario based on a learning-based Bayesian approach. Firstly, we formulate the off-grid DOA estimation model, utilizing the first-order off-grid approximation, incorporating one-bit data quantization. Subsequently, we address this problem using the Sparse Bayesian based framework and solve iteratively. However, traditional Sparse Bayesian methods often face challenges such as high computational complexity and the need for extensive hyperparameter tuning. To balance estimation accuracy and computational efficiency, we propose a novel Learning-based Sparse Bayesian framework, which leverages an unrolled neural network architecture. This framework autonomously learns hyperparameters through supervised learning, offering more accurate off-grid DOA estimates and improved computational efficiency compared to some state-of-the-art methods. Furthermore, the proposed approach is applicable to both uniform linear arrays and non-uniform sparse arrays. Simulation results validate the effectiveness of the proposed framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10976v1-abstract-full').style.display = 'none'; document.getElementById('2412.10976v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Proc. 58th Annual Asilomar Conference on Signals, Systems, and Computers (Asilomar), Pacific Grove, CA, Oct. 27 - Oct. 30, 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.06353">arXiv:2412.06353</a> <span> [<a href="https://arxiv.org/pdf/2412.06353">pdf</a>, <a href="https://arxiv.org/format/2412.06353">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"> 3D Extended Target Sensing in ISAC: Cram茅r-Rao Bound Analysis and Beamforming Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yiqiu Wang</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+W">Wei Cao</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="2412.06353v2-abstract-short" style="display: inline;"> This paper investigates an integrated sensing and communication (ISAC) system where the sensing target is a three-dimensional (3D) extended target, for which multiple scatterers from the target surface can be resolved. We first introduce a second-order truncated Fourier series surface model for an arbitrarily-shaped 3D ET. Utilizing this model, we derive tractable Cramer-Rao bounds (CRBs) for esti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06353v2-abstract-full').style.display = 'inline'; document.getElementById('2412.06353v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.06353v2-abstract-full" style="display: none;"> This paper investigates an integrated sensing and communication (ISAC) system where the sensing target is a three-dimensional (3D) extended target, for which multiple scatterers from the target surface can be resolved. We first introduce a second-order truncated Fourier series surface model for an arbitrarily-shaped 3D ET. Utilizing this model, we derive tractable Cramer-Rao bounds (CRBs) for estimating the ET kinematic parameters, including the center range, azimuth, elevation, and orientation. These CRBs depend explicitly on the transmit covariance matrix and ET shape. Then we formulate two transmit beamforming optimization problems for the base station (BS) to simultaneously support communication with multiple users and sensing of the 3D ET. The first minimizes the sensing CRB while ensuring a minimum signal-to-interference-plus-noise ratio (SINR) for each user, and it is solved using semidefinite relaxation. The second balances minimizing the CRB and maximizing communication rates through a weight factor, and is solved via successive convex approximation. To reduce the computational complexity, we further propose ISACBeam-GNN, a novel graph neural network-based beamforming method that employs a separate-then-integrate structure, learning communication and sensing (C&S) objectives independently before integrating them to balance C&S trade-offs. Simulation results show that the proposed beamforming designs that account for ET shapes significantly outperform existing baselines, offering better communication-sensing performance trade-offs as well as an improved beampattern for sensing. Results also demonstrate that ISACBeam-GNN is an efficient alternative to the optimization-based methods, with remarkable adaptability and scalability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.06353v2-abstract-full').style.display = 'none'; document.getElementById('2412.06353v2-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <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">13 pages, 9 figures, partially published in IEEE Global Communications Conference 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/2411.11866">arXiv:2411.11866</a> <span> [<a href="https://arxiv.org/pdf/2411.11866">pdf</a>, <a href="https://arxiv.org/format/2411.11866">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 Realization of Multi-channel Visible Light Communication System for Dynamic Cross-Water Surface Channels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Qi%2C+H">Han Qi</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+T">Tianrui Lin</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+T">Tianjian Wei</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Q">Qingqing Hu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Siyan Sun</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+N">Nuo Huang</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+C">Chen Gong</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="2411.11866v1-abstract-short" style="display: inline;"> This paper explores the transmission schemes for multi-channel water-to-air optical wireless communication (W2A-OWC) and introduces a prototype of a real-time W2A-OWC system based on a field-programmable gate array (FPGA). Utilizing an LED array as the transmitter and an APD array as the receiver, the system establishes a multi-channel transmission module. Such configuration enables parallel opera… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11866v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11866v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11866v1-abstract-full" style="display: none;"> This paper explores the transmission schemes for multi-channel water-to-air optical wireless communication (W2A-OWC) and introduces a prototype of a real-time W2A-OWC system based on a field-programmable gate array (FPGA). Utilizing an LED array as the transmitter and an APD array as the receiver, the system establishes a multi-channel transmission module. Such configuration enables parallel operation of multiple channels, facilitating the simultaneous transmission of multiple data streams and enhancing overall throughput. The FPGA serves as a real-time signal processing unit, handling both signal transmission and reception. By integrating low-density parity-check (LDPC) codes from 5G New Radio, the system significantly boosts its detection capabilities for dynamic W2A-OWC scenarios. The system also optimizes FPGA resource usage through time-multiplexing operation of an LDPC decoder's IP core. To evaluate the system's practicality, experiments were conducted under background radiation in an indoor water tank, measuring the frame error rate under both calm and fluctuating water surfaces. The experimental results confirm the feasibility and effectiveness of the developed W2A-OWC system. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11866v1-abstract-full').style.display = 'none'; document.getElementById('2411.11866v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 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/2411.11699">arXiv:2411.11699</a> <span> [<a href="https://arxiv.org/pdf/2411.11699">pdf</a>, <a href="https://arxiv.org/format/2411.11699">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"> LiTformer: Efficient Modeling and Analysis of High-Speed Link Transmitters Using Non-Autoregressive Transformer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Songyu Sun</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+X">Xiao Dong</a>, <a href="/search/eess?searchtype=author&query=Sha%2C+Y">Yanliang Sha</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Q">Quan Chen</a>, <a href="/search/eess?searchtype=author&query=Zhuo%2C+C">Cheng Zhuo</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="2411.11699v1-abstract-short" style="display: inline;"> High-speed serial links are fundamental to energy-efficient and high-performance computing systems such as artificial intelligence, 5G mobile and automotive, enabling low-latency and high-bandwidth communication. Transmitters (TXs) within these links are key to signal quality, while their modeling presents challenges due to nonlinear behavior and dynamic interactions with links. In this paper, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11699v1-abstract-full').style.display = 'inline'; document.getElementById('2411.11699v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.11699v1-abstract-full" style="display: none;"> High-speed serial links are fundamental to energy-efficient and high-performance computing systems such as artificial intelligence, 5G mobile and automotive, enabling low-latency and high-bandwidth communication. Transmitters (TXs) within these links are key to signal quality, while their modeling presents challenges due to nonlinear behavior and dynamic interactions with links. In this paper, we propose LiTformer: a Transformer-based model for high-speed link TXs, with a non-sequential encoder and a Transformer decoder to incorporate link parameters and capture long-range dependencies of output signals. We employ a non-autoregressive mechanism in model training and inference for parallel prediction of the signal sequence. LiTformer achieves precise TX modeling considering link impacts including crosstalk from multiple links, and provides fast prediction for various long-sequence signals with high data rates. Experimental results show that LiTformer achieves 148-456$\times$ speedup for 2-link TXs and 404-944$\times$ speedup for 16-link with mean relative errors of 0.68-1.25%, supporting 4-bit signals at Gbps data rates of single-ended and differential TXs, as well as PAM4 TXs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.11699v1-abstract-full').style.display = 'none'; document.getElementById('2411.11699v1-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 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/2410.18092">arXiv:2410.18092</a> <span> [<a href="https://arxiv.org/pdf/2410.18092">pdf</a>, <a href="https://arxiv.org/format/2410.18092">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Two-Stage Radio Map Construction with Real Environments and Sparse Measurements </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yifan Wang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+N">Na Liu</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+L">Lianming Xu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+L">Li Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18092v1-abstract-short" style="display: inline;"> Radio map construction based on extensive measurements is accurate but expensive and time-consuming, while environment-aware radio map estimation reduces the costs at the expense of low accuracy. Considering accuracy and costs, a first-predict-then-correct (FPTC) method is proposed by leveraging generative adversarial networks (GANs). A primary radio map is first predicted by a radio map predictio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18092v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18092v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18092v1-abstract-full" style="display: none;"> Radio map construction based on extensive measurements is accurate but expensive and time-consuming, while environment-aware radio map estimation reduces the costs at the expense of low accuracy. Considering accuracy and costs, a first-predict-then-correct (FPTC) method is proposed by leveraging generative adversarial networks (GANs). A primary radio map is first predicted by a radio map prediction GAN (RMP-GAN) taking environmental information as input. Then, the prediction result is corrected by a radio map correction GAN (RMC-GAN) with sparse measurements as guidelines. Specifically, the self-attention mechanism and residual-connection blocks are introduced to RMP-GAN and RMC-GAN to improve the accuracy, respectively. Experimental results validate that the proposed FPTC-GANs method achieves the best radio map construction performance, compared with the state-of-the-art methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18092v1-abstract-full').style.display = 'none'; document.getElementById('2410.18092v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.04518">arXiv:2410.04518</a> <span> [<a href="https://arxiv.org/pdf/2410.04518">pdf</a>, <a href="https://arxiv.org/format/2410.04518">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"> A Reinforcement Learning Engine with Reduced Action and State