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 108 results for author: <span class="mathjax">Song, 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=Song%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="Song, 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=Song%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="Song, 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=Song%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Song%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Song%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Song%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </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/2411.07806">arXiv:2411.07806</a> <span> [<a href="https://arxiv.org/pdf/2411.07806">pdf</a>, <a href="https://arxiv.org/format/2411.07806">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="Cryptography and Security">cs.CR</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"> Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Kang%2C+T">Tianqu Kang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zixin Wang</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2411.07806v2-abstract-short" style="display: inline;"> Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. To lessen the computational burden on resource-limited devices, combining low-rank adaptation (LoRA) with federated l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07806v2-abstract-full').style.display = 'inline'; document.getElementById('2411.07806v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.07806v2-abstract-full" style="display: none;"> Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. To lessen the computational burden on resource-limited devices, combining low-rank adaptation (LoRA) with federated learning enables parameter-efficient fine-tuning. Additionally, the split FedFT architecture partitions an FM between edge devices and a central server, reducing the necessity for complete model deployment on individual devices. However, the risk of privacy eavesdropping attacks in FedFT remains a concern, particularly in sensitive areas such as healthcare and finance. In this paper, we propose a split FedFT framework with differential privacy (DP) over wireless networks, where the inherent wireless channel noise in the uplink transmission is utilized to achieve DP guarantees without adding an extra artificial noise. We shall investigate the impact of the wireless noise on convergence performance of the proposed framework. We will also show that by updating only one of the low-rank matrices in the split FedFT with DP, the proposed method can mitigate the noise amplification effect. Simulation results will demonstrate that the proposed framework achieves higher accuracy under strict privacy budgets compared to baseline methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.07806v2-abstract-full').style.display = 'none'; document.getElementById('2411.07806v2-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 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, 3 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/2411.04568">arXiv:2411.04568</a> <span> [<a href="https://arxiv.org/pdf/2411.04568">pdf</a>, <a href="https://arxiv.org/format/2411.04568">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Dynamic-Attention-based EEG State Transition Modeling for Emotion Recognition </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Shen%2C+X">Xinke Shen</a>, <a href="/search/eess?searchtype=author&query=Gan%2C+R">Runmin Gan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+K">Kaixuan Wang</a>, <a href="/search/eess?searchtype=author&query=Yang%2C+S">Shuyi Yang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Q">Qingzhu Zhang</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quanying Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+D">Dan Zhang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sen Song</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="2411.04568v1-abstract-short" style="display: inline;"> Electroencephalogram (EEG)-based emotion decoding can objectively quantify people's emotional state and has broad application prospects in human-computer interaction and early detection of emotional disorders. Recently emerging deep learning architectures have significantly improved the performance of EEG emotion decoding. However, existing methods still fall short of fully capturing the complex s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04568v1-abstract-full').style.display = 'inline'; document.getElementById('2411.04568v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.04568v1-abstract-full" style="display: none;"> Electroencephalogram (EEG)-based emotion decoding can objectively quantify people's emotional state and has broad application prospects in human-computer interaction and early detection of emotional disorders. Recently emerging deep learning architectures have significantly improved the performance of EEG emotion decoding. However, existing methods still fall short of fully capturing the complex spatiotemporal dynamics of neural signals, which are crucial for representing emotion processing. This study proposes a Dynamic-Attention-based EEG State Transition (DAEST) modeling method to characterize EEG spatiotemporal dynamics. The model extracts spatiotemporal components of EEG that represent multiple parallel neural processes and estimates dynamic attention weights on these components to capture transitions in brain states. The model is optimized within a contrastive learning framework for cross-subject emotion recognition. The proposed method achieved state-of-the-art performance on three publicly available datasets: FACED, SEED, and SEED-V. It achieved 75.4% accuracy in the binary classification of positive and negative emotions and 59.3% in nine-class discrete emotion classification on the FACED dataset, 88.1% in the three-class classification of positive, negative, and neutral emotions on the SEED dataset, and 73.6% in five-class discrete emotion classification on the SEED-V dataset. The learned EEG spatiotemporal patterns and dynamic transition properties offer valuable insights into neural dynamics underlying emotion processing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.04568v1-abstract-full').style.display = 'none'; document.getElementById('2411.04568v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 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">14 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/2410.03143">arXiv:2410.03143</a> <span> [<a href="https://arxiv.org/pdf/2410.03143">pdf</a>, <a href="https://arxiv.org/format/2410.03143">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> ECHOPulse: ECG controlled echocardio-grams video generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yiwei Li</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+S">Sekeun Kim</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Z">Zihao Wu</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+H">Hanqi Jiang</a>, <a href="/search/eess?searchtype=author&query=Pan%2C+Y">Yi Pan</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Pengfei Jin</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sifan Song</a>, <a href="/search/eess?searchtype=author&query=Shi%2C+Y">Yucheng Shi</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+T">Tianming Liu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiang Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.03143v2-abstract-short" style="display: inline;"> Echocardiography (ECHO) is essential for cardiac assessments, but its video quality and interpretation heavily relies on manual expertise, leading to inconsistent results from clinical and portable devices. ECHO video generation offers a solution by improving automated monitoring through synthetic data and generating high-quality videos from routine health data. However, existing models often face… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03143v2-abstract-full').style.display = 'inline'; document.getElementById('2410.03143v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03143v2-abstract-full" style="display: none;"> Echocardiography (ECHO) is essential for cardiac assessments, but its video quality and interpretation heavily relies on manual expertise, leading to inconsistent results from clinical and portable devices. ECHO video generation offers a solution by improving automated monitoring through synthetic data and generating high-quality videos from routine health data. However, existing models often face high computational costs, slow inference, and rely on complex conditional prompts that require experts' annotations. To address these challenges, we propose ECHOPULSE, an ECG-conditioned ECHO video generation model. ECHOPULSE introduces two key advancements: (1) it accelerates ECHO video generation by leveraging VQ-VAE tokenization and masked visual token modeling for fast decoding, and (2) it conditions on readily accessible ECG signals, which are highly coherent with ECHO videos, bypassing complex conditional prompts. To the best of our knowledge, this is the first work to use time-series prompts like ECG signals for ECHO video generation. ECHOPULSE not only enables controllable synthetic ECHO data generation but also provides updated cardiac function information for disease monitoring and prediction beyond ECG alone. Evaluations on three public and private datasets demonstrate state-of-the-art performance in ECHO video generation across both qualitative and quantitative measures. Additionally, ECHOPULSE can be easily generalized to other modality generation tasks, such as cardiac MRI, fMRI, and 3D CT generation. Demo can seen from \url{https://github.com/levyisthebest/ECHOPulse_Prelease}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03143v2-abstract-full').style.display = 'none'; document.getElementById('2410.03143v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.12433">arXiv:2409.12433</a> <span> [<a href="https://arxiv.org/pdf/2409.12433">pdf</a>, <a href="https://arxiv.org/format/2409.12433">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Hardware Architecture">cs.AR</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"> A High-Throughput Hardware Accelerator for Lempel-Ziv 4 Compression Algorithm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+T">Tao Chen</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Suwen Song</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhongfeng 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="2409.12433v1-abstract-short" style="display: inline;"> This paper delves into recent hardware implementations of the Lempel-Ziv 4 (LZ4) algorithm, highlighting two key factors that limit the throughput of single-kernel compressors. Firstly, the actual parallelism exhibited in single-kernel designs falls short of the theoretical potential. Secondly, the clock frequency is constrained due to the presence of the feedback loops. To tackle these challenges… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12433v1-abstract-full').style.display = 'inline'; document.getElementById('2409.12433v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.12433v1-abstract-full" style="display: none;"> This paper delves into recent hardware implementations of the Lempel-Ziv 4 (LZ4) algorithm, highlighting two key factors that limit the throughput of single-kernel compressors. Firstly, the actual parallelism exhibited in single-kernel designs falls short of the theoretical potential. Secondly, the clock frequency is constrained due to the presence of the feedback loops. To tackle these challenges, we propose a novel scheme that restricts each parallelization window to a single match, thus elevating the level of actual parallelism. Furthermore, by restricting the maximum match length, we eliminate the feedback loops within the architecture, enabling a significant boost in throughput. Finally, we present a high-speed hardware architecture. The implementation results demonstrate that the proposed architecture achieves a throughput of up to 16.10 Gb/s, exhibiting a 2.648x improvement over the start-of-the-art. The new design only results in an acceptable compression ratio reduction ranging from 4.93% to 11.68% with various numbers of hash table entries, compared to the LZ4 compression ratio achieved by official software implementations disclosed on GitHub. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.12433v1-abstract-full').style.display = 'none'; document.getElementById('2409.12433v1-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 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/2408.13829">arXiv:2408.13829</a> <span> [<a href="https://arxiv.org/pdf/2408.13829">pdf</a>, <a href="https://arxiv.org/ps/2408.13829">ps</a>, <a href="https://arxiv.org/format/2408.13829">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Sensing-aided Near-Field Secure Communications with Mobile Eavesdroppers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yiming Xu</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+M">Mingxuan Zheng</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+D">Dongfang Xu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=da+Costa%2C+D+B">Daniel Benevides da Costa</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="2408.13829v1-abstract-short" style="display: inline;"> The additional degree of freedom (DoF) in the distance domain of near-field communication offers new opportunities for physical layer security (PLS) design. However, existing works mainly consider static eavesdroppers, and the related study with mobile eavesdroppers is still in its infancy due to the difficulty in obtaining the channel state information (CSI) of the eavesdropper. To this end, we p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13829v1-abstract-full').style.display = 'inline'; document.getElementById('2408.13829v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13829v1-abstract-full" style="display: none;"> The additional degree of freedom (DoF) in the distance domain of near-field communication offers new opportunities for physical layer security (PLS) design. However, existing works mainly consider static eavesdroppers, and the related study with mobile eavesdroppers is still in its infancy due to the difficulty in obtaining the channel state information (CSI) of the eavesdropper. To this end, we propose to leverage the sensing capability of integrated sensing and communication (ISAC) systems to assist PLS design. To comprehensively study the dynamic behaviors of the system, we propose a Pareto optimization framework, where a multi-objective optimization problem (MOOP) is formulated to simultaneously optimize three key performance metrics: power consumption, number of securely served users, and tracking performance, while guaranteeing the achievable rate of the users with a given leakage rate constraint. A globally optimal design based on the generalized Benders decomposition (GBD) method is proposed to achieve the Pareto optimal solutions. To reduce the computational complexity, we further design a low-complexity algorithm based on zero-forcing (ZF) beamforming and successive convex approximation (SCA). Simulation results validate the effectiveness of the proposed algorithms and reveal the intrinsic trade-offs between the three performance metrics. It is observed that near-field communication offers a favorable beam diffraction effect for PLS, where the energy of the information signal is nulled around the eavesdropper and focused on the users. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13829v1-abstract-full').style.display = 'none'; document.getElementById('2408.13829v1-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.20937">arXiv:2407.20937</a> <span> [<a href="https://arxiv.org/pdf/2407.20937">pdf</a>, <a href="https://arxiv.org/format/2407.20937">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"> EAR: Edge-Aware Reconstruction of 3-D vertebrae structures from bi-planar X-ray images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Tan%2C+L">Lixing Tan</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shuang Song</a>, <a href="/search/eess?searchtype=author&query=He%2C+Y">Yaofeng He</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+K">Kangneng Zhou</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+T">Tong Lu</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+R">Ruoxiu Xiao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.20937v2-abstract-short" style="display: inline;"> X-ray images ease the diagnosis and treatment process due to their rapid imaging speed and high resolution. However, due to the projection process of X-ray imaging, much spatial information has been lost. To accurately provide efficient spinal morphological and structural information, reconstructing the 3-D structures of the spine from the 2-D X-ray images is essential. It is challenging for curre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.20937v2-abstract-full').style.display = 'inline'; document.getElementById('2407.20937v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.20937v2-abstract-full" style="display: none;"> X-ray images ease the diagnosis and treatment process due to their rapid imaging speed and high resolution. However, due to the projection process of X-ray imaging, much spatial information has been lost. To accurately provide efficient spinal morphological and structural information, reconstructing the 3-D structures of the spine from the 2-D X-ray images is essential. It is challenging for current reconstruction methods to preserve the edge information and local shapes of the asymmetrical vertebrae structures. In this study, we propose a new Edge-Aware Reconstruction network (EAR) to focus on the performance improvement of the edge information and vertebrae shapes. In our network, by using the auto-encoder architecture as the backbone, the edge attention module and frequency enhancement module are proposed to strengthen the perception of the edge reconstruction. Meanwhile, we also combine four loss terms, including reconstruction loss, edge loss, frequency loss and projection loss. The proposed method is evaluated using three publicly accessible datasets and compared with four state-of-the-art models. The proposed method is superior to other methods and achieves 25.32%, 15.32%, 86.44%, 80.13%, 23.7612 and 0.3014 with regard to MSE, MAE, Dice, SSIM, PSNR and frequency distance. Due to the end-to-end and accurate reconstruction process, EAR can provide sufficient 3-D spatial information and precise preoperative surgical planning guidance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.20937v2-abstract-full').style.display = 'none'; document.getElementById('2407.20937v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">13 pages, 11 figures, 3 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.13703">arXiv:2407.13703</a> <span> [<a href="https://arxiv.org/pdf/2407.13703">pdf</a>, <a