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 263 results for author: <span class="mathjax">Rahman, M M</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Rahman%2C+M+M">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Rahman, M M"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Rahman%2C+M+M&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Rahman, M M"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </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/2411.12748">arXiv:2411.12748</a> <span> [<a href="https://arxiv.org/pdf/2411.12748">pdf</a>, <a href="https://arxiv.org/ps/2411.12748">ps</a>, <a href="https://arxiv.org/format/2411.12748">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Trading and Market Microstructure">q-fin.TR</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"> FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamics </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hossain%2C+M+F+B">Mabsur Fatin Bin Hossain</a>, <a href="/search/cs?searchtype=author&query=Lamia%2C+L+Z">Lubna Zahan Lamia</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mahmudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+M+M">Md Mosaddek Khan</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="2411.12748v1-abstract-short" style="display: inline;"> Time series forecasting is a key tool in financial markets, helping to predict asset prices and guide investment decisions. In highly volatile markets, such as cryptocurrencies like Bitcoin (BTC) and Ethereum (ETH), forecasting becomes more difficult due to extreme price fluctuations driven by market sentiment, technological changes, and regulatory shifts. Traditionally, forecasting relied on stat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12748v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12748v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12748v1-abstract-full" style="display: none;"> Time series forecasting is a key tool in financial markets, helping to predict asset prices and guide investment decisions. In highly volatile markets, such as cryptocurrencies like Bitcoin (BTC) and Ethereum (ETH), forecasting becomes more difficult due to extreme price fluctuations driven by market sentiment, technological changes, and regulatory shifts. Traditionally, forecasting relied on statistical methods, but as markets became more complex, deep learning models like LSTM, Bi-LSTM, and the newer FinBERT-LSTM emerged to capture intricate patterns. Building upon recent advancements and addressing the volatility inherent in cryptocurrency markets, we propose a hybrid model that combines Bidirectional Long Short-Term Memory (Bi-LSTM) networks with FinBERT to enhance forecasting accuracy for these assets. This approach fills a key gap in forecasting volatile financial markets by blending advanced time series models with sentiment analysis, offering valuable insights for investors and analysts navigating unpredictable markets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12748v1-abstract-full').style.display = 'none'; document.getElementById('2411.12748v1-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 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.12137">arXiv:2411.12137</a> <span> [<a href="https://arxiv.org/pdf/2411.12137">pdf</a>, <a href="https://arxiv.org/format/2411.12137">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+M+B">Mehil B Shah</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Khomh%2C+F">Foutse Khomh</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="2411.12137v1-abstract-short" style="display: inline;"> Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). However, DL systems are prone to bugs from many sources, including training data. Existing literature suggests that bugs in training data are highly prevalent, but little research has focused on understanding their impacts on the models used in software engineer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12137v1-abstract-full').style.display = 'inline'; document.getElementById('2411.12137v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.12137v1-abstract-full" style="display: none;"> Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). However, DL systems are prone to bugs from many sources, including training data. Existing literature suggests that bugs in training data are highly prevalent, but little research has focused on understanding their impacts on the models used in software engineering tasks. In this paper, we address this research gap through a comprehensive empirical investigation focused on three types of data prevalent in software engineering tasks: code-based, text-based, and metric-based. Using state-of-the-art baselines, we compare the models trained on clean datasets with those trained on datasets with quality issues and without proper preprocessing. By analysing the gradients, weights, and biases from neural networks under training, we identify the symptoms of data quality and preprocessing issues. Our analysis reveals that quality issues in code data cause biased learning and gradient instability, whereas problems in text data lead to overfitting and poor generalisation of models. On the other hand, quality issues in metric data result in exploding gradients and model overfitting, and inadequate preprocessing exacerbates these effects across all three data types. Finally, we demonstrate the validity and generalizability of our findings using six new datasets. Our research provides a better understanding of the impact and symptoms of data bugs in software engineering datasets. Practitioners and researchers can leverage these findings to develop better monitoring systems and data-cleaning methods to help detect and resolve data bugs in deep learning systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.12137v1-abstract-full').style.display = 'none'; document.getElementById('2411.12137v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 18 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <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 Empirical Software Engineering 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/2411.10954">arXiv:2411.10954</a> <span> [<a href="https://arxiv.org/pdf/2411.10954">pdf</a>, <a href="https://arxiv.org/format/2411.10954">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Faisal%2C+F">Fahim Faisal</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mushfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Anastasopoulos%2C+A">Antonios Anastasopoulos</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="2411.10954v1-abstract-short" style="display: inline;"> There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators ("LLM-as-a-judge") is a growing research area, their sensitivity to dialectal nuances is still underexplored and requires more focused attention. In this paper, we address these gaps through a comprehensive toxicity evaluation of LLMs across d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10954v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10954v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10954v1-abstract-full" style="display: none;"> There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators ("LLM-as-a-judge") is a growing research area, their sensitivity to dialectal nuances is still underexplored and requires more focused attention. In this paper, we address these gaps through a comprehensive toxicity evaluation of LLMs across diverse dialects. We create a multi-dialect dataset through synthetic transformations and human-assisted