Space for Scalable Cyber-Physical Optimal Response </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shining Sun</a>, <a href="/search/eess?searchtype=author&query=Haque%2C+K+A">Khandaker Akramul Haque</a>, <a href="/search/eess?searchtype=author&query=Huo%2C+X">Xiang Huo</a>, <a href="/search/eess?searchtype=author&query=Homoud%2C+L+A">Leen Al Homoud</a>, <a href="/search/eess?searchtype=author&query=Hossain-McKenzie%2C+S">Shamina Hossain-McKenzie</a>, <a href="/search/eess?searchtype=author&query=Goulart%2C+A">Ana Goulart</a>, <a href="/search/eess?searchtype=author&query=Davis%2C+K">Katherine Davis</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.04518v1-abstract-short" style="display: inline;"> Numerous research studies have been conducted to enhance the resilience of cyber-physical systems (CPSs) by detecting potential cyber or physical disturbances. However, the development of scalable and optimal response measures under power system contingency based on fusing cyber-physical data is still in an early stage. To address this research gap, this paper introduces a power system response en… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04518v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04518v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04518v1-abstract-full" style="display: none;"> Numerous research studies have been conducted to enhance the resilience of cyber-physical systems (CPSs) by detecting potential cyber or physical disturbances. However, the development of scalable and optimal response measures under power system contingency based on fusing cyber-physical data is still in an early stage. To address this research gap, this paper introduces a power system response engine based on reinforcement learning (RL) and role and interaction discovery (RID) techniques. RL-RID-GridResponder is designed to automatically detect the contingency and assist with the decision-making process to ensure optimal power system operation. The RL-RID-GridResponder learns via an RL-based structure and achieves enhanced scalability by integrating an RID module with reduced action and state spaces. The applicability of RL-RID-GridResponder in providing scalable and optimal responses for CPSs is demonstrated on power systems in the context of Denial of Service (DoS) attacks. Moreover, simulations are conducted on a Volt-Var regulation problem using the augmented WSCC 9-bus and augmented IEEE 24-bus systems based on fused cyber and physical data sets. The results show that the proposed RL-RID-GridResponder can provide fast and accurate responses to ensure optimal power system operation under DoS and can extend to other system contingencies such as line outages and loss of loads. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04518v1-abstract-full').style.display = 'none'; document.getElementById('2410.04518v1-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> 6 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09982">arXiv:2409.09982</a> <span> [<a href="https://arxiv.org/pdf/2409.09982">pdf</a>, <a href="https://arxiv.org/ps/2409.09982">ps</a>, <a href="https://arxiv.org/format/2409.09982">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"> Atomic Norm Minimization-based DoA Estimation for IRS-assisted Sensing Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+R">Renwang Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</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="2409.09982v1-abstract-short" style="display: inline;"> Intelligent reflecting surface (IRS) is expected to play a pivotal role in future wireless sensing networks owing to its potential for high-resolution and high-accuracy sensing. In this work, we investigate a multi-target direction-of-arrival (DoA) estimation problem in a semi-passive IRS-assisted sensing system, where IRS reflecting elements (REs) reflect signals from the base station to targets,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09982v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09982v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09982v1-abstract-full" style="display: none;"> Intelligent reflecting surface (IRS) is expected to play a pivotal role in future wireless sensing networks owing to its potential for high-resolution and high-accuracy sensing. In this work, we investigate a multi-target direction-of-arrival (DoA) estimation problem in a semi-passive IRS-assisted sensing system, where IRS reflecting elements (REs) reflect signals from the base station to targets, and IRS sensing elements (SEs) estimate DoA based on echo signals reflected by the targets. {First of all, instead of solely relying on IRS SEs for DoA estimation as done in the existing literature, this work fully exploits the DoA information embedded in both IRS REs and SEs matrices via the atomic norm minimization (ANM) scheme. Subsequently, the Cram茅r-Rao bound for DoA estimation is derived, revealing an inverse proportionality to $MN^3+NM^3$ under the case of identity covariance matrix of the IRS measurement matrix and a single target, where $M$ and $N$ are the number of IRS SEs and REs, respectively. Finally, extensive numerical results substantiate the superior accuracy and resolution performance of the proposed ANM-based DoA estimation method over representative baselines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09982v1-abstract-full').style.display = 'none'; document.getElementById('2409.09982v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <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 WCL</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09891">arXiv:2409.09891</a> <span> [<a href="https://arxiv.org/pdf/2409.09891">pdf</a>, <a href="https://arxiv.org/format/2409.09891">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="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"> Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Siqi Sun</a>, <a href="/search/eess?searchtype=author&query=Richmond%2C+K">Korin Richmond</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="2409.09891v1-abstract-short" style="display: inline;"> Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for text-to-speech (TTS). To overcome the fixed lexical coverage of bootstrapping training data, previous work has proposed to leverage easily accessible transcribed speech audio as an additional training source for acquiring… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09891v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09891v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09891v1-abstract-full" style="display: none;"> Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for text-to-speech (TTS). To overcome the fixed lexical coverage of bootstrapping training data, previous work has proposed to leverage easily accessible transcribed speech audio as an additional training source for acquiring novel pronunciation knowledge for uncovered words, which relies on an auxiliary ASR model as part of a cumbersome implementation flow. In this work, we propose an alternative method to leverage transcribed speech audio as an additional training source, based on multi-task learning (MTL). Experiments show that, compared to a baseline Seq2Seq frontend, the proposed MTL-based method reduces PER from 2.5% to 1.6% for those word types covered exclusively in transcribed speech audio, achieving a similar performance to the previous method but with a much simpler implementation flow. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09891v1-abstract-full').style.display = 'none'; document.getElementById('2409.09891v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09098">arXiv:2409.09098</a> <span> [<a href="https://arxiv.org/pdf/2409.09098">pdf</a>, <a href="https://arxiv.org/format/2409.09098">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"> AccentBox: Towards High-Fidelity Zero-Shot Accent Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhong%2C+J">Jinzuomu Zhong</a>, <a href="/search/eess?searchtype=author&query=Richmond%2C+K">Korin Richmond</a>, <a href="/search/eess?searchtype=author&query=Su%2C+Z">Zhiba Su</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Siqi Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.09098v2-abstract-short" style="display: inline;"> While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign Accent Conversion (FAC), accented TTS, and ZS-TTS, with a novel two-stage pipeline. In the first stage, we achieve state-of-the-art (SOTA) on Accent Identificat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09098v2-abstract-full').style.display = 'inline'; document.getElementById('2409.09098v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09098v2-abstract-full" style="display: none;"> While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue, we propose zero-shot accent generation that unifies Foreign Accent Conversion (FAC), accented TTS, and ZS-TTS, with a novel two-stage pipeline. In the first stage, we achieve state-of-the-art (SOTA) on Accent Identification (AID) with 0.56 f1 score on unseen speakers. In the second stage, we condition a ZS-TTS system on the pretrained speaker-agnostic accent embeddings extracted by the AID model. The proposed system achieves higher accent fidelity on inherent/cross accent generation, and enables unseen accent generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09098v2-abstract-full').style.display = 'none'; document.getElementById('2409.09098v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by ICASSP 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.08271">arXiv:2409.08271</a> <span> [<a href="https://arxiv.org/pdf/2409.08271">pdf</a>, <a href="https://arxiv.org/format/2409.08271">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="Graphics">cs.GR</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="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+R">Runjia Li</a>, <a href="/search/eess?searchtype=author&query=Han%2C+J">Junlin Han</a>, <a href="/search/eess?searchtype=author&query=Melas-Kyriazi%2C+L">Luke Melas-Kyriazi</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+C">Chunyi Sun</a>, <a href="/search/eess?searchtype=author&query=An%2C+Z">Zhaochong An</a>, <a href="/search/eess?searchtype=author&query=Gui%2C+Z">Zhongrui Gui</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuyang Sun</a>, <a href="/search/eess?searchtype=author&query=Torr%2C+P">Philip Torr</a>, <a href="/search/eess?searchtype=author&query=Jakab%2C+T">Tomas Jakab</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="2409.08271v1-abstract-short" style="display: inline;"> We present DreamBeast, a novel method based on score distillation sampling (SDS) for generating fantastical 3D animal assets composed of distinct parts. Existing SDS methods often struggle with this generation task due to a limited understanding of part-level semantics in text-to-image diffusion models. While recent diffusion models, such as Stable Diffusion 3, demonstrate a better part-level unde… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08271v1-abstract-full').style.display = 'inline'; document.getElementById('2409.08271v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.08271v1-abstract-full" style="display: none;"> We present DreamBeast, a novel method based on score distillation sampling (SDS) for generating fantastical 3D animal assets composed of distinct parts. Existing SDS methods often struggle with this generation task due to a limited understanding of part-level semantics in text-to-image diffusion models. While recent diffusion models, such as Stable Diffusion 3, demonstrate a better part-level understanding, they are prohibitively slow and exhibit other common problems associated with single-view diffusion models. DreamBeast overcomes this limitation through a novel part-aware knowledge transfer mechanism. For each generated asset, we efficiently extract part-level knowledge from the Stable Diffusion 3 model into a 3D Part-Affinity implicit representation. This enables us to instantly generate Part-Affinity maps from arbitrary camera views, which we then use to modulate the guidance of a multi-view diffusion model during SDS to create 3D assets of fantastical animals. DreamBeast significantly enhances the quality of generated 3D creatures with user-specified part compositions while reducing computational overhead, as demonstrated by extensive quantitative and qualitative evaluations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.08271v1-abstract-full').style.display = 'none'; document.getElementById('2409.08271v1-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> 12 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Project page: https://dreambeast3d.github.io/, code: https://github.com/runjiali-rl/threestudio-dreambeast</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.06635">arXiv:2409.06635</a> <span> [<a href="https://arxiv.org/pdf/2409.06635">pdf</a>, <a href="https://arxiv.org/ps/2409.06635">ps</a>, <a