href="https://arxiv.org/format/2407.13703">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="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"> Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Qu%2C+L">Linping Qu</a>, <a href="/search/eess?searchtype=author&query=Mao%2C+Y">Yuyi Mao</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Tsui%2C+C">Chi-Ying Tsui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.13703v3-abstract-short" style="display: inline;"> One of the most critical challenges for deploying distributed learning solutions, such as federated learning (FL), in wireless networks is the limited battery capacity of mobile clients. While it is a common belief that the major energy consumption of mobile clients comes from the uplink data transmission, this paper presents a novel finding, namely channel decoding also contributes significantly… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13703v3-abstract-full').style.display = 'inline'; document.getElementById('2407.13703v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.13703v3-abstract-full" style="display: none;"> One of the most critical challenges for deploying distributed learning solutions, such as federated learning (FL), in wireless networks is the limited battery capacity of mobile clients. While it is a common belief that the major energy consumption of mobile clients comes from the uplink data transmission, this paper presents a novel finding, namely channel decoding also contributes significantly to the overall energy consumption of mobile clients in FL. Motivated by this new observation, we propose an energy-efficient adaptive channel decoding scheme that leverages the intrinsic robustness of FL to model errors. In particular, the robustness is exploited to reduce the energy consumption of channel decoders at mobile clients by adaptively adjusting the number of decoding iterations. We theoretically prove that wireless FL with communication errors can converge at the same rate as the case with error-free communication provided the bit error rate (BER) is properly constrained. An adaptive channel decoding scheme is then proposed to improve the energy efficiency of wireless FL systems. Experimental results demonstrate that the proposed method maintains the same learning accuracy while reducing the channel decoding energy consumption by ~20% when compared to an existing approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13703v3-abstract-full').style.display = 'none'; document.getElementById('2407.13703v3-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted by the IEEE TWC</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.08458">arXiv:2407.08458</a> <span> [<a href="https://arxiv.org/pdf/2407.08458">pdf</a>, <a href="https://arxiv.org/format/2407.08458">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="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"> Joint Optimization of Age of Information and Energy Consumption in NR-V2X System based on Deep Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Song%2C+S">Shulin Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Z">Zheng Zhang</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+Q">Qiong Wu</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+Q">Qiang Fan</a>, <a href="/search/eess?searchtype=author&query=Fan%2C+P">Pingyi Fan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.08458v1-abstract-short" style="display: inline;"> Autonomous driving may be the most important application scenario of next generation, the development of wireless access technologies enabling reliable and low-latency vehicle communication becomes crucial. To address this, 3GPP has developed Vehicle-to-Everything (V2X) specifications based on 5G New Radio (NR) technology, where Mode 2 Side-Link (SL) communication resembles Mode 4 in LTE-V2X, allo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08458v1-abstract-full').style.display = 'inline'; document.getElementById('2407.08458v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.08458v1-abstract-full" style="display: none;"> Autonomous driving may be the most important application scenario of next generation, the development of wireless access technologies enabling reliable and low-latency vehicle communication becomes crucial. To address this, 3GPP has developed Vehicle-to-Everything (V2X) specifications based on 5G New Radio (NR) technology, where Mode 2 Side-Link (SL) communication resembles Mode 4 in LTE-V2X, allowing direct communication between vehicles. This supplements SL communication in LTE-V2X and represents the latest advancement in cellular V2X (C-V2X) with improved performance of NR-V2X. However, in NR-V2X Mode 2, resource collisions still occur, and thus degrade the age of information (AOI). Therefore, a interference cancellation method is employed to mitigate this impact by combining NR-V2X with Non-Orthogonal multiple access (NOMA) technology. In NR-V2X, when vehicles select smaller resource reservation interval (RRI), higher-frequency transmissions take ore energy to reduce AoI. Hence, it is important to jointly consider AoI and communication energy consumption based on NR-V2X communication. Then, we formulate such an optimization problem and employ the Deep Reinforcement Learning (DRL) algorithm to compute the optimal transmission RRI and transmission power for each transmitting vehicle to reduce the energy consumption of each transmitting vehicle and the AoI of each receiving vehicle. Extensive simulations have demonstrated the performance of our proposed algorithm. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.08458v1-abstract-full').style.display = 'none'; document.getElementById('2407.08458v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper has been accepted by sensors. The source code has been released at: https://github.com/qiongwu86/Joint-Optimization-of-AoI-and-Energy-Consumption-in-NR-V2X-System-based-on-DRL</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.04709">arXiv:2407.04709</a> <span> [<a href="https://arxiv.org/pdf/2407.04709">pdf</a>, <a href="https://arxiv.org/format/2407.04709">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> <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"> Efficient 4D Radar Data Auto-labeling Method using LiDAR-based Object Detection Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Sun%2C+M">Min-Hyeok Sun</a>, <a href="/search/eess?searchtype=author&query=Paek%2C+D">Dong-Hee Paek</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Seung-Hyun Song</a>, <a href="/search/eess?searchtype=author&query=Kong%2C+S">Seung-Hyun Kong</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.04709v1-abstract-short" style="display: inline;"> Focusing on the strength of 4D (4-Dimensional) radar, research about robust 3D object detection networks in adverse weather conditions has gained attention. To train such networks, datasets that contain large amounts of 4D radar data and ground truth labels are essential. However, the existing 4D radar datasets (e.g., K-Radar) lack sufficient sensor data and labels, which hinders the advancement i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04709v1-abstract-full').style.display = 'inline'; document.getElementById('2407.04709v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.04709v1-abstract-full" style="display: none;"> Focusing on the strength of 4D (4-Dimensional) radar, research about robust 3D object detection networks in adverse weather conditions has gained attention. To train such networks, datasets that contain large amounts of 4D radar data and ground truth labels are essential. However, the existing 4D radar datasets (e.g., K-Radar) lack sufficient sensor data and labels, which hinders the advancement in this research domain. Furthermore, enlarging the 4D radar datasets requires a time-consuming and expensive manual labeling process. To address these issues, we propose the auto-labeling method of 4D radar tensor (4DRT) in the K-Radar dataset. The proposed method initially trains a LiDAR-based object detection network (LODN) using calibrated LiDAR point cloud (LPC). The trained LODN then automatically generates ground truth labels (i.e., auto-labels, ALs) of the K-Radar train dataset without human intervention. The generated ALs are used to train the 4D radar-based object detection network (4DRODN), Radar Tensor Network with Height (RTNH). The experimental results demonstrate that RTNH trained with ALs has achieved a similar detection performance to the original RTNH which is trained with manually annotated ground truth labels, thereby verifying the effectiveness of the proposed auto-labeling method. All relevant codes will be soon available at the following GitHub project: https://github.com/kaist-avelab/K-Radar <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04709v1-abstract-full').style.display = 'none'; document.getElementById('2407.04709v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accept at IEEE IVS 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.02877">arXiv:2407.02877</a> <span> [<a href="https://arxiv.org/pdf/2407.02877">pdf</a>, <a href="https://arxiv.org/format/2407.02877">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"> Resource Allocation Design for Next-Generation Multiple Access: A Tutorial Overview </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wei%2C+Z">Zhiqiang Wei</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+D">Dongfang Xu</a>, <a href="/search/eess?searchtype=author&query=Li%2C+S">Shuangyang Li</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Ng%2C+D+W+K">Derrick Wing Kwan Ng</a>, <a href="/search/eess?searchtype=author&query=Caire%2C+G">Giuseppe Caire</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.02877v1-abstract-short" style="display: inline;"> Multiple access is the cornerstone technology for each generation of wireless cellular networks and resource allocation design plays a crucial role in multiple access. In this paper, we present a comprehensive tutorial overview for junior researchers in this field, aiming to offer a foundational guide for resource allocation design in the context of next-generation multiple access (NGMA). Initiall… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02877v1-abstract-full').style.display = 'inline'; document.getElementById('2407.02877v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.02877v1-abstract-full" style="display: none;"> Multiple access is the cornerstone technology for each generation of wireless cellular networks and resource allocation design plays a crucial role in multiple access. In this paper, we present a comprehensive tutorial overview for junior researchers in this field, aiming to offer a foundational guide for resource allocation design in the context of next-generation multiple access (NGMA). Initially, we identify three types of channels in future wireless cellular networks over which NGMA will be implemented, namely: natural channels, reconfigurable channels, and functional channels. Natural channels are traditional uplink and downlink communication channels; reconfigurable channels are defined as channels that can be proactively reshaped via emerging platforms or techniques, such as intelligent reflecting surface (IRS), unmanned aerial vehicle (UAV), and movable/fluid antenna (M/FA); and functional channels support not only communication but also other functionalities simultaneously, with typical examples including integrated sensing and communication (ISAC) and joint computing and communication (JCAC) channels. Then, we introduce NGMA models applicable to these three types of channels that cover most of the practical communication scenarios of future wireless communications. Subsequently, we articulate the key optimization technical challenges inherent in the resource allocation design for NGMA, categorizing them into rate-oriented, power-oriented, and reliability-oriented resource allocation designs. The corresponding optimization approaches for solving the formulated resource allocation design problems are then presented. Finally, simulation results are presented and discussed to elucidate the practical implications and insights derived from resource allocation designs in NGMA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02877v1-abstract-full').style.display = 'none'; document.getElementById('2407.02877v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">69 pages, 10 figures, 5 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.19464">arXiv:2406.19464</a> <span> [<a href="https://arxiv.org/pdf/2406.19464">pdf</a>, <a href="https://arxiv.org/format/2406.19464">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zeyi Liu</a>, <a href="/search/eess?searchtype=author&query=Chi%2C+C">Cheng Chi</a>, <a href="/search/eess?searchtype=author&query=Cousineau%2C+E">Eric Cousineau</a>, <a href="/search/eess?searchtype=author&query=Kuppuswamy%2C+N">Naveen Kuppuswamy</a>, <a href="/search/eess?searchtype=author&query=Burchfiel%2C+B">Benjamin Burchfiel</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shuran Song</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="2406.19464v2-abstract-short" style="display: inline;"> Audio signals provide rich information for the robot interaction and object properties through contact. This information can surprisingly ease the learning of contact-rich robot manipulation skills, especially when the visual information alone is ambiguous or incomplete. However, the usage of audio data in robot manipulation has been constrained to teleoperated demonstrations collected by either a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19464v2-abstract-full').style.display = 'inline'; document.getElementById('2406.19464v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.19464v2-abstract-full" style="display: none;"> Audio signals provide rich information for the robot interaction and object properties through contact. This information can surprisingly ease the learning of contact-rich robot manipulation skills, especially when the visual information alone is ambiguous or incomplete. However, the usage of audio data in robot manipulation has been constrained to teleoperated demonstrations collected by either attaching a microphone to the robot or object, which significantly limits its usage in robot learning pipelines. In this work, we introduce ManiWAV: an 'ear-in-hand' data collection device to collect in-the-wild human demonstrations with synchronous audio and visual feedback, and a corresponding policy interface to learn robot manipulation policy directly from the demonstrations. We demonstrate the capabilities of our system through four contact-rich manipulation tasks that require either passively sensing the contact events and modes, or actively sensing the object surface materials and states. In addition, we show that our system can generalize to unseen in-the-wild environments by learning from diverse in-the-wild human demonstrations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.19464v2-abstract-full').style.display = 'none'; document.getElementById('2406.19464v2-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">v1</span> submitted 27 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Conference on Robot Learning (CoRL) 2024; Project website: https://maniwav.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.18156">arXiv:2406.18156</a> <span> [<a href="https://arxiv.org/pdf/2406.18156">pdf</a>, <a href="https://arxiv.org/format/2406.18156">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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"> FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Qu%2C+L">Linping Qu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Tsui%2C+C">Chi-Ying Tsui</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="2406.18156v1-abstract-short" style="display: inline;"> Federated learning (FL) is a powerful machine learning paradigm which leverages the data as well as the computational resources of clients, while protecting clients' data privacy. However, the substantial model size and frequent aggregation between the server and clients result in significant communication overhead, making it challenging to deploy FL in resource-limited wireless networks. In this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18156v1-abstract-full').style.display = 'inline'; document.getElementById('2406.18156v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.18156v1-abstract-full" style="display: none;"> Federated learning (FL) is a powerful machine learning paradigm which leverages the data as well as the computational resources of clients, while protecting clients' data privacy. However, the substantial model size and frequent aggregation between the server and clients result in significant communication overhead, making it challenging to deploy FL in resource-limited wireless networks. In this work, we aim to mitigate the communication overhead by using quantization. Previous research on quantization has primarily focused on the uplink communication, employing either fixed-bit quantization or adaptive quantization methods. In this work, we introduce a holistic approach by joint uplink and downlink adaptive quantization to reduce the communication overhead. In particular, we optimize the learning convergence by determining the optimal uplink and downlink quantization bit-length, with a communication energy constraint. Theoretical analysis shows that the optimal quantization levels depend on the range of model gradients or weights. Based on this insight, we propose a decreasing-trend quantization for the uplink and an increasing-trend quantization for the downlink, which aligns with the change of the model parameters during the training process. Experimental results show that, the proposed joint uplink and downlink adaptive quantization strategy can save up to 66.7% energy compared with the existing schemes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.18156v1-abstract-full').style.display = 'none'; document.getElementById('2406.18156v1-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">This work has been submitted to the IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.16323">arXiv:2406.16323</a> <span> [<a href="https://arxiv.org/pdf/2406.16323">pdf</a>, <a href="https://arxiv.org/format/2406.16323">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"> Low-Complexity CSI Feedback for FDD Massive MIMO Systems via Learning to Optimize </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Ma%2C+Y">Yifan Ma</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2406.16323v1-abstract-short" style="display: inline;"> In frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems, the growing number of base station antennas leads to prohibitive feedback overhead for downlink channel state information (CSI). To address this challenge, state-of-the-art (SOTA) fully data-driven deep learning (DL)-based CSI feedback schemes have been proposed. However, the high computational complexity and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16323v1-abstract-full').style.display = 'inline'; document.getElementById('2406.16323v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.16323v1-abstract-full" style="display: none;"> In frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems, the growing number of base station antennas leads to prohibitive feedback overhead for downlink channel state information (CSI). To address this challenge, state-of-the-art (SOTA) fully data-driven deep learning (DL)-based CSI feedback schemes have been proposed. However, the high computational complexity and memory requirements of these methods hinder their practical deployment on resource-constrained devices like mobile phones. To solve the problem, we propose a model-driven DL-based CSI feedback approach by integrating the wisdom of compressive sensing and learning to optimize (L2O). Specifically, only a linear learnable projection is adopted at the encoder side to compress the CSI matrix, thereby significantly cutting down the user-side complexity and memory expenditure. On the other hand, the decoder incorporates two specially designed components, i.e., a learnable sparse transformation and an element-wise L2O reconstruction module. The former is developed to learn a sparse basis for CSI within the angular domain, which explores channel sparsity effectively. The latter shares the same long short term memory (LSTM) network across all elements of the optimization variable, eliminating the retraining cost when problem scale changes. Simulation results show that the proposed method achieves a comparable performance with the SOTA CSI feedback scheme but with much-reduced complexity, and enables multiple-rate feedback. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.16323v1-abstract-full').style.display = 'none'; document.getElementById('2406.16323v1-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 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 for publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.13165">arXiv:2406.13165</a> <span> [<a href="https://arxiv.org/pdf/2406.13165">pdf</a>, <a href="https://arxiv.org/format/2406.13165">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Robotics">cs.RO</span> </div> </div> <p class="title is-5 mathjax"> Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Jiang%2C+H">Haojun Jiang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Z">Zhenguo Sun</a>, <a href="/search/eess?searchtype=author&query=Jia%2C+N">Ning Jia</a>, <a href="/search/eess?searchtype=author&query=Li%2C+M">Meng Li</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yu Sun</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+S">Shaqi Luo</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shiji Song</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+G">Gao Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.13165v2-abstract-short" style="display: inline;"> Echocardiography is the only technique capable of real-time imaging of the heart and is vital for diagnosing the majority of cardiac diseases. However, there is a severe shortage of experienced cardiac sonographers, due to the heart's complex structure and significant operational challenges. To mitigate this situation, we present a Cardiac Copilot system capable of providing real-time probe moveme… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13165v2-abstract-full').style.display = 'inline'; document.getElementById('2406.13165v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.13165v2-abstract-full" style="display: none;"> Echocardiography is the only technique capable of real-time imaging of the heart and is vital for diagnosing the majority of cardiac diseases. However, there is a severe shortage of experienced cardiac sonographers, due to the heart's complex structure and significant operational challenges. To mitigate this situation, we present a Cardiac Copilot system capable of providing real-time probe movement guidance to assist less experienced sonographers in conducting freehand echocardiography. This system can enable non-experts, especially in primary departments and medically underserved areas, to perform cardiac ultrasound examinations, potentially improving global healthcare delivery. The core innovation lies in proposing a data-driven world model, named Cardiac Dreamer, for representing cardiac spatial structures. This world model can provide structure features of any cardiac planes around the current probe position in the latent space, serving as an precise navigation map for autonomous plane localization. We train our model with real-world ultrasound data and corresponding probe motion from 110 routine clinical scans with 151K sample pairs by three certified sonographers. Evaluations on three standard planes with 37K sample pairs demonstrate that the world model can reduce navigation errors by up to 33\% and exhibit more stable performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13165v2-abstract-full').style.display = 'none'; document.getElementById('2406.13165v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by MICCAI2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.09514">arXiv:2405.09514</a> <span> [<a href="https://arxiv.org/pdf/2405.09514">pdf</a>, <a href="https://arxiv.org/format/2405.09514">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <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"> Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+H">Hongru Li</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+J">Jiawei Shao</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2405.09514v1-abstract-short" style="display: inline;"> Task-oriented communication aims to extract and transmit task-relevant information to significantly reduce the communication overhead and transmission latency. However, the unpredictable distribution shifts between training and test data, including domain shift and semantic shift, can dramatically undermine the system performance. In order to tackle these challenges, it is crucial to ensure that t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09514v1-abstract-full').style.display = 'inline'; document.getElementById('2405.09514v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.09514v1-abstract-full" style="display: none;"> Task-oriented communication aims to extract and transmit task-relevant information to significantly reduce the communication overhead and transmission latency. However, the unpredictable distribution shifts between training and test data, including domain shift and semantic shift, can dramatically undermine the system performance. In order to tackle these challenges, it is crucial to ensure that the encoded features can generalize to domain-shifted data and detect semanticshifted data, while remaining compact for transmission. In this paper, we propose a novel approach based on the information bottleneck (IB) principle and invariant risk minimization (IRM) framework. The proposed method aims to extract compact and informative features that possess high capability for effective domain-shift generalization and accurate semantic-shift detection without any knowledge of the test data during training. Specifically, we propose an invariant feature encoding approach based on the IB principle and IRM framework for domainshift generalization, which aims to find the causal relationship between the input data and task result by minimizing the complexity and domain dependence of the encoded feature. Furthermore, we enhance the task-oriented communication with the label-dependent feature encoding approach for semanticshift detection which achieves joint gains in IB optimization and detection performance. To avoid the intractable computation of the IB-based objective, we leverage variational approximation to derive a tractable upper bound for optimization. Extensive simulation results on image classification tasks demonstrate that the proposed scheme outperforms state-of-the-art approaches and achieves a better rate-distortion tradeoff. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.09514v1-abstract-full').style.display = 'none'; document.getElementById('2405.09514v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <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, 8 figures, submitted to IEEE for potential publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.07218">arXiv:2405.07218</a> <span> [<a href="https://arxiv.org/pdf/2405.07218">pdf</a>, <a href="https://arxiv.org/format/2405.07218">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> </div> </div> <p class="title is-5 mathjax"> Chained Flexible Capsule Endoscope: Unraveling the Conundrum of Size Limitations and Functional Integration for Gastrointestinal Transitivity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yuan%2C+S">Sishen Yuan</a>, <a href="/search/eess?searchtype=author&query=Li%2C+G">Guang Li</a>, <a href="/search/eess?searchtype=author&query=Liang%2C+B">Baijia Liang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+L">Lailu Li</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+Q">Qingzhuo Zheng</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shuang Song</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Z">Zhen Li</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+H">Hongliang Ren</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="2405.07218v1-abstract-short" style="display: inline;"> Capsule endoscopes, predominantly serving diagnostic functions, provide lucid internal imagery but are devoid of surgical or therapeutic capabilities. Consequently, despite lesion detection, physicians frequently resort to traditional endoscopic or open surgical procedures for treatment, resulting in more complex, potentially risky interventions. To surmount these limitations, this study introduce… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.07218v1-abstract-full').style.display = 'inline'; document.getElementById('2405.07218v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.07218v1-abstract-full" style="display: none;"> Capsule endoscopes, predominantly serving diagnostic functions, provide lucid internal imagery but are devoid of surgical or therapeutic capabilities. Consequently, despite lesion detection, physicians frequently resort to traditional endoscopic or open surgical procedures for treatment, resulting in more complex, potentially risky interventions. To surmount these limitations, this study introduces a chained flexible capsule endoscope (FCE) design concept, specifically conceived to navigate the inherent volume constraints of capsule endoscopes whilst augmenting their therapeutic functionalities. The FCE's distinctive flexibility originates from a conventional rotating joint design and the incision pattern in the flexible material. In vitro experiments validated the passive navigation ability of the FCE in rugged intestinal tracts. Further, the FCE demonstrates consistent reptile-like peristalsis under the influence of an external magnetic field, and possesses the capability for film expansion and disintegration under high-frequency electromagnetic stimulation. These findings illuminate a promising path toward amplifying the therapeutic capacities of capsule endoscopes without necessitating a size compromise. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.07218v1-abstract-full').style.display = 'none'; document.getElementById('2405.07218v1-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 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/2404.16223">arXiv:2404.16223</a> <span> [<a href="https://arxiv.org/pdf/2404.16223">pdf</a>, <a href="https://arxiv.org/format/2404.16223">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"> Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Conde%2C+M+V">Marcos V. Conde</a>, <a href="/search/eess?searchtype=author&query=Vasluianu%2C+F">Florin-Alexandru Vasluianu</a>, <a href="/search/eess?searchtype=author&query=Timofte%2C+R">Radu Timofte</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jianxing Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jia Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+F">Fan Wang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiaopeng Li</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Z">Zikun Liu</a>, <a href="/search/eess?searchtype=author&query=Park%2C+H">Hyunhee Park</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sejun Song</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+C">Changho Kim</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+Z">Zhijuan Huang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+H">Hongyuan Yu</a>, <a href="/search/eess?searchtype=author&query=Wan%2C+C">Cheng Wan</a>, <a href="/search/eess?searchtype=author&query=Xiang%2C+W">Wending Xiang</a>, <a href="/search/eess?searchtype=author&query=Lin%2C+J">Jiamin Lin</a>, <a href="/search/eess?searchtype=author&query=Zhong%2C+H">Hang Zhong</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Q">Qiaosong Zhang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Y">Yue Sun</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+X">Xuanwu Yin</a>, <a href="/search/eess?searchtype=author&query=Zuo%2C+K">Kunlong Zuo</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+S">Senyan Xu</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+S">Siyuan Jiang</a>, <a href="/search/eess?searchtype=author&query=Sun%2C+Z">Zhijing Sun</a>, <a href="/search/eess?searchtype=author&query=Zhu%2C+J">Jiaying Zhu</a> , et al. (10 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.16223v1-abstract-short" style="display: inline;"> This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. Th goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as nois… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.16223v1-abstract-full').style.display = 'inline'; document.getElementById('2404.16223v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.16223v1-abstract-full" style="display: none;"> This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. Th goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. The performance of the top-5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in RAW Image Super-Resolution. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.16223v1-abstract-full').style.display = 'none'; document.getElementById('2404.16223v1-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">CVPR 2024 - NTIRE Workshop</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.11889">arXiv:2404.11889</a> <span> [<a href="https://arxiv.org/pdf/2404.11889">pdf</a>, <a href="https://arxiv.org/format/2404.11889">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3664647.3681154">10.1145/3664647.3681154 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Multi-view X-ray Image Synthesis with Multiple Domain Disentanglement from CT Scans </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Tan%2C+L">Lixing Tan</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shuang Song</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+K">Kangneng Zhou</a>, <a href="/search/eess?searchtype=author&query=Duan%2C+C">Chengbo Duan</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+L">Lanying Wang</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+H">Huayang Ren</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+L">Linlin Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+W">Wei Zhang</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+R">Ruoxiu Xiao</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="2404.11889v2-abstract-short" style="display: inline;"> X-ray images play a vital role in the intraoperative processes due to their high resolution and fast imaging speed and greatly promote the subsequent segmentation, registration and reconstruction. However, over-dosed X-rays superimpose potential risks to human health to some extent. Data-driven algorithms from volume scans to X-ray images are restricted by the scarcity of paired X-ray and volume d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11889v2-abstract-full').style.display = 'inline'; document.getElementById('2404.11889v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.11889v2-abstract-full" style="display: none;"> X-ray images play a vital role in the intraoperative processes due to their high resolution and fast imaging speed and greatly promote the subsequent segmentation, registration and reconstruction. However, over-dosed X-rays superimpose potential risks to human health to some extent. Data-driven algorithms from volume scans to X-ray images are restricted by the scarcity of paired X-ray and volume data. Existing methods are mainly realized by modelling the whole X-ray imaging procedure. In this study, we propose a learning-based approach termed CT2X-GAN to synthesize the X-ray images in an end-to-end manner using the content and style disentanglement from three different image domains. Our method decouples the anatomical structure information from CT scans and style information from unpaired real X-ray images/ digital reconstructed radiography (DRR) images via a series of decoupling encoders. Additionally, we introduce a novel consistency regularization term to improve the stylistic resemblance between synthesized X-ray images and real X-ray images. Meanwhile, we also impose a supervised process by computing the similarity of computed real DRR and synthesized DRR images. We further develop a pose attention module to fully strengthen the comprehensive information in the decoupled content code from CT scans, facilitating high-quality multi-view image synthesis in the lower 2D space. Extensive experiments were conducted on the publicly available CTSpine1K dataset and achieved 97.8350, 0.0842 and 3.0938 in terms of FID, KID and defined user-scored X-ray similarity, respectively. In comparison with 3D-aware methods ($蟺$-GAN, EG3D), CT2X-GAN is superior in improving the synthesis quality and realistic to the real X-ray images. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11889v2-abstract-full').style.display = 'none'; document.getElementById('2404.11889v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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, 10 figures, ACM MM2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.00309">arXiv:2404.00309</a> <span> [<a href="https://arxiv.org/pdf/2404.00309">pdf</a>, <a href="https://arxiv.org/format/2404.00309">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"> Model-Driven Deep Learning for Distributed Detection with Binary Quantization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Guo%2C+W">Wei Guo</a>, <a href="/search/eess?searchtype=author&query=He%2C+M">Meng He</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+C">Chuan Huang</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2404.00309v1-abstract-short" style="display: inline;"> Within the realm of rapidly advancing wireless sensor networks (WSNs), distributed detection assumes a significant role in various practical applications. However, critical challenge lies in maintaining robust detection performance while operating within the constraints of limited bandwidth and energy resources. This paper introduces a novel approach that combines model-driven deep learning (DL) w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00309v1-abstract-full').style.display = 'inline'; document.getElementById('2404.00309v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.00309v1-abstract-full" style="display: none;"> Within the realm of rapidly advancing wireless sensor networks (WSNs), distributed detection assumes a significant role in various practical applications. However, critical challenge lies in maintaining robust detection performance while operating within the constraints of limited bandwidth and energy resources. This paper introduces a novel approach that combines model-driven deep learning (DL) with binary quantization to strike a balance between communication overhead and detection performance in WSNs. We begin by establishing the lower bound of detection error probability for distributed detection using the maximum a posteriori (MAP) criterion. Furthermore, we prove the global optimality of employing identical local quantizers across sensors, thereby maximizing the corresponding Chernoff information. Subsequently, the paper derives the minimum MAP detection error probability (MAPDEP) by inplementing identical binary probabilistic quantizers across the sensors. Moreover, the paper establishes the equivalence between utilizing all quantized data and their average as input to the detector at the fusion center (FC). In particular, we derive the Kullback-Leibler (KL) divergence, which measures the difference between the true posterior probability and output of the proposed detector. Leveraging the MAPDEP and KL divergence as loss functions, the paper proposes model-driven DL method to separately train the probability controller module in the quantizer and the detector module at the FC. Numerical results validate the convergence and effectiveness of the proposed method, which achieves near-optimal performance with reduced complexity for Gaussian hypothesis testing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00309v1-abstract-full').style.display = 'none'; document.getElementById('2404.00309v1-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 March, 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/2403.06069">arXiv:2403.06069</a> <span> [<a href="https://arxiv.org/pdf/2403.06069">pdf</a>, <a href="https://arxiv.org/format/2403.06069">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Implicit Image-to-Image Schrodinger Bridge for Image Restoration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+Y">Yuang Wang</a>, <a href="/search/eess?searchtype=author&query=Yoon%2C+S">Siyeop Yoon</a>, <a href="/search/eess?searchtype=author&query=Jin%2C+P">Pengfei Jin</a>, <a href="/search/eess?searchtype=author&query=Tivnan%2C+M">Matthew Tivnan</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sifan Song</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhennong Chen</a>, <a href="/search/eess?searchtype=author&query=Hu%2C+R">Rui Hu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+L">Li Zhang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Q">Quanzheng Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+Z">Zhiqiang Chen</a>, <a href="/search/eess?searchtype=author&query=Wu%2C+D">Dufan Wu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.06069v2-abstract-short" style="display: inline;"> Diffusion-based models are widely recognized for their effectiveness in image restoration tasks; however, their iterative denoising process, which begins from Gaussian noise, often results in slow inference speeds. The Image-to-Image Schr枚dinger Bridge (I$^2$SB) presents a promising alternative by starting the generative process from corrupted images and leveraging training techniques from score-b… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06069v2-abstract-full').style.display = 'inline'; document.getElementById('2403.06069v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.06069v2-abstract-full" style="display: none;"> Diffusion-based models are widely recognized for their effectiveness in image restoration tasks; however, their iterative denoising process, which begins from Gaussian noise, often results in slow inference speeds. The Image-to-Image Schr枚dinger Bridge (I$^2$SB) presents a promising alternative by starting the generative process from corrupted images and leveraging training techniques from score-based diffusion models. In this paper, we introduce the Implicit Image-to-Image Schr枚dinger Bridge (I$^3$SB) to further accelerate the generative process of I$^2$SB. I$^3$SB reconfigures the generative process into a non-Markovian framework by incorporating the initial corrupted image into each step, while ensuring that the marginal distribution aligns with that of I$^2$SB. This allows for the direct use of the pretrained network from I$^2$SB. Extensive experiments on natural images, human face images, and medical images validate the acceleration benefits of I$^3$SB. Compared to I$^2$SB, I$^3$SB achieves the same perceptual quality with fewer generative steps, while maintaining equal or improved fidelity to the ground truth. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.06069v2-abstract-full').style.display = 'none'; document.getElementById('2403.06069v2-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 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">23 pages, 8 figures, submitted to Pattern Recognition</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.14213">arXiv:2402.14213</a> <span> [<a href="https://arxiv.org/pdf/2402.14213">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</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="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Contrastive Learning of Shared Spatiotemporal EEG Representations Across Individuals for Naturalistic Neuroscience </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Shen%2C+X">Xinke Shen</a>, <a href="/search/eess?searchtype=author&query=Tao%2C+L">Lingyi Tao</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+X">Xuyang Chen</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sen Song</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+Q">Quanying Liu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+D">Dan 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="2402.14213v2-abstract-short" style="display: inline;"> Neural representations induced by naturalistic stimuli offer insights into how humans respond to stimuli in daily life. Understanding neural mechanisms underlying naturalistic stimuli processing hinges on the precise identification and extraction of the shared neural patterns that are consistently present across individuals. Targeting the Electroencephalogram (EEG) technique, known for its rich sp… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14213v2-abstract-full').style.display = 'inline'; document.getElementById('2402.14213v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.14213v2-abstract-full" style="display: none;"> Neural representations induced by naturalistic stimuli offer insights into how humans respond to stimuli in daily life. Understanding neural mechanisms underlying naturalistic stimuli processing hinges on the precise identification and extraction of the shared neural patterns that are consistently present across individuals. Targeting the Electroencephalogram (EEG) technique, known for its rich spatial and temporal information, this study presents a framework for Contrastive Learning of Shared SpatioTemporal EEG Representations across individuals (CL-SSTER). CL-SSTER utilizes contrastive learning to maximize the similarity of EEG representations across individuals for identical stimuli, contrasting with those for varied stimuli. The network employed spatial and temporal convolutions to simultaneously learn the spatial and temporal patterns inherent in EEG. The versatility of CL-SSTER was demonstrated on three EEG datasets, including a synthetic dataset, a natural speech comprehension EEG dataset, and an emotional video watching EEG dataset. CL-SSTER attained the highest inter-subject correlation (ISC) values compared to the state-of-the-art ISC methods. The latent representations generated by CL-SSTER exhibited reliable spatiotemporal EEG patterns, which can be explained by properties of the naturalistic stimuli. CL-SSTER serves as an interpretable and scalable framework for the identification of inter-subject shared neural representations in naturalistic neuroscience. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14213v2-abstract-full').style.display = 'none'; document.getElementById('2402.14213v2-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 21 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">54 pages, 17 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/2402.10071">arXiv:2402.10071</a> <span> [<a href="https://arxiv.org/pdf/2402.10071">pdf</a>, <a href="https://arxiv.org/format/2402.10071">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Approximate Message Passing-Enhanced Graph Neural Network for OTFS Data Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhuang%2C+W">Wenhao Zhuang</a>, <a href="/search/eess?searchtype=author&query=Mao%2C+Y">Yuyi Mao</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Ge%2C+Y">Yao Ge</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+Z">Zhi Ding</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="2402.10071v2-abstract-short" style="display: inline;"> Orthogonal time frequency space (OTFS) modulation has emerged as a promising solution to support high-mobility wireless communications, for which, cost-effective data detectors are critical. Although graph neural network (GNN)-based data detectors can achieve decent detection accuracy at reasonable computational cost, they fail to best harness prior information of transmitted data. To further mini… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.10071v2-abstract-full').style.display = 'inline'; document.getElementById('2402.10071v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.10071v2-abstract-full" style="display: none;"> Orthogonal time frequency space (OTFS) modulation has emerged as a promising solution to support high-mobility wireless communications, for which, cost-effective data detectors are critical. Although graph neural network (GNN)-based data detectors can achieve decent detection accuracy at reasonable computational cost, they fail to best harness prior information of transmitted data. To further minimize the data detection error of OTFS systems, this letter develops an AMP-GNN-based detector, leveraging the approximate message passing (AMP) algorithm to iteratively improve the symbol estimates of a GNN. Given the inter-Doppler interference (IDI) symbols incur substantial computational overhead to the constructed GNN, learning-based IDI approximation is implemented to sustain low detection complexity. Simulation results demonstrate a remarkable bit error rate (BER) performance achieved by the proposed AMP-GNN-based detector compared to existing baselines. Meanwhile, the proposed IDI approximation scheme avoids a large amount of computations with negligible BER degradation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.10071v2-abstract-full').style.display = 'none'; document.getElementById('2402.10071v2-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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">8 pages, 7 figures, and 3 tables. Part of this article was submitted to IEEE for possible publication</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.09976">arXiv:2402.09976</a> <span> [<a href="https://arxiv.org/pdf/2402.09976">pdf</a>, <a href="https://arxiv.org/ps/2402.09976">ps</a>, <a href="https://arxiv.org/format/2402.09976">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"> Sensing-assisted Robust SWIPT for Mobile Energy Harvesting Receivers in Networked ISAC Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yiming Xu</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+D">Dongfang Xu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</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="2402.09976v2-abstract-short" style="display: inline;"> Simultaneous wireless information and power transfer (SWIPT) has been proposed to offer communication services and transfer power to the energy harvesting receiver (EHR) concurrently. However, existing works mainly focused on static EHRs, without considering the location uncertainty caused by the movement of EHRs and location estimation errors. To tackle this issue, this paper considers the sensin… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09976v2-abstract-full').style.display = 'inline'; document.getElementById('2402.09976v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.09976v2-abstract-full" style="display: none;"> Simultaneous wireless information and power transfer (SWIPT) has been proposed to offer communication services and transfer power to the energy harvesting receiver (EHR) concurrently. However, existing works mainly focused on static EHRs, without considering the location uncertainty caused by the movement of EHRs and location estimation errors. To tackle this issue, this paper considers the sensing-assisted SWIPT design in a networked integrated sensing and communication (ISAC) system in the presence of location uncertainty. A two-phase robust design is proposed to reduce the location uncertainty and improve the power transfer efficiency. In particular, each time frame is divided into two phases, i.e., sensing and WPT phases, via time-splitting. The sensing phase performs collaborative sensing to localize the EHR, whose results are then utilized in the WPT phase for efficient WPT. To minimize the power consumption with given communication and power transfer requirements, a two-layer optimization framework is proposed to jointly optimize the time-splitting ratio, coordinated beamforming policy, and sensing node selection. Simulation results validate the effectiveness of the proposed design and demonstrate the existence of an optimal time-splitting ratio for given location uncertainty. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09976v2-abstract-full').style.display = 'none'; document.getElementById('2402.09976v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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/2402.09974">arXiv:2402.09974</a> <span> [<a href="https://arxiv.org/pdf/2402.09974">pdf</a>, <a href="https://arxiv.org/ps/2402.09974">ps</a>, <a href="https://arxiv.org/format/2402.09974">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"> Interference Mitigation for Network-Level ISAC: An Optimization Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+D">Dongfang Xu</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Y">Yiming Xu</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+X">Xin Zhang</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xianghao Yu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Schober%2C+R">Robert Schober</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="2402.09974v1-abstract-short" style="display: inline;"> Future wireless networks are envisioned to simultaneously provide high data-rate communication and ubiquitous environment-aware services for numerous users. One promising approach to meet this demand is to employ network-level integrated sensing and communications (ISAC) by jointly designing the signal processing and resource allocation over the entire network. However, to unleash the full potenti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09974v1-abstract-full').style.display = 'inline'; document.getElementById('2402.09974v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.09974v1-abstract-full" style="display: none;"> Future wireless networks are envisioned to simultaneously provide high data-rate communication and ubiquitous environment-aware services for numerous users. One promising approach to meet this demand is to employ network-level integrated sensing and communications (ISAC) by jointly designing the signal processing and resource allocation over the entire network. However, to unleash the full potential of network-level ISAC, some critical challenges must be tackled. Among them, interference management is one of the most significant ones. In this article, we build up a bridge between interference mitigation techniques and the corresponding optimization methods, which facilitates efficient interference mitigation in network-level ISAC systems. In particular, we first identify several types of interference in network-level ISAC systems, including self-interference, mutual interference, crosstalk, clutter, and multiuser interference. Then, we present several promising techniques that can be utilized to suppress specific types of interference. For each type of interference, we discuss the corresponding problem formulation and identify the associated optimization methods. Moreover, to illustrate the effectiveness of the proposed interference mitigation techniques, two concrete network-level ISAC systems, namely coordinated cellular network-based and distributed antenna-based ISAC systems, are investigated from interference management perspective. Experiment results indicate that it is beneficial to collaboratively employ different interference mitigation techniques and leverage the network structure to achieve the full potential of network-level ISAC. Finally, we highlight several promising future research directions for the design of ISAC systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09974v1-abstract-full').style.display = 'none'; document.getElementById('2402.09974v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 February, 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">7 pages, 6 figures, and the relevant simulation code can be found at https://dongfang-xu.github.io/homepage/code/Two_cases.zip</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.03919">arXiv:2402.03919</a> <span> [<a href="https://arxiv.org/pdf/2402.03919">pdf</a>, <a href="https://arxiv.org/format/2402.03919">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Sensing Mutual Information with Random Signals in Gaussian Channels: Bridging Sensing and Communication Metrics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+F">Fan Liu</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+J">Jiajin Luo</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</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="2402.03919v1-abstract-short" style="display: inline;"> Sensing performance is typically evaluated by classical radar metrics, such as Cramer-Rao bound and signal-to-clutter-plus-noise ratio. The recent development of the integrated sensing and communication (ISAC) framework motivated the efforts to unify the performance metric for sensing and communication, where mutual information (MI) was proposed as a sensing performance metric with deterministic s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03919v1-abstract-full').style.display = 'inline'; document.getElementById('2402.03919v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.03919v1-abstract-full" style="display: none;"> Sensing performance is typically evaluated by classical radar