translations, covering 10 language clusters and 60 varieties. We then evaluated three LLMs on their ability to assess toxicity across multilingual, dialectal, and LLM-human consistency. Our findings show that LLMs are sensitive in handling both multilingual and dialectal variations. However, if we have to rank the consistency, the weakest area is LLM-human agreement, followed by dialectal consistency. Code repository: \url{https://github.com/ffaisal93/dialect_toxicity_llm_judge} <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10954v1-abstract-full').style.display = 'none'; document.getElementById('2411.10954v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20664">arXiv:2410.20664</a> <span>  </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Embedding with Large Language Models for Classification of HIPAA Safeguard Compliance Rules </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+A">Md Abdur Rahman</a>, <a href="/search/cs?searchtype=author&query=Barek%2C+M+A">Md Abdul Barek</a>, <a href="/search/cs?searchtype=author&query=Riad%2C+A+K+I">ABM Kamrul Islam Riad</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mostafizur Rahman</a>, <a href="/search/cs?searchtype=author&query=Rashid%2C+M+B">Md Bajlur Rashid</a>, <a href="/search/cs?searchtype=author&query=Ambedkar%2C+S">Smita Ambedkar</a>, <a href="/search/cs?searchtype=author&query=Miaa%2C+M+R">Md Raihan Miaa</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+F">Fan Wu</a>, <a href="/search/cs?searchtype=author&query=Cuzzocrea%2C+A">Alfredo Cuzzocrea</a>, <a href="/search/cs?searchtype=author&query=Ahamed%2C+S+I">Sheikh Iqbal Ahamed</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="2410.20664v2-abstract-short" style="display: inline;"> Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA rules categories. Therefore, providing guidance of HIPAA rules patterns classification is essential for developing secured applications for Google Play Store. In… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20664v2-abstract-full').style.display = 'inline'; document.getElementById('2410.20664v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20664v2-abstract-full" style="display: none;"> Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA rules categories. Therefore, providing guidance of HIPAA rules patterns classification is essential for developing secured applications for Google Play Store. In this work, we identified the limitations of traditional Word2Vec embeddings in processing code patterns. To address this, we adopt multilingual BERT (Bidirectional Encoder Representations from Transformers) which offers contextualized embeddings to the attributes of dataset to overcome the issues. Therefore, we applied this BERT to our dataset for embedding code patterns and then uses these embedded code to various machine learning approaches. Our results demonstrate that the models significantly enhances classification performance, with Logistic Regression achieving a remarkable accuracy of 99.95\%. Additionally, we obtained high accuracy from Support Vector Machine (99.79\%), Random Forest (99.73\%), and Naive Bayes (95.93\%), outperforming existing approaches. This work underscores the effectiveness and showcases its potential for secure application development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20664v2-abstract-full').style.display = 'none'; document.getElementById('2410.20664v2-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">v1</span> submitted 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">I am requesting the withdrawal of my paper due to critical issues identified in the methodology/results that may impact its accuracy and reliability. I also plan to make substantial revisions that go beyond minor corrections</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18921">arXiv:2410.18921</a> <span> [<a href="https://arxiv.org/pdf/2410.18921">pdf</a>, <a href="https://arxiv.org/format/2410.18921">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Logic in Computer Science">cs.LO</span> </div> </div> <p class="title is-5 mathjax"> From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+A+M+M">A M Muntasir Rahman</a>, <a href="/search/cs?searchtype=author&query=Ye%2C+J">Junyi Ye</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+W">Wei Yao</a>, <a href="/search/cs?searchtype=author&query=Yin%2C+W">Wenpeng Yin</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+G">Guiling Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18921v1-abstract-short" style="display: inline;"> Consider the math problem: "Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily have now?" Many large language models (LLMs) in previous research approach this problem by calculating the answer "1" using the equation "3 - 5 + 3." However, from a human perspective, we recognize the inherent flaw in thi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18921v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18921v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18921v1-abstract-full" style="display: none;"> Consider the math problem: "Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily have now?" Many large language models (LLMs) in previous research approach this problem by calculating the answer "1" using the equation "3 - 5 + 3." However, from a human perspective, we recognize the inherent flaw in this problem: Lily cannot eat 5 cookies if she initially only had 3. This discrepancy prompts a key question: Are current LLMs merely Blind Solver that apply mathematical operations without deeper reasoning, or can they function as Logical Thinker capable of identifying logical inconsistencies? To explore this question, we propose a benchmark dataset, FaultyMath, which includes faulty math problems of rich diversity: i) multiple mathematical categories, e.g., algebra, geometry, number theory, etc., ii) varying levels of difficulty, and iii) different origins of faultiness -- ranging from violations of common sense and ambiguous statements to mathematical contradictions and more. We evaluate a broad spectrum of LLMs, including open-source, closed-source, and math-specialized models, using FaultyMath across three dimensions: (i) How accurately can the models detect faulty math problems without being explicitly prompted to do so? (ii) When provided with hints -- either correct or misleading -- about the validity of the problems, to what extent do LLMs adapt to become reliable Logical Thinker? (iii) How trustworthy are the explanations generated by LLMs when they recognize a math problem as flawed? Through extensive experimentation and detailed analysis, our results demonstrate that existing LLMs largely function as Blind Solver and fall short of the reasoning capabilities required to perform as Logical Thinker. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18921v1-abstract-full').style.display = 'none'; document.getElementById('2410.18921v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15194">arXiv:2410.15194</a> <span> [<a href="https://arxiv.org/pdf/2410.15194">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> FSCsec: Collaboration in Financial Sector Cybersecurity -- Exploring the Impact of Resource Sharing on IT Security </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sayeed%2C+S+A">Sayed Abu Sayeed</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mir Mehedi Rahman</a>, <a href="/search/cs?searchtype=author&query=Alam%2C+S">Samiul Alam</a>, <a href="/search/cs?searchtype=author&query=Kshetri%2C+N">Naresh Kshetri</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="2410.15194v1-abstract-short" style="display: inline;"> The financial sector's dependence on digital infrastructure increases its vulnerability to cybersecurity threats, requiring strong IT security protocols with other entities. This collaboration, however, is often identified as the most vulnerable link in the chain of cybersecurity. Adopting both symbolic and substantive measures lessens the impact of IT security spending on decreasing the frequency… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15194v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15194v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15194v1-abstract-full" style="display: none;"> The financial sector's dependence on digital infrastructure increases its vulnerability to cybersecurity threats, requiring strong IT security protocols with other entities. This collaboration, however, is often identified as the most vulnerable link in the chain of cybersecurity. Adopting both symbolic and substantive measures lessens the impact of IT security spending on decreasing the frequency of data security breaches in the long run. The Protection Motivation Theory clarifies actions triggered by data sharing with other organizations, and the Institutional theory aids in comprehending the intricate relationship between transparency and organizational conduct. We investigate how things like regulatory pressure, teamwork among institutions, and people's motivations to protect themselves influence cybersecurity. By using simple theories to understand these factors, this research aims to provide insights that can help financial institutions make better decisions to protect. We have also included the discussion, conclusion, and future directions in regard to collaboration in financial sector cybersecurity for exploring impact of resource sharing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15194v1-abstract-full').style.display = 'none'; document.getElementById('2410.15194v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">8 pages, 2 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.15017">arXiv:2410.15017</a> <span> [<a href="https://arxiv.org/pdf/2410.15017">pdf</a>, <a href="https://arxiv.org/format/2410.15017">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> </div> </div> <p class="title is-5 mathjax"> DM-Codec: Distilling Multimodal Representations for Speech Tokenization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ahasan%2C+M+M">Md Mubtasim Ahasan</a>, <a href="/search/cs?searchtype=author&query=Fahim%2C+M">Md Fahim</a>, <a href="/search/cs?searchtype=author&query=Mohiuddin%2C+T">Tasnim Mohiuddin</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+A+K+M+M">A K M Mahbubur Rahman</a>, <a href="/search/cs?searchtype=author&query=Chadha%2C+A">Aman Chadha</a>, <a href="/search/cs?searchtype=author&query=Iqbal%2C+T">Tariq Iqbal</a>, <a href="/search/cs?searchtype=author&query=Amin%2C+M+A">M Ashraful Amin</a>, <a href="/search/cs?searchtype=author&query=Islam%2C+M+M">Md Mofijul Islam</a>, <a href="/search/cs?searchtype=author&query=Ali%2C+A+A">Amin Ahsan Ali</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="2410.15017v1-abstract-short" style="display: inline;"> Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing speech representations generally fall into… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15017v1-abstract-full').style.display = 'inline'; document.getElementById('2410.15017v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15017v1-abstract-full" style="display: none;"> Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing speech representations generally fall into two categories: acoustic tokens from audio codecs and semantic tokens from speech self-supervised learning models. Although recent efforts have unified acoustic and semantic tokens for improved performance, they overlook the crucial role of contextual representation in comprehensive speech modeling. Our empirical investigations reveal that the absence of contextual representations results in elevated Word Error Rate (WER) and Word Information Lost (WIL) scores in speech transcriptions. To address these limitations, we propose two novel distillation approaches: (1) a language model (LM)-guided distillation method that incorporates contextual information, and (2) a combined LM and self-supervised speech model (SM)-guided distillation technique that effectively distills multimodal representations (acoustic, semantic, and contextual) into a comprehensive speech tokenizer, termed DM-Codec. The DM-Codec architecture adopts a streamlined encoder-decoder framework with a Residual Vector Quantizer (RVQ) and incorporates the LM and SM during the training process. Experiments show DM-Codec significantly outperforms state-of-the-art speech tokenization models, reducing WER by up to 13.46%, WIL by 9.82%, and improving speech quality by 5.84% and intelligibility by 1.85% on the LibriSpeech benchmark dataset. The code, samples, and model checkpoints are available at https://github.com/mubtasimahasan/DM-Codec. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15017v1-abstract-full').style.display = 'none'; document.getElementById('2410.15017v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.03105">arXiv:2410.03105</a> <span> [<a href="https://arxiv.org/pdf/2410.03105">pdf</a>, <a href="https://arxiv.org/format/2410.03105">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="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Mamba in Vision: A Comprehensive Survey of Techniques and Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Maklachur Rahman</a>, <a href="/search/cs?searchtype=author&query=Tutul%2C+A+A">Abdullah Aman Tutul</a>, <a href="/search/cs?searchtype=author&query=Nath%2C+A">Ankur Nath</a>, <a href="/search/cs?searchtype=author&query=Laishram%2C+L">Lamyanba Laishram</a>, <a href="/search/cs?searchtype=author&query=Jung%2C+S+K">Soon Ki Jung</a>, <a href="/search/cs?searchtype=author&query=Hammond%2C+T">Tracy Hammond</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="2410.03105v1-abstract-short" style="display: inline;"> Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture long-range dependencies without complex architectural modifications. In contrast, ViTs effectively model global relationships but suffer from high computational… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03105v1-abstract-full').style.display = 'inline'; document.getElementById('2410.03105v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.03105v1-abstract-full" style="display: none;"> Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture long-range dependencies without complex architectural modifications. In contrast, ViTs effectively model global relationships but suffer from high computational costs due to the quadratic complexity of their self-attention mechanisms. Mamba addresses these limitations by leveraging Selective Structured State Space Models to effectively capture long-range dependencies with linear computational complexity. This survey analyzes the unique contributions, computational benefits, and applications of Mamba models while also identifying challenges and potential future research directions. We provide a foundational resource for advancing the understanding and growth of Mamba models in computer vision. An overview of this work is available at https://github.com/maklachur/Mamba-in-Computer-Vision. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.03105v1-abstract-full').style.display = 'none'; document.getElementById('2410.03105v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Under Review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.01750">arXiv:2410.01750</a> <span> [<a href="https://arxiv.org/pdf/2410.01750">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> AssessITS: Integrating procedural guidelines and practical evaluation metrics for organizational IT and Cybersecurity risk assessment </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mir Mehedi Rahman</a>, <a href="/search/cs?searchtype=author&query=Kshetri%2C+N">Naresh Kshetri</a>, <a href="/search/cs?searchtype=author&query=Sayeed%2C+S+A">Sayed Abu Sayeed</a>, <a href="/search/cs?searchtype=author&query=Rana%2C+M+M">Md Masud Rana</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="2410.01750v1-abstract-short" style="display: inline;"> In today's digitally driven landscape, robust Information Technology (IT) risk assessment practices are essential for safeguarding systems, digital communication, and data. This paper introduces 'AssessITS', an actionable method designed to provide organizations with comprehensive guidelines for conducting IT and cybersecurity risk assessments. Drawing extensively from NIST 800-30 Rev 1, COBIT 5,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01750v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01750v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01750v1-abstract-full" style="display: none;"> In today's digitally driven landscape, robust Information Technology (IT) risk assessment practices are essential for safeguarding systems, digital communication, and data. This paper introduces 'AssessITS', an actionable method designed to provide organizations with comprehensive guidelines for conducting IT and cybersecurity risk assessments. Drawing extensively from NIST 800-30 Rev 1, COBIT 5, and ISO 31000, 'AssessITS' bridges the gap between high-level theoretical standards and practical implementation challenges. The paper outlines a step-by-step methodology that organizations can simply adopt to systematically identify, analyze, and mitigate IT risks. By simplifying complex principles into actionable procedures, this framework equips practitioners with the tools needed to perform risk assessments independently, without too much reliance on external vendors. The guidelines are developed to be straightforward, integrating practical evaluation metrics that allow for the precise quantification of asset values, threat levels, vulnerabilities, and impacts on confidentiality, integrity, and availability. This approach ensures that the risk assessment process is not only comprehensive but also accessible, enabling decision-makers to implement effective risk mitigation strategies customized to their unique operational contexts. 'AssessITS' aims to enable organizations to enhance their IT security strength through practical, actionable guidance based on internationally recognized standards. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01750v1-abstract-full').style.display = 'none'; document.getElementById('2410.01750v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">25 pages, 8 figures, 7 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/2409.19922">arXiv:2409.19922</a> <span> [<a href="https://arxiv.org/pdf/2409.19922">pdf</a>, <a href="https://arxiv.org/format/2409.19922">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Benchmarking ChatGPT, Codeium, and GitHub Copilot: A Comparative Study of AI-Driven Programming and Debugging Assistants </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ovi%2C+M+S+I">Md Sultanul Islam Ovi</a>, <a href="/search/cs?searchtype=author&query=Anjum%2C+N">Nafisa Anjum</a>, <a href="/search/cs?searchtype=author&query=Bithe%2C+T+H">Tasmina Haque Bithe</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mahabubur Rahman</a>, <a href="/search/cs?searchtype=author&query=Smrity%2C+M+S+A">Mst. Shahnaj Akter Smrity</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="2409.19922v1-abstract-short" style="display: inline;"> With the increasing adoption of AI-driven tools in software development, large language models (LLMs) have become essential for tasks like code generation, bug fixing, and optimization. Tools like ChatGPT, GitHub Copilot, and Codeium provide valuable assistance in solving programming challenges, yet their effectiveness remains underexplored. This paper presents a comparative study of ChatGPT, Code… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19922v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19922v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19922v1-abstract-full" style="display: none;"> With the increasing adoption of AI-driven tools in software development, large language models (LLMs) have become essential for tasks like code generation, bug fixing, and optimization. Tools like ChatGPT, GitHub Copilot, and Codeium provide valuable assistance in solving programming challenges, yet their effectiveness remains underexplored. This paper presents a comparative study of ChatGPT, Codeium, and GitHub Copilot, evaluating their performance on LeetCode problems across varying difficulty levels and categories. Key metrics such as success rates, runtime efficiency, memory usage, and error-handling capabilities are assessed. GitHub Copilot showed superior performance on easier and medium tasks, while ChatGPT excelled in memory efficiency and debugging. Codeium, though promising, struggled with more complex problems. Despite their strengths, all tools faced challenges in handling harder problems. These insights provide a deeper understanding of each tool's capabilities and limitations, offering guidance for developers and researchers seeking to optimize AI integration in coding workflows. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19922v1-abstract-full').style.display = 'none'; document.getElementById('2409.19922v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.09504">arXiv:2409.09504</a> <span> [<a href="https://arxiv.org/pdf/2409.09504">pdf</a>, <a href="https://arxiv.org/format/2409.09504">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Uddessho: An Extensive Benchmark Dataset for Multimodal Author Intent Classification in Low-Resource Bangla Language </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Faria%2C+F+T+J">Fatema Tuj Johora Faria</a>, <a href="/search/cs?searchtype=author&query=Moin%2C+M+B">Mukaffi Bin Moin</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mahfuzur Rahman</a>, <a href="/search/cs?searchtype=author&query=Shanto%2C+M+M+A">Md Morshed Alam Shanto</a>, <a href="/search/cs?searchtype=author&query=Fahim%2C+A+I">Asif Iftekher Fahim</a>, <a href="/search/cs?searchtype=author&query=Hoque%2C+M+M">Md. Moinul Hoque</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="2409.09504v1-abstract-short" style="display: inline;"> With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share their thoughts and opinions. The proposed method leverages multimodal data with particular emphasis on authorship identification, aiming to understand the underl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09504v1-abstract-full').style.display = 'inline'; document.getElementById('2409.09504v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.09504v1-abstract-full" style="display: none;"> With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share their thoughts and opinions. The proposed method leverages multimodal data with particular emphasis on authorship identification, aiming to understand the underlying purpose behind textual content, especially in the context of varied user-generated