href="https://arxiv.org/format/2409.06635">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="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"> MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wenyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuo Sun</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+B">Bin Wang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+X">Xunlong Zou</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zhuohan Liu</a>, <a href="/search/eess?searchtype=author&query=He%2C+Y">Yingxu He</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+G">Geyu Lin</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+N+F">Nancy F. Chen</a>, <a href="/search/eess?searchtype=author&query=Aw%2C+A+T">Ai Ti Aw</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="2409.06635v2-abstract-short" style="display: inline;"> The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder with a pre-trained LLM, which are subsequently finetuned on specific audio tasks. However, the pre-t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06635v2-abstract-full').style.display = 'inline'; document.getElementById('2409.06635v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.06635v2-abstract-full" style="display: none;"> The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder with a pre-trained LLM, which are subsequently finetuned on specific audio tasks. However, the pre-trained audio encoder has constrained capacity to capture features for new tasks and datasets. To address this, we propose to incorporate mixtures of `weak' encoders (MoWE) into the AudioLLM framework. MoWE supplements a base encoder with a pool of relatively light weight encoders, selectively activated based on the audio input to enhance feature extraction without significantly increasing model size. Our empirical results demonstrate that MoWE effectively improves multi-task performance, broadening the applicability of AudioLLMs to more diverse audio tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06635v2-abstract-full').style.display = 'none'; document.getElementById('2409.06635v2-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 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/2409.03265">arXiv:2409.03265</a> <span> [<a href="https://arxiv.org/pdf/2409.03265">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Enhancing digital core image resolution using optimal upscaling algorithm: with application to paired SEM images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=You%2C+S">Shaohua You</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuqi Sun</a>, <a href="/search/eess?searchtype=author&query=Yan%2C+Z">Zhengting Yan</a>, <a href="/search/eess?searchtype=author&query=Liao%2C+Q">Qinzhuo Liao</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+H">Huiying Tang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+L">Lianhe Sun</a>, <a href="/search/eess?searchtype=author&query=Li%2C+G">Gensheng Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.03265v1-abstract-short" style="display: inline;"> The porous media community extensively utilizes digital rock images for core analysis. High-resolution digital rock images that possess sufficient quality are essential but often challenging to acquire. Super-resolution (SR) approaches enhance the resolution of digital rock images and provide improved visualization of fine features and structures, aiding in the analysis and interpretation of rock… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03265v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03265v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03265v1-abstract-full" style="display: none;"> The porous media community extensively utilizes digital rock images for core analysis. High-resolution digital rock images that possess sufficient quality are essential but often challenging to acquire. Super-resolution (SR) approaches enhance the resolution of digital rock images and provide improved visualization of fine features and structures, aiding in the analysis and interpretation of rock properties, such as pore connectivity and mineral distribution. However, there is a current shortage of real paired microscopic images for super-resolution training. In this study, we used two types of Scanning Electron Microscopes (SEM) to obtain the images of shale samples in five regions, with 1X, 2X, 4X, 8X and 16X magnifications. We used these real scanned paired images as a reference to select the optimal method of image generation and validated it using Enhanced Deep Super Resolution (EDSR) and Very Deep Super Resolution (VDSR) methods. Our experiments show that the bilinear algorithm is more suitable than the commonly used bicubic method, for establishing low-resolution datasets in the SR approaches, which is partially attributed to the mechanism of Scanning Electron Microscopes (SEM). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03265v1-abstract-full').style.display = 'none'; document.getElementById('2409.03265v1-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 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/2408.15947">arXiv:2408.15947</a> <span> [<a href="https://arxiv.org/pdf/2408.15947">pdf</a>, <a href="https://arxiv.org/format/2408.15947">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"> Auxiliary Input in Training: Incorporating Catheter Features into Deep Learning Models for ECG-Free Dynamic Coronary Roadmapping </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yikang Liu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+L">Lin Zhao</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+E+Z">Eric Z. Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xiao Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+T">Terrence Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shanhui Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.15947v1-abstract-short" style="display: inline;"> Dynamic coronary roadmapping is a technology that overlays the vessel maps (the "roadmap") extracted from an offline image sequence of X-ray angiography onto a live stream of X-ray fluoroscopy in real-time. It aims to offer navigational guidance for interventional surgeries without the need for repeated contrast agent injections, thereby reducing the risks associated with radiation exposure and ki… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15947v1-abstract-full').style.display = 'inline'; document.getElementById('2408.15947v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.15947v1-abstract-full" style="display: none;"> Dynamic coronary roadmapping is a technology that overlays the vessel maps (the "roadmap") extracted from an offline image sequence of X-ray angiography onto a live stream of X-ray fluoroscopy in real-time. It aims to offer navigational guidance for interventional surgeries without the need for repeated contrast agent injections, thereby reducing the risks associated with radiation exposure and kidney failure. The precision of the roadmaps is contingent upon the accurate alignment of angiographic and fluoroscopic images based on their cardiac phases, as well as precise catheter tip tracking. The former ensures the selection of a roadmap that closely matches the vessel shape in the current frame, while the latter uses catheter tips as reference points to adjust for translational motion between the roadmap and the present vessel tree. Training deep learning models for both tasks is challenging and underexplored. However, incorporating catheter features into the models could offer substantial benefits, given humans heavily rely on catheters to complete the tasks. To this end, we introduce a simple but effective method, auxiliary input in training (AIT), and demonstrate that it enhances model performance across both tasks, outperforming baseline methods in knowledge incorporation and transfer learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.15947v1-abstract-full').style.display = 'none'; document.getElementById('2408.15947v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 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">MICCAI 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.18862">arXiv:2406.18862</a> <span> [<a href="https://arxiv.org/pdf/2406.18862">pdf</a>, <a href="https://arxiv.org/format/2406.18862">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="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+P">Peikun Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sining Sun</a>, <a href="/search/eess?searchtype=author&query=Shan%2C+C">Changhao Shan</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+Q">Qing Yang</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.18862v1-abstract-short" style="display: inline;"> Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (ASR). These models typically adopt a unified method to model discrete speech and text tokens, followed by training a decoder-only transformer. However, they are all designed for non-streaming ASR tasks, where the entire s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18862v1-abstract-full').style.display = 'inline'; document.getElementById('2406.18862v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.18862v1-abstract-full" style="display: none;"> Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (ASR). These models typically adopt a unified method to model discrete speech and text tokens, followed by training a decoder-only transformer. However, they are all designed for non-streaming ASR tasks, where the entire speech utterance is needed during decoding. Hence, we introduce a decoder-only model exclusively designed for streaming recognition, incorporating a dedicated boundary token to facilitate streaming recognition and employing causal attention masking during the training phase. Furthermore, we introduce right-chunk attention and various data augmentation techniques to improve the model's contextual modeling abilities. While achieving streaming speech recognition, experiments on the AISHELL-1 and -2 datasets demonstrate the competitive performance of our streaming approach with non-streaming decoder-only counterparts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18862v1-abstract-full').style.display = 'none'; document.getElementById('2406.18862v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for Interspeech 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.18391">arXiv:2406.18391</a> <span> [<a href="https://arxiv.org/pdf/2406.18391">pdf</a>, <a href="https://arxiv.org/format/2406.18391">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"> CmWave and Sub-THz: Key Radio Enablers and Complementary Spectrum for 6G </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Katwe%2C+M+V">Mayur V. Katwe</a>, <a href="/search/eess?searchtype=author&query=Kaushik%2C+A">Aryan Kaushik</a>, <a href="/search/eess?searchtype=author&query=Singh%2C+K">Keshav Singh</a>, <a href="/search/eess?searchtype=author&query=Di+Renzo%2C+M">Marco Di Renzo</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+D">Doohwan Lee</a>, <a href="/search/eess?searchtype=author&query=Armada%2C+A+G">Ana G. Armada</a>, <a href="/search/eess?searchtype=author&query=Eldar%2C+Y+C">Yonina C. Eldar</a>, <a href="/search/eess?searchtype=author&query=Dobre%2C+O+A">Octavia A. Dobre</a>, <a href="/search/eess?searchtype=author&query=Rappaport%2C+T+S">Theodore S. Rappaport</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.18391v1-abstract-short" style="display: inline;"> Sixth-generation (6G) networks are poised to revolutionize communication by exploring alternative spectrum options, aiming to capitalize on strengths while mitigating limitations in current fifth-generation (5G) spectrum. This paper explores the potential opportunities and emerging trends for cmWave and sub-THz spectra as key radio enablers. This paper poses and answers three key questions regardi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18391v1-abstract-full').style.display = 'inline'; document.getElementById('2406.18391v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.18391v1-abstract-full" style="display: none;"> Sixth-generation (6G) networks are poised to revolutionize communication by exploring alternative spectrum options, aiming to capitalize on strengths while mitigating limitations in current fifth-generation (5G) spectrum. This paper explores the potential opportunities and emerging trends for cmWave and sub-THz spectra as key radio enablers. This paper poses and answers three key questions regarding motivation of additional spectrum to explore the strategic implementation and benefits of cmWave and sub-THz spectra. Also, we show using case studies how these complementary spectrum bands will enable new applications in 6G, such as integrated sensing and communication (ISAC), re-configurable intelligent surfaces (RIS) and non-terrestrial networks (NTN). Numerical simulations reveal that the ISAC performance of cmWave and sub-THz spectra outperforms that of existing 5G spectrum, including sub-6 GHz and mmWave. Additionally, we illustrate the effective interplay between RIS and NTN to counteract the effects of high attenuation at sub-THz frequencies. Finally, ongoing standardization endeavors, challenges and promising directions are elucidated for these complementary spectrum bands. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18391v1-abstract-full').style.display = 'none'; document.getElementById('2406.18391v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.16020">arXiv:2406.16020</a> <span> [<a href="https://arxiv.org/pdf/2406.16020">pdf</a>, <a href="https://arxiv.org/format/2406.16020">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"> AudioBench: A Universal Benchmark for Audio Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+B">Bin Wang</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+X">Xunlong Zou</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+G">Geyu Lin</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shuo Sun</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zhuohan Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wenyu Zhang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zhengyuan Liu</a>, <a href="/search/eess?searchtype=author&query=Aw%2C+A">AiTi Aw</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+N+F">Nancy F. Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.16020v4-abstract-short" style="display: inline;"> We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main aspects: speech understanding, audio scene understanding, and voice understanding (paralinguistic). Despite recent advancements, there lacks a comprehensive benchma… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16020v4-abstract-full').style.display = 'inline'; document.getElementById('2406.16020v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16020v4-abstract-full" style="display: none;"> We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs). It encompasses 8 distinct tasks and 26 datasets, among which, 7 are newly proposed datasets. The evaluation targets three main aspects: speech understanding, audio scene understanding, and voice understanding (paralinguistic). Despite recent advancements, there lacks a comprehensive benchmark for AudioLLMs on instruction following capabilities conditioned on audio signals. AudioBench addresses this gap by setting up datasets as well as desired evaluation metrics. Besides, we also evaluated the capabilities of five popular models and found that no single model excels consistently across all tasks. We outline the research outlook for AudioLLMs and anticipate that our open-sourced evaluation toolkit, data, and leaderboard will offer a robust testbed for future model developments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16020v4-abstract-full').style.display = 'none'; document.getElementById('2406.16020v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">v4 - Add acknowledgment and slight update on structure; Code: https://github.com/AudioLLMs/AudioBench</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.07399">arXiv:2406.07399</a> <span> [<a href="https://arxiv.org/pdf/2406.07399">pdf</a>, <a href="https://arxiv.org/format/2406.07399">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Redefining Automotive Radar Imaging: A Domain-Informed 1D Deep Learning Approach for High-Resolution and Efficient Performance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zheng%2C+R">Ruxin Zheng</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a>, <a href="/search/eess?searchtype=author&query=Caesar%2C+H">Holger Caesar</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+H">Honglei Chen</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jian Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.07399v1-abstract-short" style="display: inline;"> Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for precise semantic scene interpretation. Classical super-resolution techniques adapted from optical imaging inadequately address the distinct characteristics of radar… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07399v1-abstract-full').style.display = 'inline'; document.getElementById('2406.07399v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.07399v1-abstract-full" style="display: none;"> Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for precise semantic scene interpretation. Classical super-resolution techniques adapted from optical imaging inadequately address the distinct characteristics of radar signal data. In response, our study redefines radar imaging super-resolution as a one-dimensional (1D) signal super-resolution spectra estimation problem by harnessing the radar signal processing domain knowledge, introducing innovative data normalization and a domain-informed signal-to-noise ratio (SNR)-guided loss function. Our tailored deep learning network for automotive radar imaging exhibits remarkable scalability, parameter efficiency and fast inference speed, alongside enhanced performance in terms of radar imaging quality and resolution. Extensive testing confirms that our SR-SPECNet sets a new benchmark in producing high-resolution radar range-azimuth images, outperforming existing methods across varied antenna configurations and dataset sizes. Source code and new radar dataset will be made publicly available online. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.07399v1-abstract-full').style.display = 'none'; document.getElementById('2406.07399v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.01937">arXiv:2406.01937</a> <span> [<a href="https://arxiv.org/pdf/2406.01937">pdf</a>, <a href="https://arxiv.org/format/2406.01937">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"> Cram茅r-Rao Bound Analysis and Beamforming Design for Integrated Sensing and Communication with Extended Targets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yiqiu Wang</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.01937v1-abstract-short" style="display: inline;"> This paper studies an integrated sensing and communication (ISAC) system, where a multi-antenna base station transmits beamformed signals for joint downlink multi-user communication and radar sensing of an extended target (ET). By considering echo signals as reflections from valid elements on the ET contour, a set of novel Cram茅r-Rao bounds (CRBs) is derived for parameter estimation of the ET, inc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.01937v1-abstract-full').style.display = 'inline'; document.getElementById('2406.01937v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.01937v1-abstract-full" style="display: none;"> This paper studies an integrated sensing and communication (ISAC) system, where a multi-antenna base station transmits beamformed signals for joint downlink multi-user communication and radar sensing of an extended target (ET). By considering echo signals as reflections from valid elements on the ET contour, a set of novel Cram茅r-Rao bounds (CRBs) is derived for parameter estimation of the ET, including central range, direction, and orientation. The ISAC transmit beamforming design is then formulated as an optimization problem, aiming to minimize the CRB associated with radar sensing, while satisfying a minimum signal-to-interference-pulse-noise ratio requirement for each communication user, along with a 3-dB beam coverage constraint tailored for the ET. To solve this non-convex problem, we utilize semidefinite relaxation (SDR) and propose a rank-one solution extraction scheme for non-tight relaxation circumstances. To reduce the computation complexity, we further employ an efficient zero-forcing (ZF) based beamforming design, where the sensing task is performed in the null space of communication channels. Numerical results validate the effectiveness of the obtained CRB, revealing the diverse features of CRB for differently shaped ETs. The proposed SDR beamforming design outperforms benchmark designs with lower estimation error and CRB, while the ZF beamforming design greatly improves computation efficiency with minor sensing performance loss. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.01937v1-abstract-full').style.display = 'none'; document.getElementById('2406.01937v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submitted to IEEE Transactions on Wireless Communications. arXiv admin note: text overlap with arXiv:2312.10641</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.18844">arXiv:2405.18844</a> <span> [<a href="https://arxiv.org/pdf/2405.18844">pdf</a>, <a href="https://arxiv.org/format/2405.18844">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"> Optical IRS for Visible Light Communication: Modeling, Design, and Open Issues </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shiyuan Sun</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fang Yang</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+W">Weidong Mei</a>, <a href="/search/eess?searchtype=author&query=Song%2C+J">Jian Song</a>, <a href="/search/eess?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rui Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.18844v1-abstract-short" style="display: inline;"> Optical intelligent reflecting surface (OIRS) offers a new and effective approach to resolving the line-of-sight blockage issue in visible light communication (VLC) by enabling redirection of light to bypass obstacles, thereby dramatically enhancing indoor VLC coverage and reliability. This article provides a comprehensive overview of OIRS for VLC, including channel modeling, design techniques, an… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.18844v1-abstract-full').style.display = 'inline'; document.getElementById('2405.18844v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.18844v1-abstract-full" style="display: none;"> Optical intelligent reflecting surface (OIRS) offers a new and effective approach to resolving the line-of-sight blockage issue in visible light communication (VLC) by enabling redirection of light to bypass obstacles, thereby dramatically enhancing indoor VLC coverage and reliability. This article provides a comprehensive overview of OIRS for VLC, including channel modeling, design techniques, and open issues. First, we present the characteristics of OIRS-reflected channels and introduce two practical models, namely, optics model and association model, which are then compared in terms of applicable conditions, configuration methods, and channel parameters. Next, under the more practically appealing association model, we discuss the main design techniques for OIRS-aided VLC systems, including beam alignment, channel estimation, and OIRS reflection optimization. Finally, open issues are identified to stimulate future research in this area. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.18844v1-abstract-full').style.display = 'none'; document.getElementById('2405.18844v1-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 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/2405.17297">arXiv:2405.17297</a> <span> [<a href="https://arxiv.org/pdf/2405.17297">pdf</a>, <a href="https://arxiv.org/format/2405.17297">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"> Enhanced Automotive Radar Collaborative Sensing By Exploiting Constructive Interference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+L">Lifan Xu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a>, <a href="/search/eess?searchtype=author&query=Swindlehurst%2C+A+L">A. Lee Swindlehurst</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="2405.17297v1-abstract-short" style="display: inline;"> Automotive radar emerges as a crucial sensor for autonomous vehicle perception. As more cars are equipped radars, radar interference is an unavoidable challenge. Unlike conventional approaches such as interference mitigation and interference-avoiding technologies, this paper introduces an innovative collaborative sensing scheme with multiple automotive radars that exploits constructive interferenc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17297v1-abstract-full').style.display = 'inline'; document.getElementById('2405.17297v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.17297v1-abstract-full" style="display: none;"> Automotive radar emerges as a crucial sensor for autonomous vehicle perception. As more cars are equipped radars, radar interference is an unavoidable challenge. Unlike conventional approaches such as interference mitigation and interference-avoiding technologies, this paper introduces an innovative collaborative sensing scheme with multiple automotive radars that exploits constructive interference. Through collaborative sensing, our method optimally aligns cross-path interference signals from other radars with another radar's self-echo signals, thereby significantly augmenting its target detection capabilities. This approach alleviates the need for extensive raw data sharing between collaborating radars. Instead, only an optimized weighting matrix needs