metrics, such as Cramer-Rao bound and signal-to-clutter-plus-noise ratio. The recent development of the integrated sensing and communication (ISAC) framework motivated the efforts to unify the performance metric for sensing and communication, where mutual information (MI) was proposed as a sensing performance metric with deterministic signals. However, the need of communication in ISAC systems necessitates the transmission of random signals for sensing applications, whereas an explicit evaluation for the sensing mutual information (SMI) with random signals is not yet available in the literature. This paper aims to fill the research gap and investigate the unification of sensing and communication performance metrics. For that purpose, we first derive the explicit expression for the SMI with random signals utilizing random matrix theory. On top of that, we further build up the connections between SMI and traditional sensing metrics, such as ergodic minimum mean square error (EMMSE), ergodic linear minimum mean square error (ELMMSE), and ergodic Bayesian Cram茅r-Rao bound (EBCRB). Such connections open up the opportunity to unify sensing and communication performance metrics, which facilitates the analysis and design for ISAC systems. Finally, SMI is utilized to optimize the precoder for both sensing-only and ISAC applications. Simulation results validate the accuracy of the theoretical results and the effectiveness of the proposed precoding designs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03919v1-abstract-full').style.display = 'none'; document.getElementById('2402.03919v1-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 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">arXiv admin note: substantial text overlap with arXiv:2311.07081</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.01467">arXiv:2402.01467</a> <span> [<a href="https://arxiv.org/pdf/2402.01467">pdf</a>, <a href="https://arxiv.org/format/2402.01467">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neural and Evolutionary Computing">cs.NE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Brain-Like Replay Naturally Emerges in Reinforcement Learning Agents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Wang%2C+J">Jiyi Wang</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+L">Likai Tang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+H">Huimiao Chen</a>, <a href="/search/eess?searchtype=author&query=Mattar%2C+M+G">Marcelo G Mattar</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sen Song</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="2402.01467v2-abstract-short" style="display: inline;"> Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular reinforcement learning model that could generate replay. We prove that replay generated in this way helps complete the task. We also analyze the information contained in t… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01467v2-abstract-full').style.display = 'inline'; document.getElementById('2402.01467v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01467v2-abstract-full" style="display: none;"> Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular reinforcement learning model that could generate replay. We prove that replay generated in this way helps complete the task. We also analyze the information contained in the representation and provide a mechanism for how replay makes a difference. Our design avoids complex assumptions and enables replay to emerge naturally within a task-optimized paradigm. Our model also reproduces key phenomena observed in biological agents. This research explores the structural biases in modular ANN to generate replay and its potential utility in developing efficient RL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01467v2-abstract-full').style.display = 'none'; document.getElementById('2402.01467v2-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">v1</span> submitted 2 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/2402.01271">arXiv:2402.01271</a> <span> [<a href="https://arxiv.org/pdf/2402.01271">pdf</a>, <a href="https://arxiv.org/format/2402.01271">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xu%2C+L">Linping Xu</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+J">Jiawei Jiang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+D">Dejun Zhang</a>, <a href="/search/eess?searchtype=author&query=Xia%2C+X">Xianjun Xia</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+L">Li Chen</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+Y">Yijian Xiao</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+P">Piao Ding</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenyi Song</a>, <a href="/search/eess?searchtype=author&query=Yin%2C+S">Sixing Yin</a>, <a href="/search/eess?searchtype=author&query=Sohel%2C+F">Ferdous Sohel</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="2402.01271v1-abstract-short" style="display: inline;"> Recently, neural networks have proven to be effective in performing speech coding task at low bitrates. However, under-utilization of intra-frame correlations and the error of quantizer specifically degrade the reconstructed audio quality. To improve the coding quality, we present an end-to-end neural speech codec, namely CBRC (Convolutional and Bidirectional Recurrent neural Codec). An interleave… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01271v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01271v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01271v1-abstract-full" style="display: none;"> Recently, neural networks have proven to be effective in performing speech coding task at low bitrates. However, under-utilization of intra-frame correlations and the error of quantizer specifically degrade the reconstructed audio quality. To improve the coding quality, we present an end-to-end neural speech codec, namely CBRC (Convolutional and Bidirectional Recurrent neural Codec). An interleaved structure using 1D-CNN and Intra-BRNN is designed to exploit the intra-frame correlations more efficiently. Furthermore, Group-wise and Beam-search Residual Vector Quantizer (GB-RVQ) is used to reduce the quantization noise. CBRC encodes audio every 20ms with no additional latency, which is suitable for real-time communication. Experimental results demonstrate the superiority of the proposed codec when comparing CBRC at 3kbps with Opus at 12kbps. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01271v1-abstract-full').style.display = 'none'; document.getElementById('2402.01271v1-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, 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">INTERSPEECH 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.15321">arXiv:2401.15321</a> <span> [<a href="https://arxiv.org/pdf/2401.15321">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</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/10.1016/j.apenergy.2024.122736">10.1016/j.apenergy.2024.122736 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Localization of Dummy Data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Qu%2C+Z">Zhaoyang Qu</a>, <a href="/search/eess?searchtype=author&query=Dong%2C+Y">Yunchang Dong</a>, <a href="/search/eess?searchtype=author&query=Li%2C+Y">Yang Li</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Siqi Song</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+T">Tao Jiang</a>, <a href="/search/eess?searchtype=author&query=Li%2C+M">Min Li</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Q">Qiming Wang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+L">Lei Wang</a>, <a href="/search/eess?searchtype=author&query=Bo%2C+X">Xiaoyong Bo</a>, <a href="/search/eess?searchtype=author&query=Zang%2C+J">Jiye Zang</a>, <a href="/search/eess?searchtype=author&query=Xu%2C+Q">Qi Xu</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="2401.15321v1-abstract-short" style="display: inline;"> The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial separation between the injected malicious data and legitimate data, rendering their precise detection challenging using conventional distance-based methods. Furthermore, existing researc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.15321v1-abstract-full').style.display = 'inline'; document.getElementById('2401.15321v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.15321v1-abstract-full" style="display: none;"> The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial separation between the injected malicious data and legitimate data, rendering their precise detection challenging using conventional distance-based methods. Furthermore, existing research predominantly focuses on various machine learning techniques, often analyzing the temporal data sequences post-attack or relying solely on Euclidean spatial characteristics. Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization. To address this issue, this study takes a comprehensive approach. Initially, it examines the underlying principles of these new DDIAs on power systems. Here, an intricate mathematical model of the DDIA is designed, accounting for incomplete topological knowledge and alternating current (AC) state estimation from an attacker's perspective. Subsequently, by integrating a priori knowledge of grid topology and considering the temporal correlations within measurement data and the topology-dependent attributes of the power grid, this study introduces temporal and spatial attention matrices. These matrices adaptively capture the spatio-temporal correlations within the attacks. Leveraging gated stacked causal convolution and graph wavelet sparse convolution, the study jointly extracts spatio-temporal DDIA features. Finally, the research proposes a DDIA localization method based on spatio-temporal graph neural networks. The accuracy and effectiveness of the DDIA model are rigorously demonstrated through comprehensive analytical cases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.15321v1-abstract-full').style.display = 'none'; document.getElementById('2401.15321v1-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">Accepted by Applied Energy</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Applied Energy 360 (2024) 122736 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.05915">arXiv:2401.05915</a> <span> [<a href="https://arxiv.org/pdf/2401.05915">pdf</a>, <a href="https://arxiv.org/format/2401.05915">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> </div> </div> <p class="title is-5 mathjax"> Neural Implicit Surface Reconstruction of Freehand 3D Ultrasound Volume with Geometric Constraints </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Chen%2C+H">Hongbo Chen</a>, <a href="/search/eess?searchtype=author&query=Kumaralingam%2C+L">Logiraj Kumaralingam</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+S">Shuhang Zhang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Sheng Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+F">Fayi Zhang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+H">Haibin Zhang</a>, <a href="/search/eess?searchtype=author&query=Pham%2C+T">Thanh-Tu Pham</a>, <a href="/search/eess?searchtype=author&query=Lou%2C+E+H+M">Edmond H. M. Lou</a>, <a href="/search/eess?searchtype=author&query=Punithakumar%2C+K">Kumaradevan Punithakumar</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yuyao Zhang</a>, <a href="/search/eess?searchtype=author&query=Le%2C+L+H">Lawrence H. Le</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+R">Rui 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="2401.05915v4-abstract-short" style="display: inline;"> Three-dimensional (3D) freehand ultrasound (US) is a widely used imaging modality that allows non-invasive imaging of medical anatomy without radiation exposure. Surface reconstruction of US volume is vital to acquire the accurate anatomical structures needed for modeling, registration, and visualization. However, traditional methods cannot produce a high-quality surface due to image noise. Despit… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05915v4-abstract-full').style.display = 'inline'; document.getElementById('2401.05915v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.05915v4-abstract-full" style="display: none;"> Three-dimensional (3D) freehand ultrasound (US) is a widely used imaging modality that allows non-invasive imaging of medical anatomy without radiation exposure. Surface reconstruction of US volume is vital to acquire the accurate anatomical structures needed for modeling, registration, and visualization. However, traditional methods cannot produce a high-quality surface due to image noise. Despite improvements in smoothness, continuity, and resolution from deep learning approaches, research on surface reconstruction in freehand 3D US is still limited. This study introduces FUNSR, a self-supervised neural implicit surface reconstruction method to learn signed distance functions (SDFs) from US volumes. In particular, FUNSR iteratively learns the SDFs by moving the 3D queries sampled around volumetric point clouds to approximate the surface, guided by two novel geometric constraints: sign consistency constraint and onsurface constraint with adversarial learning. Our approach has been thoroughly evaluated across four datasets to demonstrate its adaptability to various anatomical structures, including a hip phantom dataset, two vascular datasets and one publicly available prostate dataset. We also show that smooth and continuous representations greatly enhance the visual appearance of US data. Furthermore, we highlight the potential of our method to improve segmentation performance, and its robustness to noise distribution and motion perturbation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05915v4-abstract-full').style.display = 'none'; document.getElementById('2401.05915v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 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">Preprint</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.13683">arXiv:2312.13683</a> <span> [<a href="https://arxiv.org/pdf/2312.13683">pdf</a>, <a href="https://arxiv.org/format/2312.13683">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Joint Channel Estimation and Cooperative Localization for Near-Field Ultra-Massive MIMO </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Cao%2C+R">Ruoxiao Cao</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xianghao Yu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Huang%2C+K">Kaibin Huang</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Gong%2C+Y">Yi Gong</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2312.13683v1-abstract-short" style="display: inline;"> The next-generation (6G) wireless networks are expected to provide not only seamless and high data-rate communications, but also ubiquitous sensing services. By providing vast spatial degrees of freedom (DoFs), ultra-massive multiple-input multiple-output (UM-MIMO) technology is a key enabler for both sensing and communications in 6G. However, the adoption of UM-MIMO leads to a shift from the far… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13683v1-abstract-full').style.display = 'inline'; document.getElementById('2312.13683v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.13683v1-abstract-full" style="display: none;"> The next-generation (6G) wireless networks are expected to provide not only seamless and high data-rate communications, but also ubiquitous sensing services. By providing vast spatial degrees of freedom (DoFs), ultra-massive multiple-input multiple-output (UM-MIMO) technology is a key enabler for both sensing and communications in 6G. However, the adoption of UM-MIMO leads to a shift from the far field to the near field in terms of the electromagnetic propagation, which poses novel challenges in system design. Specifically, near-field effects introduce highly non-linear spherical wave models that render existing designs based on plane wave assumptions ineffective. In this paper, we focus on two crucial tasks in sensing and communications, respectively, i.e., localization and channel estimation, and investigate their joint design by exploring the near-field propagation characteristics, achieving mutual benefits between two tasks. In addition, multiple base stations (BSs) are leveraged to collaboratively facilitate a cooperative localization framework. To address the joint channel estimation and cooperative localization problem for near-field UM-MIMO systems, we propose a variational Newtonized near-field channel estimation (VNNCE) algorithm and a Gaussian fusion cooperative localization (GFCL) algorithm. The VNNCE algorithm exploits the spatial DoFs provided by the near-field channel to obtain position-related soft information, while the GFCL algorithm fuses this soft information to achieve more accurate localization. Additionally, we introduce a joint architecture that seamlessly integrates channel estimation and cooperative localization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.13683v1-abstract-full').style.display = 'none'; document.getElementById('2312.13683v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Submit to JSAC</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.10438">arXiv:2312.10438</a> <span> [<a href="https://arxiv.org/pdf/2312.10438">pdf</a>, <a href="https://arxiv.org/format/2312.10438">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> <div 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/JSTSP.2024.3414137">10.1109/JSTSP.2024.3414137 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Bayes-Optimal Unsupervised Learning for Channel Estimation in Near-Field Holographic MIMO </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+W">Wentao Yu</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xianghao Yu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Murch%2C+R">Ross Murch</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2312.10438v2-abstract-short" style="display: inline;"> Holographic MIMO (HMIMO) is being increasingly recognized as a key enabling technology for 6G wireless systems through the deployment of an extremely large number of antennas within a compact space to fully exploit the potentials of the electromagnetic (EM) channel. Nevertheless, the benefits of HMIMO systems cannot be fully unleashed without an efficient means to estimate the high-dimensional cha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.10438v2-abstract-full').style.display = 'inline'; document.getElementById('2312.10438v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.10438v2-abstract-full" style="display: none;"> Holographic MIMO (HMIMO) is being increasingly recognized as a key enabling technology for 6G wireless systems through the deployment of an extremely large number of antennas within a compact space to fully exploit the potentials of the electromagnetic (EM) channel. Nevertheless, the benefits of HMIMO systems cannot be fully unleashed without an efficient means to estimate the high-dimensional channel, whose distribution becomes increasingly complicated due to the accessibility of the near-field region. In this