posts on social media. Current methods often face challenges in low-resource languages like Bangla, particularly when author traits intricately link with intent, as observed in social media posts. To address this, we present the Multimodal-based Author Bangla Intent Classification (MABIC) framework, utilizing text and images to gain deeper insights into the conveyed intentions. We have created a dataset named "Uddessho," comprising 3,048 instances sourced from social media. Our methodology comprises two approaches for classifying textual intent and multimodal author intent, incorporating early fusion and late fusion techniques. In our experiments, the unimodal approach achieved an accuracy of 64.53% in interpreting Bangla textual intent. In contrast, our multimodal approach significantly outperformed traditional unimodal methods, achieving an accuracy of 76.19%. This represents an improvement of 11.66%. To our best knowledge, this is the first research work on multimodal-based author intent classification for low-resource Bangla language social media posts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.09504v1-abstract-full').style.display = 'none'; document.getElementById('2409.09504v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted for publication in "18th International Conference on Information Technology and Applications (ICITA 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/2409.06206">arXiv:2409.06206</a> <span> [<a href="https://arxiv.org/pdf/2409.06206">pdf</a>, <a href="https://arxiv.org/format/2409.06206">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> </div> </div> <p class="title is-5 mathjax"> AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cai%2C+H">Hongyi Cai</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Mahdinur Rahman</a>, <a href="/search/cs?searchtype=author&query=Akhtar%2C+M+S">Mohammad Shahid Akhtar</a>, <a href="/search/cs?searchtype=author&query=Li%2C+J">Jie Li</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jingyu Wu</a>, <a href="/search/cs?searchtype=author&query=Fang%2C+Z">Zhili Fang</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="2409.06206v1-abstract-short" style="display: inline;"> Image Transformers show a magnificent success in Image Restoration tasks. Nevertheless, most of transformer-based models are strictly bounded by exorbitant memory occupancy. Our goal is to reduce the memory consumption of Swin Transformer and at the same time speed up the model during training process. Thus, we introduce AgileIR, group shifted attention mechanism along with window attention, which… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06206v1-abstract-full').style.display = 'inline'; document.getElementById('2409.06206v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.06206v1-abstract-full" style="display: none;"> Image Transformers show a magnificent success in Image Restoration tasks. Nevertheless, most of transformer-based models are strictly bounded by exorbitant memory occupancy. Our goal is to reduce the memory consumption of Swin Transformer and at the same time speed up the model during training process. Thus, we introduce AgileIR, group shifted attention mechanism along with window attention, which sparsely simplifies the model in architecture. We propose Group Shifted Window Attention (GSWA) to decompose Shift Window Multi-head Self Attention (SW-MSA) and Window Multi-head Self Attention (W-MSA) into groups across their attention heads, contributing to shrinking memory usage in back propagation. In addition to that, we keep shifted window masking and its shifted learnable biases during training, in order to induce the model interacting across windows within the channel. We also re-allocate projection parameters to accelerate attention matrix calculation, which we found a negligible decrease in performance. As a result of experiment, compared with our baseline SwinIR and other efficient quantization models, AgileIR keeps the performance still at 32.20 dB on Set5 evaluation dataset, exceeding other methods with tailor-made efficient methods and saves over 50% memory while a large batch size is employed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.06206v1-abstract-full').style.display = 'none'; document.getElementById('2409.06206v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.04651">arXiv:2409.04651</a> <span> [<a href="https://arxiv.org/pdf/2409.04651">pdf</a>, <a href="https://arxiv.org/format/2409.04651">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Introducing Ensemble Machine Learning Algorithms for Automatic Test Case Generation using Learning Based Testing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+S+M+M">Sheikh Md. Mushfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Eisty%2C+N+U">Nasir U. Eisty</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="2409.04651v1-abstract-short" style="display: inline;"> Ensemble methods are powerful machine learning algorithms that combine multiple models to enhance prediction capabilities and reduce generalization errors. However, their potential to generate effective test cases for fault detection in a System Under Test (SUT) has not been extensively explored. This study aims to systematically investigate the combination of ensemble methods and base classifiers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04651v1-abstract-full').style.display = 'inline'; document.getElementById('2409.04651v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.04651v1-abstract-full" style="display: none;"> Ensemble methods are powerful machine learning algorithms that combine multiple models to enhance prediction capabilities and reduce generalization errors. However, their potential to generate effective test cases for fault detection in a System Under Test (SUT) has not been extensively explored. This study aims to systematically investigate the combination of ensemble methods and base classifiers for model inference in a Learning Based Testing (LBT) algorithm to generate fault-detecting test cases for SUTs as a proof of concept. We conduct a series of experiments on functions, generating effective test cases using different ensemble methods and classifier combinations for model inference in our proposed LBT method. We then compare the test suites based on their mutation score. The results indicate that Boosting ensemble methods show overall better performance in generating effective test cases, and the proposed method is performing better than random generation. This analysis helps determine the appropriate ensemble methods for various types of functions. By incorporating ensemble methods into the LBT, this research contributes to the understanding of how to leverage ensemble methods for effective test case generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.04651v1-abstract-full').style.display = 'none'; document.getElementById('2409.04651v1-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 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.03957">arXiv:2409.03957</a> <span> [<a href="https://arxiv.org/pdf/2409.03957">pdf</a>, <a href="https://arxiv.org/format/2409.03957">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> On the Prevalence, Evolution, and Impact of Code Smells in Simulation Modelling Software </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mahbub%2C+R">Riasat Mahbub</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Habib%2C+M+A">Muhammad Ahsanul Habib</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="2409.03957v1-abstract-short" style="display: inline;"> Simulation