to be exchanged between the radars. This approach considerably decreases the data bandwidth requirements for the wireless channel, making it a more feasible and practical solution for automotive radar collaboration. Numerical results demonstrate the effectiveness of the constructive interference approach for enhanced object detection capability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.17297v1-abstract-full').style.display = 'none'; document.getElementById('2405.17297v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">paper accepted by IEEE SAM Workshop 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16893">arXiv:2405.16893</a> <span> [<a href="https://arxiv.org/pdf/2405.16893">pdf</a>, <a href="https://arxiv.org/format/2405.16893">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"> Cross Far- and Near-Field Channel Measurement and Modeling in Extremely Large-scale Antenna Array (ELAA) Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yiqin Wang</a>, <a href="/search/eess?searchtype=author&query=Han%2C+C">Chong Han</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jianhua Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2405.16893v1-abstract-short" style="display: inline;"> Technologies like ultra-massive multiple-input-multiple-output (UM-MIMO) and reconfigurable intelligent surfaces (RISs) are of special interest to meet the key performance indicators of future wireless systems including ubiquitous connectivity and lightning-fast data rates. One of their common features, the extremely large-scale antenna array (ELAA) systems with hundreds or thousands of antennas,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16893v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16893v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16893v1-abstract-full" style="display: none;"> Technologies like ultra-massive multiple-input-multiple-output (UM-MIMO) and reconfigurable intelligent surfaces (RISs) are of special interest to meet the key performance indicators of future wireless systems including ubiquitous connectivity and lightning-fast data rates. One of their common features, the extremely large-scale antenna array (ELAA) systems with hundreds or thousands of antennas, give rise to near-field (NF) propagation and bring new challenges to channel modeling and characterization. In this paper, a cross-field channel model for ELAA systems is proposed, which improves the statistical model in 3GPP TR 38.901 by refining the propagation path with its first and last bounces and differentiating the characterization of parameters like path loss, delay, and angles in near- and far-fields. A comprehensive analysis of cross-field boundaries and closed-form expressions of corresponding NF or FF parameters are provided. Furthermore, cross-field experiments carried out in a typical indoor scenario at 300 GHz verify the variation of MPC parameters across the antenna array, and demonstrate the distinction of channels between different antenna elements. Finally, detailed generation procedures of the cross-field channel model are provided, based on which simulations and analysis on NF probabilities and channel coefficients are conducted for $4\times4$, $8\times8$, $16\times16$, and $9\times21$ uniform planar arrays at different frequency bands. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16893v1-abstract-full').style.display = 'none'; document.getElementById('2405.16893v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 33 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.05715">arXiv:2405.05715</a> <span> [<a href="https://arxiv.org/pdf/2405.05715">pdf</a>, <a href="https://arxiv.org/format/2405.05715">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"> Shifting the ISAC Trade-Off with Fluid Antenna Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zou%2C+J">Jiaqi Zou</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+H">Hao Xu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+C">Chao Wang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+L">Lvxin Xu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Songlin Sun</a>, <a href="/search/eess?searchtype=author&query=Meng%2C+K">Kaitao Meng</a>, <a href="/search/eess?searchtype=author&query=Masouros%2C+C">Christos Masouros</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="2405.05715v1-abstract-short" style="display: inline;"> As an emerging antenna technology, a fluid antenna system (FAS) enhances spatial diversity to improve both sensing and communication performance by shifting the active antennas among available ports. In this letter, we study the potential of shifting the integrated sensing and communication (ISAC) trade-off with FAS. We propose the model for FAS-enabled ISAC and jointly optimize the transmit beamf… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05715v1-abstract-full').style.display = 'inline'; document.getElementById('2405.05715v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.05715v1-abstract-full" style="display: none;"> As an emerging antenna technology, a fluid antenna system (FAS) enhances spatial diversity to improve both sensing and communication performance by shifting the active antennas among available ports. In this letter, we study the potential of shifting the integrated sensing and communication (ISAC) trade-off with FAS. We propose the model for FAS-enabled ISAC and jointly optimize the transmit beamforming and port selection of FAS. In particular, we aim to minimize the transmit power, while satisfying both communication and sensing requirements. An efficient iterative algorithm based on sparse optimization, convex approximation, and a penalty approach is developed. The simulation results show that the proposed scheme can attain 33% reductions in transmit power with guaranteed sensing and communication performance, showing the great potential of the fluid antenna for striking a flexible tradeoff between sensing and communication in ISAC systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.05715v1-abstract-full').style.display = 'none'; document.getElementById('2405.05715v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.02788">arXiv:2405.02788</a> <span> [<a href="https://arxiv.org/pdf/2405.02788">pdf</a>, <a href="https://arxiv.org/format/2405.02788">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"> Antenna Failure Resilience: Deep Learning-Enabled Robust DOA Estimation with Single Snapshot Sparse Arrays </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zheng%2C+R">Ruxin Zheng</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+H">Hongshan Liu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+H">Honglei Chen</a>, <a href="/search/eess?searchtype=author&query=Soltanalian%2C+M">Mojtaba Soltanalian</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jian 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="2405.02788v1-abstract-short" style="display: inline;"> Recent advancements in Deep Learning (DL) for Direction of Arrival (DOA) estimation have highlighted its superiority over traditional methods, offering faster inference, enhanced super-resolution, and robust performance in low Signal-to-Noise Ratio (SNR) environments. Despite these advancements, existing research predominantly focuses on multi-snapshot scenarios, a limitation in the context of aut… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02788v1-abstract-full').style.display = 'inline'; document.getElementById('2405.02788v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.02788v1-abstract-full" style="display: none;"> Recent advancements in Deep Learning (DL) for Direction of Arrival (DOA) estimation have highlighted its superiority over traditional methods, offering faster inference, enhanced super-resolution, and robust performance in low Signal-to-Noise Ratio (SNR) environments. Despite these advancements, existing research predominantly focuses on multi-snapshot scenarios, a limitation in the context of automotive radar systems which demand high angular resolution and often rely on limited snapshots, sometimes as scarce as a single snapshot. Furthermore, the increasing interest in sparse arrays for automotive radar, owing to their cost-effectiveness and reduced antenna element coupling, presents additional challenges including susceptibility to random sensor failures. This paper introduces a pioneering DL framework featuring a sparse signal augmentation layer, meticulously crafted to bolster single snapshot DOA estimation across diverse sparse array setups and amidst antenna failures. To our best knowledge, this is the first work to tackle this issue. Our approach improves the adaptability of deep learning techniques to overcome the unique difficulties posed by sparse arrays with single snapshot. We conduct thorough evaluations of our network's performance using simulated and real-world data, showcasing the efficacy and real-world viability of our proposed solution. The code and real-world dataset employed in this study are available at https://github.com/ruxinzh/Deep_RSA_DOA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.02788v1-abstract-full').style.display = 'none'; document.getElementById('2405.02788v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Invited paper for IEEE Asilomar conference 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/2404.14778">arXiv:2404.14778</a> <span> [<a href="https://arxiv.org/pdf/2404.14778">pdf</a>, <a href="https://arxiv.org/format/2404.14778">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"> Channel Estimation for Optical Intelligent Reflecting Surface-Assisted VLC System: A Joint Space-Time Sampling Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shiyuan Sun</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fang Yang</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+W">Weidong Mei</a>, <a href="/search/eess?searchtype=author&query=Song%2C+J">Jian Song</a>, <a href="/search/eess?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rui Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.14778v1-abstract-short" style="display: inline;"> Optical intelligent reflecting surface (OIRS) has attracted increasing attention due to its capability of overcoming signal blockages in visible light communication (VLC), an emerging technology for the next-generation advanced transceivers. However, current works on OIRS predominantly assume known channel state information (CSI), which is essential to practical OIRS configuration. To bridge such… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14778v1-abstract-full').style.display = 'inline'; document.getElementById('2404.14778v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14778v1-abstract-full" style="display: none;"> Optical intelligent reflecting surface (OIRS) has attracted increasing attention due to its capability of overcoming signal blockages in visible light communication (VLC), an emerging technology for the next-generation advanced transceivers. However, current works on OIRS predominantly assume known channel state information (CSI), which is essential to practical OIRS configuration. To bridge such a gap, this paper proposes a new and customized channel estimation protocol for OIRSs under the alignment-based channel model. Specifically, we first unveil OIRS spatial and temporal coherence characteristics and derive the coherence distance and the coherence time in closed form. Next, to achieve fast beam alignment over different coherence time, we propose to dynamically tune the rotational angles of the OIRS reflecting elements following a geometric optics-based non-uniform codebook. Given the above beam alignment, we propose an efficient joint space-time sampling-based algorithm to estimate the OIRS channel. In particular, we divide the OIRS into multiple subarrays based on the coherence distance and sequentially estimate their associated CSI, followed by a spacetime interpolation to retrieve full CSI for other non-aligned transceiver antennas. Numerical results validate our theoretical analyses and demonstrate the efficacy of our proposed OIRS channel estimation scheme as compared to other benchmark schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14778v1-abstract-full').style.display = 'none'; document.getElementById('2404.14778v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.14706">arXiv:2404.14706</a> <span> [<a href="https://arxiv.org/pdf/2404.14706">pdf</a>, <a href="https://arxiv.org/format/2404.14706">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"> Channel Estimation for Optical IRS-Assisted VLC System via Spatial Coherence </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shiyuan Sun</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+F">Fang Yang</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+W">Weidong Mei</a>, <a href="/search/eess?searchtype=author&query=Song%2C+J">Jian Song</a>, <a href="/search/eess?searchtype=author&query=Han%2C+Z">Zhu Han</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rui Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.14706v1-abstract-short" style="display: inline;"> Optical intelligent reflecting surface (OIRS) has been considered a promising technology for visible light communication (VLC) by constructing visual line-of-sight propagation paths to address the signal blockage issue. However, the existing works on OIRSs are mostly based on perfect channel state information (CSI), whose acquisition appears to be challenging due to the passive nature of the OIRS.