paper, we address the fundamental challenge of designing a low-complexity Bayes-optimal channel estimator in near-field HMIMO systems operating in unknown EM environments. The core idea is to estimate the HMIMO channels solely based on the Stein's score function of the received pilot signals and an estimated noise level, without relying on priors or supervision that is not feasible in practical deployment. A neural network is trained with the unsupervised denoising score matching objective to learn the parameterized score function. Meanwhile, a principal component analysis (PCA)-based algorithm is proposed to estimate the noise level leveraging the low-rank near-field spatial correlation. Building upon these techniques, we develop a Bayes-optimal score-based channel estimator for fully-digital HMIMO transceivers in a closed form. The optimal score-based estimator is also extended to hybrid analog-digital HMIMO systems by incorporating it into a low-complexity message passing algorithm. The (quasi-) Bayes-optimality of the proposed estimators is validated both in theory and by extensive simulation results. In addition to optimality, it is shown that our proposal is robust to various mismatches and can quickly adapt to dynamic EM environments in an online manner thanks to its unsupervised nature, demonstrating its potential in real-world deployment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.10438v2-abstract-full').style.display = 'none'; document.getElementById('2312.10438v2-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">16 pages, 7 figures, 3 tables, accepted by IEEE Journal of Selected Topics in Signal Processing</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.09952">arXiv:2312.09952</a> <span> [<a href="https://arxiv.org/pdf/2312.09952">pdf</a>, <a href="https://arxiv.org/format/2312.09952">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Multi-level graph learning for audio event classification and human-perceived annoyance rating prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hou%2C+Y">Yuanbo Hou</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+Q">Qiaoqiao Ren</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Siyang Song</a>, <a href="/search/eess?searchtype=author&query=Song%2C+Y">Yuxin Song</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wenwu Wang</a>, <a href="/search/eess?searchtype=author&query=Botteldooren%2C+D">Dick Botteldooren</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="2312.09952v1-abstract-short" style="display: inline;"> WHO's report on environmental noise estimates that 22 M people suffer from chronic annoyance related to noise caused by audio events (AEs) from various sources. Annoyance may lead to health issues and adverse effects on metabolic and cognitive systems. In cities, monitoring noise levels does not provide insights into noticeable AEs, let alone their relations to annoyance. To create annoyance-relat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09952v1-abstract-full').style.display = 'inline'; document.getElementById('2312.09952v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.09952v1-abstract-full" style="display: none;"> WHO's report on environmental noise estimates that 22 M people suffer from chronic annoyance related to noise caused by audio events (AEs) from various sources. Annoyance may lead to health issues and adverse effects on metabolic and cognitive systems. In cities, monitoring noise levels does not provide insights into noticeable AEs, let alone their relations to annoyance. To create annoyance-related monitoring, this paper proposes a graph-based model to identify AEs in a soundscape, and explore relations between diverse AEs and human-perceived annoyance rating (AR). Specifically, this paper proposes a lightweight multi-level graph learning (MLGL) based on local and global semantic graphs to simultaneously perform audio event classification (AEC) and human annoyance rating prediction (ARP). Experiments show that: 1) MLGL with 4.1 M parameters improves AEC and ARP results by using semantic node information in local and global context aware graphs; 2) MLGL captures relations between coarse and fine-grained AEs and AR well; 3) Statistical analysis of MLGL results shows that some AEs from different sources significantly correlate with AR, which is consistent with previous research on human perception of these sound sources. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.09952v1-abstract-full').style.display = 'none'; document.getElementById('2312.09952v1-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 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by ICASSP 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/2311.07908">arXiv:2311.07908</a> <span> [<a href="https://arxiv.org/pdf/2311.07908">pdf</a>, <a href="https://arxiv.org/format/2311.07908">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Learning Bayes-Optimal Channel Estimation for Holographic MIMO in Unknown EM Environments </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+W">Wentao Yu</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+X">Xianghao Yu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Murch%2C+R+D">Ross D. Murch</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</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="2311.07908v2-abstract-short" style="display: inline;"> Holographic MIMO (HMIMO) has recently been recognized as a promising enabler for future 6G systems through the use of an ultra-massive number of antennas in a compact space to exploit the propagation characteristics of the electromagnetic (EM) channel. Nevertheless, the promised gain of HMIMO could not be fully unleashed without an efficient means to estimate the high-dimensional channel. Bayes-op… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.07908v2-abstract-full').style.display = 'inline'; document.getElementById('2311.07908v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.07908v2-abstract-full" style="display: none;"> Holographic MIMO (HMIMO) has recently been recognized as a promising enabler for future 6G systems through the use of an ultra-massive number of antennas in a compact space to exploit the propagation characteristics of the electromagnetic (EM) channel. Nevertheless, the promised gain of HMIMO could not be fully unleashed without an efficient means to estimate the high-dimensional channel. Bayes-optimal estimators typically necessitate either a large volume of supervised training samples or a priori knowledge of the true channel distribution, which could hardly be available in practice due to the enormous system scale and the complicated EM environments. It is thus important to design a Bayes-optimal estimator for the HMIMO channels in arbitrary and unknown EM environments, free of any supervision or priors. This work proposes a self-supervised minimum mean-square-error (MMSE) channel estimation algorithm based on powerful machine learning tools, i.e., score matching and principal component analysis. The training stage requires only the pilot signals, without knowing the spatial correlation, the ground-truth channels, or the received signal-to-noise-ratio. Simulation results will show that, even being totally self-supervised, the proposed algorithm can still approach the performance of the oracle MMSE method with an extremely low complexity, making it a competitive candidate in practice. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.07908v2-abstract-full').style.display = 'none'; document.getElementById('2311.07908v2-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 3 figures, 1 table, accepted for presentation at IEEE ICC 2024, Denver, CO, USA</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.07081">arXiv:2311.07081</a> <span> [<a href="https://arxiv.org/pdf/2311.07081">pdf</a>, <a href="https://arxiv.org/format/2311.07081">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Sensing Mutual Information with Random Signals in Gaussian Channels </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+F">Fan Liu</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+Z">Zhanyuan Xie</a>, <a href="/search/eess?searchtype=author&query=Jiang%2C+Z">Zheng Jiang</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</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="2311.07081v1-abstract-short" style="display: inline;"> Sensing performance is typically evaluated by classical metrics, such as Cramer-Rao bound and signal-to-clutter-plus-noise ratio. The recent development of the integrated sensing and communication (ISAC) framework motivated the efforts to unify the metric for sensing and communication, where researchers have proposed to utilize mutual information (MI) to measure the sensing performance with determ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.07081v1-abstract-full').style.display = 'inline'; document.getElementById('2311.07081v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.07081v1-abstract-full" style="display: none;"> Sensing performance is typically evaluated by classical metrics, such as Cramer-Rao bound and signal-to-clutter-plus-noise ratio. The recent development of the integrated sensing and communication (ISAC) framework motivated the efforts to unify the metric for sensing and communication, where researchers have proposed to utilize mutual information (MI) to measure the sensing performance with deterministic signals. However, the need to communicate in ISAC systems necessitates the use of random signals for sensing applications and the closed-form evaluation for the sensing mutual information (SMI) with random signals is not yet available in the literature. This paper investigates the achievable performance and precoder design for sensing applications with random signals. For that purpose, we first derive the closed-form expression for the SMI with random signals by utilizing random matrix theory. The result reveals some interesting physical insights regarding the relation between the SMI with deterministic and random signals. The derived SMI is then utilized to optimize the precoder by leveraging a manifold-based optimization approach. The effectiveness of the proposed methods is validated by simulation results. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.07081v1-abstract-full').style.display = 'none'; document.getElementById('2311.07081v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.04468">arXiv:2311.04468</a> <span> [<a href="https://arxiv.org/pdf/2311.04468">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="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> A human brain atlas of chi-separation for normative iron and myelin distributions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Min%2C+K">Kyeongseon Min</a>, <a href="/search/eess?searchtype=author&query=Sohn%2C+B">Beomseok Sohn</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+W+J">Woo Jung Kim</a>, <a href="/search/eess?searchtype=author&query=Park%2C+C+J">Chae Jung Park</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Soohwa Song</a>, <a href="/search/eess?searchtype=author&query=Shin%2C+D+H">Dong Hoon Shin</a>, <a href="/search/eess?searchtype=author&query=Chang%2C+K+W">Kyung Won Chang</a>, <a href="/search/eess?searchtype=author&query=Shin%2C+N">Na-Young Shin</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+M">Minjun Kim</a>, <a href="/search/eess?searchtype=author&query=Shin%2C+H">Hyeong-Geol Shin</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+P+H">Phil Hyu Lee</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+J">Jongho Lee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2311.04468v3-abstract-short" style="display: inline;"> Iron and myelin are primary susceptibility sources in the human brain. These substances are essential for healthy brain, and their abnormalities are often related to various neurological disorders. Recently, an advanced susceptibility mapping technique, which is referred to as chi-separation, has been proposed, successfully disentangling paramagnetic iron from diamagnetic myelin. This method opene… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.04468v3-abstract-full').style.display = 'inline'; document.getElementById('2311.04468v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.04468v3-abstract-full" style="display: none;"> Iron and myelin are primary susceptibility sources in the human brain. These substances are essential for healthy brain, and their abnormalities are often related to various neurological disorders. Recently, an advanced susceptibility mapping technique, which is referred to as chi-separation, has been proposed, successfully disentangling paramagnetic iron from diamagnetic myelin. This method opened a potential for generating high resolution iron and myelin maps in the brain. Utilizing this technique, this study constructs a normative chi-separation atlas from 106 healthy human brains. The resulting atlas provides detailed anatomical structures associated with the distributions of iron and myelin, clearly delineating subcortical nuclei, thalamic nuclei, and white matter fiber bundles. Additionally, susceptibility values in a number of regions of interest are reported along with age-dependent changes. This atlas may have direct applications such as localization of subcortical structures for deep brain stimulation or high-intensity focused ultrasound and also serve as a valuable resource for future research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.04468v3-abstract-full').style.display = 'none'; document.getElementById('2311.04468v3-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 9 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.18656">arXiv:2310.18656</a> <span> [<a href="https://arxiv.org/pdf/2310.18656">pdf</a>, <a href="https://arxiv.org/format/2310.18656">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"> Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Shen%2C+H">Haoran Shen</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+Y">Yifu Zhang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wenxuan Wang</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+C">Chen Chen</a>, <a href="/search/eess?searchtype=author&query=Liu%2C+J">Jing Liu</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shanshan Song</a>, <a href="/search/eess?searchtype=author&query=Li%2C+J">Jiangyun 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="2310.18656v1-abstract-short" style="display: inline;"> Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18656v1-abstract-full').style.display = 'inline'; document.getElementById('2310.18656v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.18656v1-abstract-full" style="display: none;"> Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.18656v1-abstract-full').style.display = 'none'; document.getElementById('2310.18656v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by WACV 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/2310.04440">arXiv:2310.04440</a> <span> [<a href="https://arxiv.org/pdf/2310.04440">pdf</a>, <a href="https://arxiv.org/format/2310.04440">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Systems and Control">eess.SY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Facilitating Battery Swapping Services for Freight Trucks with Spatial-Temporal Demand Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Liu%2C+L">Linyu Liu</a>, <a href="/search/eess?searchtype=author&query=Dai%2C+Z">Zhen Dai</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shiji Song</a>, <a href="/search/eess?searchtype=author&query=Li%2C+X">Xiaocheng Li</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+G">Guanting 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="2310.04440v2-abstract-short" style="display: inline;"> Electrifying heavy-duty trucks offers a substantial opportunity to curtail carbon emissions, advancing toward a carbon-neutral future. However, the inherent challenges of limited battery energy and the sheer weight of heavy-duty trucks lead to reduced mileage and prolonged charging durations. Consequently, battery-swapping services emerge as an attractive solution for these trucks. This paper empl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.04440v2-abstract-full').style.display = 'inline'; document.getElementById('2310.04440v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.04440v2-abstract-full" style="display: none;"> Electrifying heavy-duty trucks offers a substantial opportunity to curtail carbon emissions, advancing toward a carbon-neutral future. However, the inherent challenges of limited battery energy and the sheer weight of heavy-duty trucks lead to reduced mileage and prolonged charging durations. Consequently, battery-swapping services emerge as an attractive solution for these trucks. This paper employs a two-fold approach to investigate the potential and enhance the efficacy of such services. Firstly, spatial-temporal demand prediction models are adopted to predict the traffic patterns for the upcoming hours. Subsequently, the prediction guides an optimization module for efficient battery allocation and deployment. Analyzing the heavy-duty truck data on a highway network spanning over 2,500 miles, our model and analysis underscore the value of prediction/machine learning in facilitating future decision-makings. In particular, we find that the initial phase of implementing battery-swapping services favors mobile battery-swapping stations, but as the system matures, fixed-location stations are preferred. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.04440v2-abstract-full').style.display = 'none'; document.getElementById('2310.04440v2-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 90B06; 68T07 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.03889">arXiv:2310.03889</a> <span> [<a href="https://arxiv.org/pdf/2310.03889">pdf</a>, <a href="https://arxiv.org/ps/2310.03889">ps</a>, <a href="https://arxiv.org/format/2310.03889">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1109/LSP.2023.3319233">10.1109/LSP.2023.3319233 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hou%2C+Y">Yuanbo Hou</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Siyang Song</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+C">Chuang Yu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wenwu Wang</a>, <a href="/search/eess?searchtype=author&query=Botteldooren%2C+D">Dick Botteldooren</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.03889v1-abstract-short" style="display: inline;"> Most deep learning-based acoustic scene classification (ASC) approaches identify scenes based on acoustic features converted from audio clips containing mixed information entangled by polyphonic audio events (AEs). However, these approaches have difficulties in explaining what cues they use to identify scenes. This paper conducts the first study on disclosing the relationship between real-life aco… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.03889v1-abstract-full').style.display = 'inline'; document.getElementById('2310.03889v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.03889v1-abstract-full" style="display: none;"> Most deep learning-based acoustic scene classification (ASC) approaches identify scenes based on acoustic features converted from audio clips containing mixed information entangled by polyphonic audio events (AEs). However, these approaches have difficulties in explaining what cues they use to identify scenes. This paper conducts the first study on disclosing the relationship between real-life acoustic scenes and semantic embeddings from the most relevant AEs. Specifically, we propose an event-relational graph representation learning (ERGL) framework for ASC to classify scenes, and simultaneously answer clearly and straightly which cues are used in classifying. In the event-relational graph, embeddings of each event are treated as nodes, while relationship cues derived from each pair of nodes are described by multi-dimensional edge features. Experiments on a real-life ASC dataset show that the proposed ERGL achieves competitive performance on ASC by learning embeddings of only a limited number of AEs. The results show the feasibility of recognizing diverse acoustic scenes based on the audio event-relational graph. Visualizations of graph representations learned by ERGL are available here (https://github.com/Yuanbo2020/ERGL). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.03889v1-abstract-full').style.display = 'none'; document.getElementById('2310.03889v1-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">IEEE Signal Processing Letters, doi: 10.1109/LSP.2023.3319233</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.12783">arXiv:2309.12783</a> <span> [<a href="https://arxiv.org/pdf/2309.12783">pdf</a>, <a href="https://arxiv.org/ps/2309.12783">ps</a>, <a href="https://arxiv.org/format/2309.12783">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"> Multi-objective Optimization of Space-Air-Ground Integrated Network Slicing Relying on a Pair of Central and Distributed Learning Algorithms </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Zhou%2C+G">Guorong Zhou</a>, <a href="/search/eess?searchtype=author&query=Zhao%2C+L">Liqiang Zhao</a>, <a href="/search/eess?searchtype=author&query=Zheng%2C+G">Gan Zheng</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jiankang Zhang</a>, <a href="/search/eess?searchtype=author&query=Hanzo%2C+L">Lajos Hanzo</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.12783v1-abstract-short" style="display: inline;"> As an attractive enabling technology for next-generation wireless communications, network slicing supports diverse customized services in the global space-air-ground integrated network (SAGIN) with diverse resource constraints. In this paper, we dynamically consider three typical classes of radio access network (RAN) slices, namely high-throughput slices, low-delay slices and wide-coverage slices,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.12783v1-abstract-full').style.display = 'inline'; document.getElementById('2309.12783v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.12783v1-abstract-full" style="display: none;"> As an attractive enabling technology for next-generation wireless communications, network slicing supports diverse customized services in the global space-air-ground integrated network (SAGIN) with diverse resource constraints. In this paper, we dynamically consider three typical classes of radio access network (RAN) slices, namely high-throughput slices, low-delay slices and wide-coverage slices, under the same underlying physical SAGIN. The throughput, the service delay and the coverage area of these three classes of RAN slices are jointly optimized in a non-scalar form by considering the distinct channel features and service advantages of the terrestrial, aerial and satellite components of SAGINs. A joint central and distributed multi-agent deep deterministic policy gradient (CDMADDPG) algorithm is proposed for solving the above problem to obtain the Pareto optimal solutions. The algorithm first determines the optimal virtual unmanned aerial vehicle (vUAV) positions and the inter-slice sub-channel and power sharing by relying on a centralized unit. Then it optimizes the intra-slice sub-channel and power allocation, and the virtual base station (vBS)/vUAV/virtual low earth orbit (vLEO) satellite deployment in support of three classes of slices by three separate distributed units. Simulation results verify that the proposed method approaches the Pareto-optimal exploitation of multiple RAN slices, and outperforms the benchmarkers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.12783v1-abstract-full').style.display = 'none'; document.getElementById('2309.12783v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 14 figures, journal</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.10065">arXiv:2309.10065</a> <span> [<a href="https://arxiv.org/pdf/2309.10065">pdf</a>, <a href="https://arxiv.org/format/2309.10065">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</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"> Bayesian longitudinal tensor response regression for modeling neuroplasticity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Kundu%2C+S">Suprateek Kundu</a>, <a href="/search/eess?searchtype=author&query=Reinhardt%2C+A">Alec Reinhardt</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Serena Song</a>, <a href="/search/eess?searchtype=author&query=Han%2C+J">Joo Han</a>, <a href="/search/eess?searchtype=author&query=Meadows%2C+M+L">M. Lawson Meadows</a>, <a href="/search/eess?searchtype=author&query=Crosson%2C+B">Bruce Crosson</a>, <a href="/search/eess?searchtype=author&query=Krishnamurthy%2C+V">Venkatagiri Krishnamurthy</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.10065v2-abstract-short" style="display: inline;"> A major interest in longitudinal neuroimaging studies involves investigating voxel-level neuroplasticity due to treatment and other factors across visits. However, traditional voxel-wise methods are beset with several pitfalls, which can compromise the accuracy of these approaches. We propose a novel Bayesian tensor response regression approach for longitudinal imaging data, which pools informatio… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.10065v2-abstract-full').style.display = 'inline'; document.getElementById('2309.10065v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.10065v2-abstract-full" style="display: none;"> A major interest in longitudinal neuroimaging studies involves investigating voxel-level neuroplasticity due to treatment and other factors across visits. However, traditional voxel-wise methods are beset with several pitfalls, which can compromise the accuracy of these approaches. We propose a novel Bayesian tensor response regression approach for longitudinal imaging data, which pools information across spatially-distributed voxels to infer significant changes while adjusting for covariates. The proposed method, which is implemented using Markov chain Monte Carlo (MCMC) sampling, utilizes low-rank decomposition to reduce dimensionality and preserve spatial configurations of voxels when estimating coefficients. It also enables feature selection via joint credible regions which respect the shape of the posterior distributions for more accurate inference. In addition to group level inferences, the method is able to infer individual-level neuroplasticity, allowing for examination of personalized disease or recovery trajectories. The advantages of the proposed approach in terms of prediction and feature selection over voxel-wise regression are highlighted via extensive simulation studies. Subsequently, we apply the approach to a longitudinal Aphasia dataset consisting of task functional MRI images from a group of subjects who were administered either a control intervention or intention treatment at baseline and were followed up over subsequent visits. Our analysis revealed that while the control therapy showed long-term increases in brain activity, the intention treatment produced predominantly short-term changes, both of which were concentrated in distinct localized regions. In contrast, the voxel-wise regression failed to detect any significant neuroplasticity after multiplicity adjustments, which is biologically implausible and implies lack of power. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.10065v2-abstract-full').style.display = 'none'; document.getElementById('2309.10065v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">28 pages, 8 figures, 6 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.09575">arXiv:2309.09575</a> <span> [<a href="https://arxiv.org/pdf/2309.09575">pdf</a>, <a href="https://arxiv.org/format/2309.09575">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> </div> </div> <p class="title is-5 mathjax"> Deep Learning for Near-Field XL-MIMO Transceiver Design: Principles and Techniques </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Yu%2C+W">Wentao Yu</a>, <a href="/search/eess?searchtype=author&query=Ma%2C+Y">Yifan Ma</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.09575v3-abstract-short" style="display: inline;"> Massive multiple-input multiple-output (MIMO) has been a critical enabling technology in 5th generation (5G) wireless networks. With the advent of 6G, a natural evolution is to employ even more antennas, potentially an order of magnitude more, to meet the ever-increasing demand for spectral efficiency. This is beyond a mere quantitative scale-up. The enlarged array aperture brings a paradigm shift… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.09575v3-abstract-full').style.display = 'inline'; document.getElementById('2309.09575v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.09575v3-abstract-full" style="display: none;"> Massive multiple-input multiple-output (MIMO) has been a critical enabling technology in 5th generation (5G) wireless networks. With the advent of 6G, a natural evolution is to employ even more antennas, potentially an order of magnitude more, to meet the ever-increasing demand for spectral efficiency. This is beyond a mere quantitative scale-up. The enlarged array aperture brings a paradigm shift towards near-field communications, departing from traditional far-field approaches. However, designing advanced transceiver algorithms for near-field systems is extremely challenging because of the enormous system scale, the complicated channel characteristics, and the uncertainties in the propagation environments. Hence, it is important to develop scalable, low-complexity, and robust algorithms that can efficiently characterize and leverage the properties of the near-field channel. In this article, we discuss the principles and advocate two general frameworks to design deep learning-based near-field transceivers covering both iterative and non-iterative algorithms. Case studies on channel estimation and beam focusing are presented to provide a hands-on tutorial. Finally, we discuss open issues and shed light on future directions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.09575v3-abstract-full').style.display = 'none'; document.getElementById('2309.09575v3-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 3 figures, 2 tables, accepted by IEEE Communications Magazine, Special Issue on Near-Field MIMO Technologies Towards 6G</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.11980">arXiv:2308.11980</a> <span> [<a href="https://arxiv.org/pdf/2308.11980">pdf</a>, <a href="https://arxiv.org/format/2308.11980">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Joint Prediction of Audio Event and Annoyance Rating in an Urban Soundscape by Hierarchical Graph Representation Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Hou%2C+Y">Yuanbo Hou</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Siyang Song</a>, <a href="/search/eess?searchtype=author&query=Luo%2C+C">Cheng Luo</a>, <a href="/search/eess?searchtype=author&query=Mitchell%2C+A">Andrew Mitchell</a>, <a href="/search/eess?searchtype=author&query=Ren%2C+Q">Qiaoqiao Ren</a>, <a href="/search/eess?searchtype=author&query=Xie%2C+W">Weicheng Xie</a>, <a href="/search/eess?searchtype=author&query=Kang%2C+J">Jian Kang</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+W">Wenwu Wang</a>, <a href="/search/eess?searchtype=author&query=Botteldooren%2C+D">Dick Botteldooren</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.11980v1-abstract-short" style="display: inline;"> Sound events in daily life carry rich information about the objective world. The composition of these sounds affects the mood of people in a soundscape. Most previous approaches only focus on classifying and detecting audio events and scenes, but may ignore their perceptual quality that may impact humans' listening mood for the environment, e.g. annoyance. To this end, this paper proposes a novel… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11980v1-abstract-full').style.display = 'inline'; document.getElementById('2308.11980v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.11980v1-abstract-full" style="display: none;"> Sound events in daily life carry rich information about the objective world. The composition of these sounds affects the mood of people in a soundscape. Most previous approaches only focus on classifying and detecting audio events and scenes, but may ignore their perceptual quality that may impact humans' listening mood for the environment, e.g. annoyance. To this end, this paper proposes a novel hierarchical graph representation learning (HGRL) approach which links objective audio events (AE) with subjective annoyance ratings (AR) of the soundscape perceived by humans. The hierarchical graph consists of fine-grained event (fAE) embeddings with single-class event semantics, coarse-grained event (cAE) embeddings with multi-class event semantics, and AR embeddings. Experiments show the proposed HGRL successfully integrates AE with AR for AEC and ARP tasks, while coordinating the relations between cAE and fAE and further aligning the two different grains of AE information with the AR. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11980v1-abstract-full').style.display = 'none'; document.getElementById('2308.11980v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">INTERSPEECH 2023, Code and models: https://github.com/Yuanbo2020/HGRL</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.03137">arXiv:2308.03137</a> <span> [<a href="https://arxiv.org/pdf/2308.03137">pdf</a>, <a href="https://arxiv.org/format/2308.03137">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"> Digital Self-Interference Cancellation With Robust Multi-layered Total Least Mean Squares Adaptive Filters </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Song%2C+S">Shiyu Song</a>, <a href="/search/eess?searchtype=author&query=Tang%2C+Y">Yanqun Tang</a>, <a href="/search/eess?searchtype=author&query=Wei%2C+X">Xizhang Wei</a>, <a href="/search/eess?searchtype=author&query=Zhou%2C+Y">Yu Zhou</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+X">Xianjie Lu</a>, <a href="/search/eess?searchtype=author&query=Wang%2C+Z">Zhengpeng Wang</a>, <a href="/search/eess?searchtype=author&query=Ge%2C+S">Songhu Ge</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.03137v1-abstract-short" style="display: inline;"> In simultaneous transmit and receive (STAR) wireless communications, digital self-interference (SI) cancellation is required before estimating the remote transmission (RT) channel. Considering the inherent connection between SI channel reconstruction and RT channel estimation, we propose a multi-layered M-estimate total least mean squares (m-MTLS) joint estimator to estimate both channels. In each… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03137v1-abstract-full').style.display = 'inline'; document.getElementById('2308.03137v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.03137v1-abstract-full" style="display: none;"> In simultaneous transmit and receive (STAR) wireless communications, digital self-interference (SI) cancellation is required before estimating the remote transmission (RT) channel. Considering the inherent connection between SI channel reconstruction and RT channel estimation, we propose a multi-layered M-estimate total least mean squares (m-MTLS) joint estimator to estimate both channels. In each layer, our proposed m-MTLS estimator first employs an M-estimate total least mean squares (MTLS) algorithm to eliminate residual SI from the received signal and give a new estimation of the RT channel. Then, it gives the final RT channel estimation based on the weighted sum of the estimation values obtained from each layer. Compared to traditional minimum mean square error (MMSE) estimator and single-layered MTLS estimator, it demonstrates that the m-MTLS estimator has better performance of normalized mean squared difference (NMSD). Besides, the simulation results also show the robustness of m-MTLS estimator even in scenarios where the local reference signal is contaminated with noise, and the received signal is impacted by strong impulse noise. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.03137v1-abstract-full').style.display = 'none'; document.getElementById('2308.03137v1-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 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.02416">arXiv:2308.02416</a> <span> [<a href="https://arxiv.org/pdf/2308.02416">pdf</a>, <a href="https://arxiv.org/format/2308.02416">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Local-Global Temporal Fusion Network with an Attention Mechanism for Multiple and Multiclass Arrhythmia Classification </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Kim%2C+Y+K">Yun Kwan Kim</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+M">Minji Lee</a>, <a href="/search/eess?searchtype=author&query=Jo%2C+K">Kunwook Jo</a>, <a href="/search/eess?searchtype=author&query=Song%2C+H+S">Hee Seok Song</a>, <a href="/search/eess?searchtype=author&query=Lee%2C+S">Seong-Whan Lee</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.02416v2-abstract-short" style="display: inline;"> Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms (ECGs). However, forming a CDSS for the arrhythmia classification task is challenging due to the varying lengths of arrhythmias. Although the onset time of arrhythmia varies, previously developed methods have not consid… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.02416v2-abstract-full').style.display = 'inline'; document.getElementById('2308.02416v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.02416v2-abstract-full" style="display: none;"> Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms (ECGs). However, forming a CDSS for the arrhythmia classification task is challenging due to the varying lengths of arrhythmias. Although the onset time of arrhythmia varies, previously developed methods have not considered such conditions. Thus, we propose a framework that consists of (i) local temporal information extraction, (ii) global pattern extraction, and (iii) local-global information fusion with attention to perform arrhythmia detection and classification with a constrained input length. The 10-class and 4-class performances of our approach were assessed by detecting the onset and offset of arrhythmia as an episode and the duration of arrhythmia based on the MIT-BIH arrhythmia database (MITDB) and MIT-BIH atrial fibrillation database (AFDB), respectively. The results were statistically superior to those achieved by the comparison models. To check the generalization ability of the proposed method, an AFDB-trained model was tested on the MITDB, and superior performance was attained compared with that of a state-of-the-art model. The proposed method can capture local-global information and dynamics without incurring information losses. Therefore, arrhythmias can be recognized more accurately, and their occurrence times can be calculated; thus, the clinical field can create more accurate treatment plans by using the proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.02416v2-abstract-full').style.display = 'none'; document.getElementById('2308.02416v2-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 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T07; 92C55 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.10538">arXiv:2307.10538</a> <span> [<a href="https://arxiv.org/pdf/2307.10538">pdf</a>, <a href="https://arxiv.org/format/2307.10538">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"> Power Allocation for Device-to-Device Interference Channel Using Truncated Graph Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Kim%2C+D">Dohoon Kim</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</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="2307.10538v2-abstract-short" style="display: inline;"> Power control for the device-to-device interference channel with single-antenna transceivers has been widely analyzed with both model-based methods and learning-based approaches. Although the learning-based approaches, i.e., datadriven and model-driven, offer performance improvement, the widely adopted graph neural network suffers from learning the heterophilous power distribution of the interfere… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10538v2-abstract-full').style.display = 'inline'; document.getElementById('2307.10538v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.10538v2-abstract-full" style="display: none;"> Power control for the device-to-device interference channel with single-antenna transceivers has been widely analyzed with both model-based methods and learning-based approaches. Although the learning-based approaches, i.e., datadriven and model-driven, offer performance improvement, the widely adopted graph neural network suffers from learning the heterophilous power distribution of the interference channel. In this paper, we propose a deep learning architecture in the family of graph transformers to circumvent the issue. Experiment results show that the proposed methods achieve the state-of-theart performance across a wide range of untrained network configurations. Furthermore, we show there is a trade-off between model complexity and generality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10538v2-abstract-full').style.display = 'none'; document.getElementById('2307.10538v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">6 pages, 5 figures. Accepted in IEEE International Mediterranean Conference on 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/2307.04977">arXiv:2307.04977</a> <span> [<a href="https://arxiv.org/pdf/2307.04977">pdf</a>, <a href="https://arxiv.org/format/2307.04977">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"> Model-Driven Sensing-Node Selection and Power Allocation for Tracking Maneuvering Targets in Perceptive Mobile Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Xie%2C+L">Lei Xie</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Eldar%2C+Y+C">Yonina C. Eldar</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.04977v2-abstract-short" style="display: inline;"> Maneuvering target tracking will be an important service of future wireless networks to assist innovative applications such as intelligent transportation. However, tracking maneuvering targets by cellular networks faces many challenges. For example, the dense network and high-speed targets make the selection of the sensing nodes (SNs) and the associated power allocation very challenging. Existing… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.04977v2-abstract-full').style.display = 'inline'; document.getElementById('2307.04977v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.04977v2-abstract-full" style="display: none;"> Maneuvering target tracking will be an important service of future wireless networks to assist innovative applications such as intelligent transportation. However, tracking maneuvering targets by cellular networks faces many challenges. For example, the dense network and high-speed targets make the selection of the sensing nodes (SNs) and the associated power allocation very challenging. Existing methods demonstrated engaging performance, but with high computational complexity. In this paper, we propose a model-driven deep learning (DL)-based approach for SN selection. To this end, we first propose an iterative SN selection method by jointly exploiting the majorization-minimization (MM) framework and the alternating direction method of multipliers (ADMM). Then, we unfold the iterative algorithm as a deep neural network and prove its convergence. The proposed method achieves lower computational complexity, because the number of layers is less than the number of iterations required by the original algorithm, and each layer only involves simple matrix-vector additions/multiplications. Finally, we propose an efficient power allocation method based on fixed point (FP) water filling and solve the joint SN selection and power allocation problem under the alternative optimization framework. Simulation results show that the proposed method achieves better performance than the conventional optimization-based methods with much lower computational complexity. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.04977v2-abstract-full').style.display = 'none'; document.getElementById('2307.04977v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.02344">arXiv:2306.02344</a> <span> [<a href="https://arxiv.org/pdf/2306.02344">pdf</a>, <a href="https://arxiv.org/format/2306.02344">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> Influence of Lossy Speech Codecs on Hearing-aid, Binaural Sound Source Localisation using DNNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Song%2C+S">Siyuan Song</a>, <a href="/search/eess?searchtype=author&query=Kindt%2C+S">Stijn Kindt</a>, <a href="/search/eess?searchtype=author&query=Maes%2C+J">Jasper Maes</a>, <a href="/search/eess?searchtype=author&query=Madhu%2C+A+B+N">Alexander Bohlender. Nilesh Madhu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.02344v1-abstract-short" style="display: inline;"> Hearing aids are typically equipped with multiple microphones to exploit spatial information for source localisation and speech enhancement. Especially for hearing aids, a good source localisation is important: it not only guides source separation methods but can also be used to enhance spatial cues, increasing user-awareness of important events in their surroundings. We use a state-of-the-art dee… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.02344v1-abstract-full').style.display = 'inline'; document.getElementById('2306.02344v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.02344v1-abstract-full" style="display: none;"> Hearing aids are typically equipped with multiple microphones to exploit spatial information for source localisation and speech enhancement. Especially for hearing aids, a good source localisation is important: it not only guides source separation methods but can also be used to enhance spatial cues, increasing user-awareness of important events in their surroundings. We use a state-of-the-art deep neural network (DNN) to perform binaural direction-of-arrival (DoA) estimation, where the DNN uses information from all microphones at both ears. However, hearing aids have limited bandwidth to exchange this data. Bluetooth low-energy (BLE) is emerging as an attractive option to facilitate such data exchange, with the LC3plus codec offering several bitrate and latency trade-off possibilities. In this paper, we investigate the effect of such lossy codecs on localisation accuracy. Specifically, we consider two conditions: processing at one ear vs processing at a central point, which influences the number of channels that need to be encoded. Performance is benchmarked against a baseline that allows full audio-exchange - yielding valuable insights into the usage of DNNs under lossy encoding. We also extend the Pyroomacoustics library to include hearing-device and head-related transfer functions (HD-HRTFs) to suitably train the networks. This can also benefit other researchers in the field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.02344v1-abstract-full').style.display = 'none'; document.getElementById('2306.02344v1-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.00812">arXiv:2306.00812</a> <span> [<a href="https://arxiv.org/pdf/2306.00812">pdf</a>, <a href="https://arxiv.org/format/2306.00812">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> </div> </div> <p class="title is-5 mathjax"> Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Le%2C+X">Xiaohuai Le</a>, <a href="/search/eess?searchtype=author&query=Lei%2C+T">Tong Lei</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+L">Li Chen</a>, <a href="/search/eess?searchtype=author&query=Guo%2C+Y">Yiqing Guo</a>, <a href="/search/eess?searchtype=author&query=He%2C+C">Chao He</a>, <a href="/search/eess?searchtype=author&query=Chen%2C+C">Cheng Chen</a>, <a href="/search/eess?searchtype=author&query=Xia%2C+X">Xianjun Xia</a>, <a href="/search/eess?searchtype=author&query=Gao%2C+H">Hua Gao</a>, <a href="/search/eess?searchtype=author&query=Xiao%2C+Y">Yijian Xiao</a>, <a href="/search/eess?searchtype=author&query=Ding%2C+P">Piao Ding</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenyi Song</a>, <a href="/search/eess?searchtype=author&query=Lu%2C+J">Jing Lu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.00812v1-abstract-short" style="display: inline;"> With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccura… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00812v1-abstract-full').style.display = 'inline'; document.getElementById('2306.00812v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.00812v1-abstract-full" style="display: none;"> With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. The signal processing-based comb filters used in RNNoise and PercepNet have limited performance and may cause speech quality degradation due to inaccurate fundamental frequency estimation. To tackle this problem, we propose a learnable comb filter to enhance harmonics. Based on the sub-band model, we design a DNN-based fundamental frequency estimator to estimate the discrete fundamental frequencies and a comb filter for harmonic enhancement, which are trained via an end-to-end pattern. The experiments show the advantages of our proposed method over PecepNet and DeepFilterNet. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00812v1-abstract-full').style.display = 'none'; document.getElementById('2306.00812v1-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 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">accepted by Interspeech 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.12423">arXiv:2305.12423</a> <span> [<a href="https://arxiv.org/pdf/2305.12423">pdf</a>, <a href="https://arxiv.org/format/2305.12423">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <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"> Task-Oriented Communication with Out-of-Distribution Detection: An Information Bottleneck Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Li%2C+H">Hongru Li</a>, <a href="/search/eess?searchtype=author&query=Yu%2C+W">Wentao Yu</a>, <a href="/search/eess?searchtype=author&query=He%2C+H">Hengtao He</a>, <a href="/search/eess?searchtype=author&query=Shao%2C+J">Jiawei Shao</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shenghui Song</a>, <a href="/search/eess?searchtype=author&query=Zhang%2C+J">Jun Zhang</a>, <a href="/search/eess?searchtype=author&query=Letaief%2C+K+B">Khaled B. Letaief</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.12423v3-abstract-short" style="display: inline;"> Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications. Most existing deep learning (DL)-based task-oriented communication systems adopt a closed-world scenario, assuming either the same data distribution for training and testing, or the system could hav… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.12423v3-abstract-full').style.display = 'inline'; document.getElementById('2305.12423v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.12423v3-abstract-full" style="display: none;"> Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications. Most existing deep learning (DL)-based task-oriented communication systems adopt a closed-world scenario, assuming either the same data distribution for training and testing, or the system could have access to a large out-of-distribution (OoD) dataset for retraining. However, in practical open-world scenarios, task-oriented communication systems need to handle unknown OoD data. Under such circumstances, the powerful approximation ability of learning methods may force the task-oriented communication systems to overfit the training data (i.e., in-distribution data) and provide overconfident judgments when encountering OoD data. Based on the information bottleneck (IB) framework, we propose a class conditional IB (CCIB) approach to address this problem in this paper, supported by information-theoretical insights. The idea is to extract distinguishable features from in-distribution data while keeping their compactness and informativeness. This is achieved by imposing the class conditional latent prior distribution and enforcing the latent of different classes to be far away from each other. Simulation results shall demonstrate that the proposed approach detects OoD data more efficiently than the baselines and state-of-the-art approaches, without compromising the rate-distortion tradeoff. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.12423v3-abstract-full').style.display = 'none'; document.getElementById('2305.12423v3-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">v1</span> submitted 21 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">code available in github, accepted by IEEE GLOBECOM2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.09946">arXiv:2305.09946</a> <span> [<a href="https://arxiv.org/pdf/2305.09946">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 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/10.1038/s41698-024-00690-y">10.1038/s41698-024-00690-y <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> AdaMSS: Adaptive Multi-Modality Segmentation-to-Survival Learning for Survival Outcome Prediction from PET/CT Images </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/eess?searchtype=author&query=Meng%2C+M">Mingyuan Meng</a>, <a href="/search/eess?searchtype=author&query=Gu%2C+B">Bingxin Gu</a>, <a href="/search/eess?searchtype=author&query=Fulham%2C+M">Michael Fulham</a>, <a href="/search/eess?searchtype=author&query=Song%2C+S">Shaoli Song</a>, <a href="/search/eess?searchtype=author&query=Feng%2C+D">Dagan Feng</a>, <a href="/search/eess?searchtype=author&query=Bi%2C+L">Lei Bi</a>, <a href="/search/eess?searchtype=author&query=Kim%2C+J">Jinman Kim</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.09946v3-abstract-short" style="display: inline;"> Survival prediction is a major concern for cancer management. Deep survival models based on deep learning have been widely adopted to perform end-to-end survival prediction from medical images. Recent deep survival models achieved promising performance by jointly performing tumor segmentation with survival prediction, where the models were guided to extract tumor-related information through Multi-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.09946v3-abstract-full').style.display = 'inline'; document.getElementById('2305.09946v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.09946v3-abstract-full" style="display: none;"> Survival prediction is a major concern for cancer management. Deep survival models based on deep learning have been widely adopted to perform end-to-end survival prediction from medical images. Recent deep survival models achieved promising performance by jointly performing tumor segmentation with survival prediction, where the models were guided to extract tumor-related information through Multi-Task Learning (MTL). However, these deep survival models have difficulties in exploring out-of-tumor prognostic information. In addition, existing deep survival models are unable to effectively leverage multi-modality images. Empirically-designed fusion strategies were commonly adopted to fuse multi-modality information via task-specific manually-designed networks, thus limiting the adaptability to different scenarios. In this study, we propose an Adaptive Multi-modality Segmentation-to-Survival model (AdaMSS) for survival prediction from PET/CT images. Instead of adopting MTL, we propose a novel Segmentation-to-Survival Learning (SSL) strategy, where our AdaMSS is trained for tumor segmentation and survival prediction sequentially in two stages. This strategy enables the AdaMSS to focus on tumor regions in the first stage and gradually expand its focus to include other prognosis-related regions in the second stage. We also propose a data-driven strategy to fuse multi-modality information, which realizes adaptive optimization of fusion strategies based on training data during training. With the SSL and data-driven fusion strategies, our AdaMSS is designed as an adaptive model that can self-adapt its focus regions and fusion strategy for different training stages. Extensive experiments with two large clinical datasets show that our AdaMSS outperforms state-of-the-art survival prediction methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.09946v3-abstract-full').style.display = 'none'; document.getElementById('2305.09946v3-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">The extended version of this paper has been published at npj Precision Oncology as "Adaptive segmentation-to-survival learning for survival prediction from multi-modality medical images"</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> npj Precision Oncology, vol. 8, p. 232, 2024 </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Song%2C+S&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Song%2C+S&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Song%2C+S&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Song%2C+S&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </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