modelling systems are routinely used to test or understand real-world scenarios in a controlled setting. They have found numerous applications in scientific research, engineering, and industrial operations. Due to their complex nature, the simulation systems could suffer from various code quality issues and technical debt. However, to date, there has not been any investigation into thei… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03957v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03957v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03957v1-abstract-full" style="display: none;"> Simulation modelling systems are routinely used to test or understand real-world scenarios in a controlled setting. They have found numerous applications in scientific research, engineering, and industrial operations. Due to their complex nature, the simulation systems could suffer from various code quality issues and technical debt. However, to date, there has not been any investigation into their code quality issues (e.g. code smells). In this paper, we conduct an empirical study investigating the prevalence, evolution, and impact of code smells in simulation software systems. First, we employ static analysis tools (e.g. Designite) to detect and quantify the prevalence of various code smells in 155 simulation and 327 traditional projects from Github. Our findings reveal that certain code smells (e.g. Long Statement, Magic Number) are more prevalent in simulation software systems than in traditional software systems. Second, we analyze the evolution of these code smells across multiple project versions and investigate their chances of survival. Our experiments show that some code smells such as Magic Number and Long Parameter List can survive a long time in simulation software systems. Finally, we examine any association between software bugs and code smells. Our experiments show that although Design and Architecture code smells are introduced simultaneously with bugs, there is no significant association between code smells and bugs in simulation systems. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03957v1-abstract-full').style.display = 'none'; document.getElementById('2409.03957v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <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 24th IEEE International Conference on Source Code Analysis and Manipulation (SCAM 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/2409.03245">arXiv:2409.03245</a> <span> [<a href="https://arxiv.org/pdf/2409.03245">pdf</a>, <a href="https://arxiv.org/format/2409.03245">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> </div> </div> <p class="title is-5 mathjax"> UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mahfuzur Rahman</a>, <a href="/search/cs?searchtype=author&query=Siddique%2C+S">Sunzida Siddique</a>, <a href="/search/cs?searchtype=author&query=Kamal%2C+M">Marufa Kamal</a>, <a href="/search/cs?searchtype=author&query=Rifat%2C+R+H">Rakib Hossain Rifat</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+K+D">Kishor Datta Gupta</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="2409.03245v1-abstract-short" style="display: inline;"> Unmanned Aerial Vehicles (UAVs), have greatly revolutionized the process of gathering and analyzing data in diverse research domains, providing unmatched adaptability and effectiveness. This paper presents a thorough examination of Unmanned Aerial Vehicle (UAV) datasets, emphasizing their wide range of applications and progress. UAV datasets consist of various types of data, such as satellite imag… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03245v1-abstract-full').style.display = 'inline'; document.getElementById('2409.03245v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.03245v1-abstract-full" style="display: none;"> Unmanned Aerial Vehicles (UAVs), have greatly revolutionized the process of gathering and analyzing data in diverse research domains, providing unmatched adaptability and effectiveness. This paper presents a thorough examination of Unmanned Aerial Vehicle (UAV) datasets, emphasizing their wide range of applications and progress. UAV datasets consist of various types of data, such as satellite imagery, images captured by drones, and videos. These datasets can be categorized as either unimodal or multimodal, offering a wide range of detailed and comprehensive information. These datasets play a crucial role in disaster damage assessment, aerial surveillance, object recognition, and tracking. They facilitate the development of sophisticated models for tasks like semantic segmentation, pose estimation, vehicle re-identification, and gesture recognition. By leveraging UAV datasets, researchers can significantly enhance the capabilities of computer vision models, thereby advancing technology and improving our understanding of complex, dynamic environments from an aerial perspective. This review aims to encapsulate the multifaceted utility of UAV datasets, emphasizing their pivotal role in driving innovation and practical applications in multiple domains. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.03245v1-abstract-full').style.display = 'none'; document.getElementById('2409.03245v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.09005">arXiv:2408.09005</a> <span> [<a href="https://arxiv.org/pdf/2408.09005">pdf</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> </div> </div> <p class="title is-5 mathjax"> Comparative Performance Analysis of Transformer-Based Pre-Trained Models for Detecting Keratoconus Disease </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Ahmed%2C+N">Nayeem Ahmed</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Maruf Rahman</a>, <a href="/search/cs?searchtype=author&query=Ishrak%2C+M+F">Md Fatin Ishrak</a>, <a href="/search/cs?searchtype=author&query=Joy%2C+M+I+K">Md Imran Kabir Joy</a>, <a href="/search/cs?searchtype=author&query=Sabuj%2C+M+S+H">Md Sanowar Hossain Sabuj</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+S">Md. Sadekur Rahman</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="2408.09005v1-abstract-short" style="display: inline;"> This study compares eight pre-trained CNNs for diagnosing keratoconus, a degenerative eye disease. A carefully selected dataset of keratoconus, normal, and suspicious cases was used. The models tested include DenseNet121, EfficientNetB0, InceptionResNetV2, InceptionV3, MobileNetV2, ResNet50, VGG16, and VGG19. To maximize model training, bad sample removal, resizing, rescaling, and augmentation wer… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09005v1-abstract-full').style.display = 'inline'; document.getElementById('2408.09005v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.09005v1-abstract-full" style="display: none;"> This study compares eight pre-trained CNNs for diagnosing keratoconus, a degenerative eye disease. A carefully selected dataset of keratoconus, normal, and suspicious cases was used. The models tested include DenseNet121, EfficientNetB0, InceptionResNetV2, InceptionV3, MobileNetV2, ResNet50, VGG16, and VGG19. To maximize model training, bad sample removal, resizing, rescaling, and augmentation were used. The models were trained with similar parameters, activation function, classification function, and optimizer to compare performance. To determine class separation effectiveness, each model was evaluated on accuracy, precision, recall, and F1-score. MobileNetV2 was the best accurate model in identifying keratoconus and normal cases with few misclassifications. InceptionV3 and DenseNet121 both performed well in keratoconus detection, but they had trouble with questionable cases. In contrast, EfficientNetB0, ResNet50, and VGG19 had more difficulty distinguishing dubious cases from regular ones, indicating the need for model refining and development. A detailed comparison of state-of-the-art CNN architectures for automated keratoconus identification reveals each model's benefits and weaknesses. This study shows that advanced deep learning models can enhance keratoconus diagnosis and treatment planning. Future research should explore hybrid models and integrate clinical parameters to improve diagnostic accuracy and robustness in real-world clinical applications, paving the way for more effective AI-driven ophthalmology tools. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.09005v1-abstract-full').style.display = 'none'; document.getElementById('2408.09005v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <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, 3 tables, 27 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.4.m </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.08261">arXiv:2408.08261</a> <span> [<a href="https://arxiv.org/pdf/2408.08261">pdf</a>, <a href="https://arxiv.org/format/2408.08261">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> mhGPT: A Lightweight Generative Pre-Trained Transformer for Mental Health Text Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kim%2C+D">Dae-young Kim</a>, <a href="/search/cs?searchtype=author&query=Hwa%2C+R">Rebecca Hwa</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Muhammad Mahbubur Rahman</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="2408.08261v1-abstract-short" style="display: inline;"> This paper introduces mhGPT, a lightweight generative pre-trained transformer trained on mental health-related social media and PubMed articles. Fine-tuned for specific mental health tasks, mhGPT was evaluated under limited hardware constraints and compared with state-of-the-art models like MentaLLaMA and Gemma. Despite having only 1.98 billion parameters and using just 5% of the dataset, mhGPT ou… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08261v1-abstract-full').style.display = 'inline'; document.getElementById('2408.08261v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.08261v1-abstract-full" style="display: none;"> This paper introduces mhGPT, a lightweight generative pre-trained transformer trained on mental health-related social media and PubMed articles. Fine-tuned for specific mental health tasks, mhGPT was evaluated under limited hardware constraints and compared with state-of-the-art models like MentaLLaMA and Gemma. Despite having only 1.98 billion parameters and using just 5% of the dataset, mhGPT outperformed larger models and matched the performance of models trained on significantly more data. The key contributions include integrating diverse mental health data, creating a custom tokenizer, and optimizing a smaller architecture for low-resource settings. This research could advance AI-driven mental health care, especially in areas with limited computing power. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.08261v1-abstract-full').style.display = 'none'; document.getElementById('2408.08261v1-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 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/2407.14671">arXiv:2407.14671</a> <span> [<a href="https://arxiv.org/pdf/2407.14671">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> DefTesPY: Cyber defense model with enhanced data modeling and analysis for Tesla company via Python Language </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kshetri%2C+N">Naresh Kshetri</a>, <a href="/search/cs?searchtype=author&query=Sultana%2C+I">Irin Sultana</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mir Mehedi Rahman</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+D">Darshana Shah</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="2407.14671v1-abstract-short" style="display: inline;"> Several types of cyber-attacks on automobiles and business firms keep on rising as we are preparing to counter cybercrimes with several new technologies and defense models. Cyber defense (also, counter intelligence) is a computer network defense mechanism that involves response to activities, critical infrastructure protection, and information assurance for corporations, government bodies, and oth… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14671v1-abstract-full').style.display = 'inline'; document.getElementById('2407.14671v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.14671v1-abstract-full" style="display: none;"> Several types of cyber-attacks on automobiles and business firms keep on rising as we are preparing to counter cybercrimes with several new technologies and defense models. Cyber defense (also, counter intelligence) is a computer network defense mechanism that involves response to activities, critical infrastructure protection, and information assurance for corporations, government bodies, and other conceivable networks. Cyber defense focuses on preventing, detecting, and responding to assaults or threats in a timely manner so that no infrastructure or information is compromised. With the increasing volume and complexity of cyber threats, most companies need cyber defense to protect sensitive information and assets. We can control attacker actions by utilizing firewalls at different levels, an intrusion detection system (IDS), with the intrusion prevention system (IPS) which can be installed independently or in combination with other protection approaches. Tesla is an American clean energy and automotive company in Austin, Texas, USA. The recent data breach at Tesla affected over 75,000 individuals as the company pinpoints two former employees as the offender revealing more than 23,000 internal files from 2015 to 2022. In this work, we will emphasize data modeling and data analysis using cyber defense model and python with a survey of the Tesla company. We have proposed a defense model, DefTesPY, with enhanced data modeling and data analysis based on the encountered cyber-attacks and cybercrimes for Tesla company till date. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.14671v1-abstract-full').style.display = 'none'; document.getElementById('2407.14671v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">11 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.13742">arXiv:2407.13742</a> <span> [<a href="https://arxiv.org/pdf/2407.13742">pdf</a>, <a href="https://arxiv.org/format/2407.13742">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> CellularLint: A Systematic Approach to Identify Inconsistent Behavior in Cellular Network Specifications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mirza Masfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Karim%2C+I">Imtiaz Karim</a>, <a href="/search/cs?searchtype=author&query=Bertino%2C+E">Elisa Bertino</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="2407.13742v1-abstract-short" style="display: inline;"> In recent years, there has been a growing focus on scrutinizing the security of cellular networks, often attributing security vulnerabilities to issues in the underlying protocol design descriptions. These protocol design specifications, typically extensive documents that are thousands of pages long, can harbor inaccuracies, underspecifications, implicit assumptions, and internal inconsistencies.