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14706v1-abstract-full').style.display = 'inline'; document.getElementById('2404.14706v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.14706v1-abstract-full" style="display: none;"> Optical intelligent reflecting surface (OIRS) has been considered a promising technology for visible light communication (VLC) by constructing visual line-of-sight propagation paths to address the signal blockage issue. However, the existing works on OIRSs are mostly based on perfect channel state information (CSI), whose acquisition appears to be challenging due to the passive nature of the OIRS. To tackle this challenge, this paper proposes a customized channel estimation algorithm for OIRSs. Specifically, we first unveil the OIRS spatial coherence characteristics and derive the coherence distance in closed form. Based on this property, a spatial sampling-based algorithm is proposed to estimate the OIRS-reflected channel, by dividing the OIRS into multiple subarrays based on the coherence distance and sequentially estimating their associated CSI, followed by an interpolation to retrieve the full CSI. Simulation results validate the derived OIRS spatial coherence and demonstrate the efficacy of the proposed OIRS channel estimation algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.14706v1-abstract-full').style.display = 'none'; document.getElementById('2404.14706v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.10556">arXiv:2404.10556</a> <span> [<a href="https://arxiv.org/pdf/2404.10556">pdf</a>, <a href="https://arxiv.org/format/2404.10556">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Generative AI for Advanced UAV Networking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+G">Geng Sun</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+W">Wenwen Xie</a>, <a href="/search/eess?searchtype=author&query=Niyato%2C+D">Dusit Niyato</a>, <a href="/search/eess?searchtype=author&query=Du%2C+H">Hongyang Du</a>, <a href="/search/eess?searchtype=author&query=Kang%2C+J">Jiawen Kang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+J">Jing Wu</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sumei Sun</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+P">Ping Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.10556v1-abstract-short" style="display: inline;"> With the impressive achievements of chatGPT and Sora, generative artificial intelligence (GAI) has received increasing attention. Not limited to the field of content generation, GAI is also widely used to solve the problems in wireless communication scenarios due to its powerful learning and generalization capabilities. Therefore, we discuss key applications of GAI in improving unmanned aerial veh… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.10556v1-abstract-full').style.display = 'inline'; document.getElementById('2404.10556v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.10556v1-abstract-full" style="display: none;"> With the impressive achievements of chatGPT and Sora, generative artificial intelligence (GAI) has received increasing attention. Not limited to the field of content generation, GAI is also widely used to solve the problems in wireless communication scenarios due to its powerful learning and generalization capabilities. Therefore, we discuss key applications of GAI in improving unmanned aerial vehicle (UAV) communication and networking performance in this article. Specifically, we first review the key technologies of GAI and the important roles of UAV networking. Then, we show how GAI can improve the communication, networking, and security performances of UAV systems. Subsequently, we propose a novel framework of GAI for advanced UAV networking, and then present a case study of UAV-enabled spectrum map estimation and transmission rate optimization based on the proposed framework to verify the effectiveness of GAI-enabled UAV systems. Finally, we discuss some important open directions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.10556v1-abstract-full').style.display = 'none'; document.getElementById('2404.10556v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07473">arXiv:2404.07473</a> <span> [<a href="https://arxiv.org/pdf/2404.07473">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> LUCF-Net: Lightweight U-shaped Cascade Fusion Network for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Songkai Sun</a>, <a href="/search/eess?searchtype=author&query=She%2C+Q">Qingshan She</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+Y">Yuliang Ma</a>, <a href="/search/eess?searchtype=author&query=Li%2C+R">Rihui Li</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yingchun Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.07473v1-abstract-short" style="display: inline;"> In this study, the performance of existing U-shaped neural network architectures was enhanced for medical image segmentation by adding Transformer. Although Transformer architectures are powerful at extracting global information, its ability to capture local information is limited due to its high complexity. To address this challenge, we proposed a new lightweight U-shaped cascade fusion network (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07473v1-abstract-full').style.display = 'inline'; document.getElementById('2404.07473v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07473v1-abstract-full" style="display: none;"> In this study, the performance of existing U-shaped neural network architectures was enhanced for medical image segmentation by adding Transformer. Although Transformer architectures are powerful at extracting global information, its ability to capture local information is limited due to its high complexity. To address this challenge, we proposed a new lightweight U-shaped cascade fusion network (LUCF-Net) for medical image segmentation. It utilized an asymmetrical structural design and incorporated both local and global modules to enhance its capacity for local and global modeling. Additionally, a multi-layer cascade fusion decoding network was designed to further bolster the network's information fusion capabilities. Validation results achieved on multi-organ datasets in CT format, cardiac segmentation datasets in MRI format, and dermatology datasets in image format demonstrated that the proposed model outperformed other state-of-the-art methods in handling local-global information, achieving an improvement of 1.54% in Dice coefficient and 2.6 mm in Hausdorff distance on multi-organ segmentation. Furthermore, as a network that combines Convolutional Neural Network and Transformer architectures, it achieves competitive segmentation performance with only 6.93 million parameters and 6.6 gigabytes of floating point operations, without the need of pre-training. In summary, the proposed method demonstrated enhanced performance while retaining a simpler model design compared to other Transformer-based segmentation networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07473v1-abstract-full').style.display = 'none'; document.getElementById('2404.07473v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.03327">arXiv:2404.03327</a> <span> [<a href="https://arxiv.org/pdf/2404.03327">pdf</a>, <a href="https://arxiv.org/format/2404.03327">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"> DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shangquan Sun</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+W">Wenqi Ren</a>, <a href="/search/eess?searchtype=author&query=Peng%2C+J">Jingyang Peng</a>, <a href="/search/eess?searchtype=author&query=Song%2C+F">Fenglong Song</a>, <a href="/search/eess?searchtype=author&query=Cao%2C+X">Xiaochun Cao</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="2404.03327v1-abstract-short" style="display: inline;"> Many existing methods for low-light image enhancement (LLIE) based on Retinex theory ignore important factors that affect the validity of this theory in digital imaging, such as noise, quantization error, non-linearity, and dynamic range overflow. In this paper, we propose a new expression called Digital-Imaging Retinex theory (DI-Retinex) through theoretical and experimental analysis of Retinex t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03327v1-abstract-full').style.display = 'inline'; document.getElementById('2404.03327v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.03327v1-abstract-full" style="display: none;"> Many existing methods for low-light image enhancement (LLIE) based on Retinex theory ignore important factors that affect the validity of this theory in digital imaging, such as noise, quantization error, non-linearity, and dynamic range overflow. In this paper, we propose a new expression called Digital-Imaging Retinex theory (DI-Retinex) through theoretical and experimental analysis of Retinex theory in digital imaging. Our new expression includes an offset term in the enhancement model, which allows for pixel-wise brightness contrast adjustment with a non-linear mapping function. In addition, to solve the lowlight enhancement problem in an unsupervised manner, we propose an image-adaptive masked reverse degradation loss in Gamma space. We also design a variance suppression loss for regulating the additional offset term. Extensive experiments show that our proposed method outperforms all existing unsupervised methods in terms of visual quality, model size, and speed. Our algorithm can also assist downstream face detectors in low-light, as it shows the most performance gain after the low-light enhancement compared to other methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03327v1-abstract-full').style.display = 'none'; document.getElementById('2404.03327v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.08758">arXiv:2403.08758</a> <span> [<a href="https://arxiv.org/pdf/2403.08758">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Spatiotemporal Diffusion Model with Paired Sampling for Accelerated Cardiac Cine MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Qiu%2C+S">Shihan Qiu</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+S">Shaoyan Pan</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yikang Liu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+L">Lin Zhao</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+J">Jian Xu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+T">Terrence Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+E+Z">Eric Z. Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xiao Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shanhui Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.08758v1-abstract-short" style="display: inline;"> Current deep learning reconstruction for accelerated cardiac cine MRI suffers from spatial and temporal blurring. We aim to improve image sharpness and motion delineation for cine MRI under high undersampling rates. A spatiotemporal diffusion enhancement model conditional on an existing deep learning reconstruction along with a novel paired sampling strategy was developed. The diffusion model prov… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08758v1-abstract-full').style.display = 'inline'; document.getElementById('2403.08758v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.08758v1-abstract-full" style="display: none;"> Current deep learning reconstruction for accelerated cardiac cine MRI suffers from spatial and temporal blurring. We aim to improve image sharpness and motion delineation for cine MRI under high undersampling rates. A spatiotemporal diffusion enhancement model conditional on an existing deep learning reconstruction along with a novel paired sampling strategy was developed. The diffusion model provided sharper tissue boundaries and clearer motion than the original reconstruction in experts evaluation on clinical data. The innovative paired sampling strategy substantially reduced artificial noises in the generative results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08758v1-abstract-full').style.display = 'none'; document.getElementById('2403.08758v1-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 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/2403.08749">arXiv:2403.08749</a> <span> [<a href="https://arxiv.org/pdf/2403.08749">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Clinically Feasible Diffusion Reconstruction for Highly-Accelerated Cardiac Cine MRI </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Qiu%2C+S">Shihan Qiu</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+S">Shaoyan Pan</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Y">Yikang Liu</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+L">Lin Zhao</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+J">Jian Xu</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+T">Terrence Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+E+Z">Eric Z. Chen</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xiao Chen</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shanhui Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.08749v1-abstract-short" style="display: inline;"> The currently limited quality of accelerated cardiac cine reconstruction may potentially be improved by the emerging diffusion models, but the clinically unacceptable long processing time poses a challenge. We aim to develop a clinically feasible diffusion-model-based reconstruction pipeline to improve the image quality of cine MRI. A multi-in multi-out diffusion enhancement model together with fa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08749v1-abstract-full').style.display = 'inline'; document.getElementById('2403.08749v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.08749v1-abstract-full" style="display: none;"> The currently limited quality of accelerated cardiac cine reconstruction may potentially be improved by the emerging diffusion models, but the clinically unacceptable long processing time poses a challenge. We aim to develop a clinically feasible diffusion-model-based reconstruction pipeline to improve the image quality of cine MRI. A multi-in multi-out diffusion enhancement model together with fast inference strategies were developed to be used in conjunction with a reconstruction model. The diffusion reconstruction reduced spatial and temporal blurring in prospectively undersampled clinical data, as validated by experts inspection. The 1.5s per video processing time enabled the approach to be applied in clinical scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08749v1-abstract-full').style.display = 'none'; document.getElementById('2403.08749v1-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 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/2403.08168">arXiv:2403.08168</a> <span> [<a href="https://arxiv.org/pdf/2403.08168">pdf</a>, <a href="https://arxiv.org/format/2403.08168">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"> Collaborative Automotive Radar Sensing via Mixed-Precision Distributed Array Completion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Eamaz%2C+A">Arian Eamaz</a>, <a href="/search/eess?searchtype=author&query=Yeganegi%2C+F">Farhang Yeganegi</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+Y">Yunqiao Hu</a>, <a href="/search/eess?searchtype=author&query=Soltanalian%2C+M">Mojtaba Soltanalian</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.08168v1-abstract-short" style="display: inline;"> This paper investigates the effects of coarse quantization with mixed precision on measurements obtained from sparse linear arrays, synthesized by a collaborative automotive radar sensing strategy. The mixed quantization precision significantly reduces the data amount that needs to be shared from radar nodes to the fusion center for coherent processing. We utilize the low-rank properties inherent… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08168v1-abstract-full').style.display = 'inline'; document.getElementById('2403.08168v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.08168v1-abstract-full" style="display: none;"> This paper investigates the effects of coarse quantization with mixed precision on measurements obtained from sparse linear arrays, synthesized by a collaborative automotive radar sensing strategy. The mixed quantization precision significantly reduces the data amount that needs to be shared from radar nodes to the fusion center for coherent processing. We utilize the low-rank properties inherent in the constructed Hankel matrix of the mixed-precision array, to recover azimuth angles from quantized measurements. Our proposed approach addresses the challenge of mixed-quantized Hankel matrix completion, allowing for accurate estimation of the azimuth angles of interest. To evaluate the recovery performance of the proposed scheme, we establish a quasi-isometric embedding with a high probability for mixed-precision quantization. The effectiveness of our proposed scheme is demonstrated through numerical results, highlighting successful reconstruction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.08168v1-abstract-full').style.display = 'none'; document.getElementById('2403.08168v1-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> 12 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 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">arXiv admin note: text overlap with arXiv:2312.05423</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.03145">arXiv:2403.03145</a> <span> [<a href="https://arxiv.org/pdf/2403.03145">pdf</a>, <a href="https://arxiv.org/format/2403.03145">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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Multimedia">cs.MM</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"> Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+Y">Yuxin Guo</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+S">Shijie Ma</a>, <a href="/search/eess?searchtype=author&query=Su%2C+H">Hu Su</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhiqing Wang</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+Y">Yuhao Zhao</a>, <a href="/search/eess?searchtype=author&query=Zou%2C+W">Wei Zou</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Siyang Sun</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+Y">Yun Zheng</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="2403.03145v1-abstract-short" style="display: inline;"> Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without any bounding-box annotations, they struggle to achieve precise localization, especially for small objects, and suffer from blurry boundaries and false positives.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.03145v1-abstract-full').style.display = 'inline'; document.getElementById('2403.03145v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.03145v1-abstract-full" style="display: none;"> Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without any bounding-box annotations, they struggle to achieve precise localization, especially for small objects, and suffer from blurry boundaries and false positives. Moreover, the naive semi-supervised method is poor in fully leveraging the information of abundant unlabeled data. In this paper, we propose a novel semi-supervised learning framework for AVSL, namely Dual Mean-Teacher (DMT), comprising two teacher-student structures to circumvent the confirmation bias issue. Specifically, two teachers, pre-trained on limited labeled data, are employed to filter out noisy samples via the consensus between their predictions, and then generate high-quality pseudo-labels by intersecting their confidence maps. The sufficient utilization of both labeled and unlabeled data and the proposed unbiased framework enable DMT to outperform current state-of-the-art methods by a large margin, with CIoU of 90.4% and 48.8% on Flickr-SoundNet and VGG-Sound Source, obtaining 8.9%, 9.6% and 4.6%, 6.4% improvements over self- and semi-supervised methods respectively, given only 3% positional-annotations. We also extend our framework to some existing AVSL methods and consistently boost their performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.03145v1-abstract-full').style.display = 'none'; document.getElementById('2403.03145v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to NeurIPS2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.14018">arXiv:2402.14018</a> <span> [<a href="https://arxiv.org/pdf/2402.14018">pdf</a>, <a href="https://arxiv.org/format/2402.14018">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"> Performance Evaluation and Analysis of Thresholding-based Interference Mitigation for Automotive Radar Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+J">Jun Li</a>, <a href="/search/eess?searchtype=author&query=Youn%2C+J">Jihwan Youn</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+R">Ryan Wu</a>, <a href="/search/eess?searchtype=author&query=Overdevest%2C+J">Jeroen Overdevest</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shunqiao Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.14018v1-abstract-short" style="display: inline;"> In automotive radar, time-domain thresholding (TD-TH) and time-frequency domain thresholding (TFD-TH) are crucial techniques underpinning numerous interference mitigation methods. Despite their importance, comprehensive evaluations of these methods in dense traffic scenarios with different types of interference are limited. In this study, we segment automotive radar interference into three distinc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14018v1-abstract-full').style.display = 'inline'; document.getElementById('2402.14018v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.14018v1-abstract-full" style="display: none;"> In automotive radar, time-domain thresholding (TD-TH) and time-frequency domain thresholding (TFD-TH) are crucial techniques underpinning numerous interference mitigation methods. Despite their importance, comprehensive evaluations of these methods in dense traffic scenarios with different types of interference are limited. In this study, we segment automotive radar interference into three distinct categories. Utilizing the in-house traffic scenario and automotive radar simulator, we evaluate interference mitigation methods across multiple metrics: probability of detection, signal-to-interference-plus-noise ratio, and phase error involving hundreds of targets and dozens of interfering radars. The numerical results highlight that TFD-TH is more effective than TD-TH, particularly as the density and signal correlation of interfering radars escalate. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14018v1-abstract-full').style.display = 'none'; document.getElementById('2402.14018v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.09619">arXiv:2402.09619</a> <span> [<a href="https://arxiv.org/pdf/2402.09619">pdf</a>, <a href="https://arxiv.org/ps/2402.09619">ps</a>, <a href="https://arxiv.org/format/2402.09619">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="Networking and Internet Architecture">cs.NI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Statistics Theory">math.ST</span> </div> </div> <p class="title is-5 mathjax"> Dynamic Cooperative MAC Optimization in RSU-Enhanced VANETs: A Distributed Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zhou Zhang</a>, <a href="/search/eess?searchtype=author&query=Atapattu%2C+S">Saman Atapattu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yizhu Wang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sumei Sun</a>, <a href="/search/eess?searchtype=author&query=Sithamparanathan%2C+K">Kandeepan Sithamparanathan</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="2402.09619v1-abstract-short" style="display: inline;"> This paper presents an optimization approach for cooperative Medium Access Control (MAC) techniques in Vehicular Ad Hoc Networks (VANETs) equipped with Roadside Unit (RSU) to enhance network throughput. Our method employs a distributed cooperative MAC scheme based on Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) protocol, featuring selective RSU probing and adaptive transmission… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09619v1-abstract-full').style.display = 'inline'; document.getElementById('2402.09619v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.09619v1-abstract-full" style="display: none;"> This paper presents an optimization approach for cooperative Medium Access Control (MAC) techniques in Vehicular Ad Hoc Networks (VANETs) equipped with Roadside Unit (RSU) to enhance network throughput. Our method employs a distributed cooperative MAC scheme based on Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) protocol, featuring selective RSU probing and adaptive transmission. It utilizes a dual timescale channel access framework, with a ``large-scale'' phase accounting for gradual changes in vehicle locations and a ``small-scale'' phase adapting to rapid channel fluctuations. We propose the RSU Probing and Cooperative Access (RPCA) strategy, a two-stage approach based on dynamic inter-vehicle distances from the RSU. Using optimal sequential planned decision theory, we rigorously prove its optimality in maximizing average system throughput per large-scale phase. For practical implementation in VANETs, we develop a distributed MAC algorithm with periodic location updates. It adjusts thresholds based on inter-vehicle and vehicle-RSU distances during the large-scale phase and accesses channels following the RPCA strategy with updated thresholds during the small-scale phase. Simulation results confirm the effectiveness and efficiency of our algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09619v1-abstract-full').style.display = 'none'; document.getElementById('2402.09619v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 5 figures, IEEE ICC 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/2402.03988">arXiv:2402.03988</a> <span> [<a href="https://arxiv.org/pdf/2402.03988">pdf</a>, <a href="https://arxiv.org/format/2402.03988">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"> REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Tseng%2C+L">Liang-Hsuan Tseng</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+E">En-Pei Hu</a>, <a href="/search/eess?searchtype=author&query=Chiang%2C+C">Cheng-Han Chiang</a>, <a href="/search/eess?searchtype=author&query=Tseng%2C+Y">Yuan Tseng</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H">Hung-yi Lee</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+L">Lin-shan Lee</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shao-Hua Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.03988v3-abstract-short" style="display: inline;"> Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is represented by a segment of speech signal with variable length and unknown boundary, and this segmental structure makes learning the mapping between speech and text… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03988v3-abstract-full').style.display = 'inline'; document.getElementById('2402.03988v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.03988v3-abstract-full" style="display: none;"> Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is represented by a segment of speech signal with variable length and unknown boundary, and this segmental structure makes learning the mapping between speech and text challenging, especially without paired data. In this paper, we propose REBORN,Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR. REBORN alternates between (1) training a segmentation model that predicts the boundaries of the segmental structures in speech signals and (2) training the phoneme prediction model, whose input is the speech feature segmented by the segmentation model, to predict a phoneme transcription. Since supervised data for training the segmentation model is not available, we use reinforcement learning to train the segmentation model to favor segmentations that yield phoneme sequence predictions with a lower perplexity. We conduct extensive experiments and find that under the same setting, REBORN outperforms all prior unsupervised ASR models on LibriSpeech, TIMIT, and five non-English languages in Multilingual LibriSpeech. We comprehensively analyze why the boundaries learned by REBORN improve the unsupervised ASR performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03988v3-abstract-full').style.display = 'none'; document.getElementById('2402.03988v3-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">NeurIPS 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/2402.01031">arXiv:2402.01031</a> <span> [<a href="https://arxiv.org/pdf/2402.01031">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1093/radadv/umae035">10.1093/radadv/umae035 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> MRAnnotator: multi-Anatomy and many-Sequence MRI segmentation of 44 structures </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+A">Alexander Zhou</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zelong Liu</a>, <a href="/search/eess?searchtype=author&query=Tieu%2C+A">Andrew Tieu</a>, <a href="/search/eess?searchtype=author&query=Patel%2C+N">Nikhil Patel</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sean Sun</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+A">Anthony Yang</a>, <a href="/search/eess?searchtype=author&query=Choi%2C+P">Peter Choi</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+H">Hao-Chih Lee</a>, <a href="/search/eess?searchtype=author&query=Tordjman%2C+M">Mickael Tordjman</a>, <a href="/search/eess?searchtype=author&query=Deyer%2C+L">Louisa Deyer</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+Y">Yunhao Mei</a>, <a href="/search/eess?searchtype=author&query=Fauveau%2C+V">Valentin Fauveau</a>, <a href="/search/eess?searchtype=author&query=Soultanidis%2C+G">George Soultanidis</a>, <a href="/search/eess?searchtype=author&query=Taouli%2C+B">Bachir Taouli</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+M">Mingqian Huang</a>, <a href="/search/eess?searchtype=author&query=Doshi%2C+A">Amish Doshi</a>, <a href="/search/eess?searchtype=author&query=Fayad%2C+Z+A">Zahi A. Fayad</a>, <a href="/search/eess?searchtype=author&query=Deyer%2C+T">Timothy Deyer</a>, <a href="/search/eess?searchtype=author&query=Mei%2C+X">Xueyan Mei</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="2402.01031v2-abstract-short" style="display: inline;"> In this retrospective study, we annotated 44 structures on two datasets: an internal dataset of 1,518 MRI sequences from 843 patients at the Mount Sinai Health System, and an external dataset of 397 MRI sequences from 263 patients for benchmarking. The internal dataset trained the nnU-Net model MRAnnotator, which demonstrated strong generalizability on the external dataset. MRAnnotator outperforme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01031v2-abstract-full').style.display = 'inline'; document.getElementById('2402.01031v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01031v2-abstract-full" style="display: none;"> In this retrospective study, we annotated 44 structures on two datasets: an internal dataset of 1,518 MRI sequences from 843 patients at the Mount Sinai Health System, and an external dataset of 397 MRI sequences from 263 patients for benchmarking. The internal dataset trained the nnU-Net model MRAnnotator, which demonstrated strong generalizability on the external dataset. MRAnnotator outperformed existing models such as TotalSegmentator MRI and MRSegmentator on both datasets, achieving an overall average Dice score of 0.878 on the internal dataset and 0.875 on the external set. Model weights are available on GitHub, and the external test set can be shared upon request. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01031v2-abstract-full').style.display = 'none'; document.getElementById('2402.01031v2-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, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Radiology Advances, Volume 2, Issue 1, January 2025 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.15344">arXiv:2401.15344</a> <span> [<a href="https://arxiv.org/pdf/2401.15344">pdf</a>, <a href="https://arxiv.org/format/2401.15344">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 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/TWC.2024.3486023">10.1109/TWC.2024.3486023 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> IRS Aided Millimeter-Wave Sensing and Communication: Beam Scanning, Beam Splitting, and Performance Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+R">Renwang Li</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+X">Xiaodan Shao</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Shu Sun</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+M">Meixia Tao</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+R">Rui Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2401.15344v1-abstract-short" style="display: inline;"> Integrated sensing and communication (ISAC) has attracted growing interests for enabling the future 6G wireless networks, due to its capability of sharing spectrum and hardware resources between communication and sensing systems. However, existing works on ISAC usually need to modify the communication protocol to cater for the new sensing performance requirement, which may be difficult to implemen… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.15344v1-abstract-full').style.display = 'inline'; document.getElementById('2401.15344v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.15344v1-abstract-full" style="display: none;"> Integrated sensing and communication (ISAC) has attracted growing interests for enabling the future 6G wireless networks, due to its capability of sharing spectrum and hardware resources between communication and sensing systems. However, existing works on ISAC usually need to modify the communication protocol to cater for the new sensing performance requirement, which may be difficult to implement in practice. In this paper, we study a new intelligent reflecting surface (IRS) aided millimeter-wave (mmWave) ISAC system by exploiting the distinct beam scanning operation in mmWave communications to achieve efficient sensing at the same time. First, we propose a two-phase ISAC protocol aided by a semi-passive IRS, consisting of beam scanning and data transmission. Specifically, in the beam scanning phase, the IRS finds the optimal beam for reflecting signals from the base station to a communication user via its passive elements. Meanwhile, the IRS directly estimates the angle of a nearby target based on echo signals from the target using its equipped active sensing element. Then, in the data transmission phase, the sensing accuracy is further improved by leveraging the data signals via possible IRS beam splitting. Next, we derive the achievable rate of the communication user as well as the Cram茅r-Rao bound and the approximate mean square error of the target angle estimation Finally, extensive simulation results are provided to verify our analysis as well as the effectiveness of the proposed scheme. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.15344v1-abstract-full').style.display = 'none'; document.getElementById('2401.15344v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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 TWC</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> IEEE Transactions on Wireless Communications, vol. 23, no. 12, pp. 19713-19727, Dec. 2024 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.16064">arXiv:2312.16064</a> <span> [<a href="https://arxiv.org/pdf/2312.16064">pdf</a>, <a href="https://arxiv.org/format/2312.16064">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Goal-Oriented Integration of Sensing, Communication, Computing, and Control for Mission-Critical Internet-of-Things </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cao%2C+J">Jie Cao</a>, <a href="/search/eess?searchtype=author&query=Kurniawan%2C+E">Ernest Kurniawan</a>, <a href="/search/eess?searchtype=author&query=Boonkajay%2C+A">Amnart Boonkajay</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+S">Sumei Sun</a>, <a href="/search/eess?searchtype=author&query=Popovski%2C+P">Petar Popovski</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+X">Xu Zhu</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="2312.16064v2-abstract-short" style="display: inline;"> Driven by the development goal of network paradigm and demand for various functions in the sixth-generation (6G) mission-critical Internet-of-Things (MC-IoT), we foresee a goal-oriented integration of sensing, communication, computing, and control (GIS3C) in this paper. We first provide an overview of the tasks, requirements, and challenges of MC-IoT. Then we introduce an end-to-end GIS3C architec… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.16064v2-abstract-full').style.display = 'inline'; document.getElementById('2312.16064v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.16064v2-abstract-full" style="display: none;"> Driven by the development goal of network paradigm and demand for various functions in the sixth-generation (6G) mission-critical Internet-of-Things (MC-IoT), we foresee a goal-oriented integration of sensing, communication, computing, and control (GIS3C) in this paper. We first provide an overview of the tasks, requirements, and challenges of MC-IoT. Then we introduce an end-to-end GIS3C architecture, in which goal-oriented communication is leveraged to bridge and empower sensing, communication, control, and computing functionalities. By revealing the interplay among multiple subsystems in terms of key performance indicators and parameters, this paper introduces unified metrics, i.e., task completion effectiveness and cost, to facilitate S3C co-design in MC-IoT. The preliminary results demonstrate the benefits of GIS3C in improving task completion effectiveness while reducing costs. We also identify and highlight the gaps and challenges in applying GIS3C in the future 6G networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.16064v2-abstract-full').style.display = 'none'; document.getElementById('2312.16064v2-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </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=Sun%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Sun%2C+S&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </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