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13742v1-abstract-full').style.display = 'inline'; document.getElementById('2407.13742v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.13742v1-abstract-full" style="display: none;"> In recent years, there has been a growing focus on scrutinizing the security of cellular networks, often attributing security vulnerabilities to issues in the underlying protocol design descriptions. These protocol design specifications, typically extensive documents that are thousands of pages long, can harbor inaccuracies, underspecifications, implicit assumptions, and internal inconsistencies. In light of the evolving landscape, we introduce CellularLint--a semi-automatic framework for inconsistency detection within the standards of 4G and 5G, capitalizing on a suite of natural language processing techniques. Our proposed method uses a revamped few-shot learning mechanism on domain-adapted large language models. Pre-trained on a vast corpus of cellular network protocols, this method enables CellularLint to simultaneously detect inconsistencies at various levels of semantics and practical use cases. In doing so, CellularLint significantly advances the automated analysis of protocol specifications in a scalable fashion. In our investigation, we focused on the Non-Access Stratum (NAS) and the security specifications of 4G and 5G networks, ultimately uncovering 157 inconsistencies with 82.67% accuracy. After verification of these inconsistencies on open-source implementations and 17 commercial devices, we confirm that they indeed have a substantial impact on design decisions, potentially leading to concerns related to privacy, integrity, availability, and interoperability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.13742v1-abstract-full').style.display = 'none'; document.getElementById('2407.13742v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at USENIX Security 24</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.09187">arXiv:2407.09187</a> <span> [<a href="https://arxiv.org/pdf/2407.09187">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Enhancing Depressive Post Detection in Bangla: A Comparative Study of TF-IDF, BERT and FastText Embeddings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Sazan%2C+S+A">Saad Ahmed Sazan</a>, <a href="/search/cs?searchtype=author&query=Miraz%2C+M+H">Mahdi H. Miraz</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+A+B+M+M">A B M Muntasir Rahman</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="2407.09187v1-abstract-short" style="display: inline;"> Due to massive adoption of social media, detection of users' depression through social media analytics bears significant importance, particularly for underrepresented languages, such as Bangla. This study introduces a well-grounded approach to identify depressive social media posts in Bangla, by employing advanced natural language processing techniques. The dataset used in this work, annotated by… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09187v1-abstract-full').style.display = 'inline'; document.getElementById('2407.09187v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.09187v1-abstract-full" style="display: none;"> Due to massive adoption of social media, detection of users' depression through social media analytics bears significant importance, particularly for underrepresented languages, such as Bangla. This study introduces a well-grounded approach to identify depressive social media posts in Bangla, by employing advanced natural language processing techniques. The dataset used in this work, annotated by domain experts, includes both depressive and non-depressive posts, ensuring high-quality data for model training and evaluation. To address the prevalent issue of class imbalance, we utilised random oversampling for the minority class, thereby enhancing the model's ability to accurately detect depressive posts. We explored various numerical representation techniques, including Term Frequency-Inverse Document Frequency (TF-IDF), Bidirectional Encoder Representations from Transformers (BERT) embedding and FastText embedding, by integrating them with a deep learning-based Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) model. The results obtained through extensive experimentation, indicate that the BERT approach performed better the others, achieving a F1-score of 84%. This indicates that BERT, in combination with the CNN-BiLSTM architecture, effectively recognises the nuances of Bangla texts relevant to depressive contents. Comparative analysis with the existing state-of-the-art methods demonstrates that our approach with BERT embedding performs better than others in terms of evaluation metrics and the reliability of dataset annotations. Our research significantly contribution to the development of reliable tools for detecting depressive posts in the Bangla language. By highlighting the efficacy of different embedding techniques and deep learning models, this study paves the way for improved mental health monitoring through social media platforms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.09187v1-abstract-full').style.display = 'none'; document.getElementById('2407.09187v1-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 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.04831">arXiv:2407.04831</a> <span> [<a href="https://arxiv.org/pdf/2407.04831">pdf</a>, <a href="https://arxiv.org/format/2407.04831">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Code Hallucination </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mirza Masfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Kundu%2C+A">Ashish Kundu</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="2407.04831v2-abstract-short" style="display: inline;"> Generative models such as large language models are extensively used as code copilots and for whole program generation. However, the programs they generate often have questionable correctness, authenticity and reliability in terms of integration as they might not follow the user requirements, provide incorrect and/or nonsensical outputs, or even contain semantic/syntactic errors - overall known as… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04831v2-abstract-full').style.display = 'inline'; document.getElementById('2407.04831v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.04831v2-abstract-full" style="display: none;"> Generative models such as large language models are extensively used as code copilots and for whole program generation. However, the programs they generate often have questionable correctness, authenticity and reliability in terms of integration as they might not follow the user requirements, provide incorrect and/or nonsensical outputs, or even contain semantic/syntactic errors - overall known as LLM hallucination. In this work, we present several types of code hallucination. We have generated such hallucinated code manually using large language models. We also present a technique - HallTrigger, in order to demonstrate efficient ways of generating arbitrary code hallucination. Our method leverages 3 different dynamic attributes of LLMs to craft prompts that can successfully trigger hallucinations from models without the need to access model architecture or parameters. Results from popular blackbox models suggest that HallTrigger is indeed effective and the pervasive LLM hallucination have sheer impact on software development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04831v2-abstract-full').style.display = 'none'; document.getElementById('2407.04831v2-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10708">arXiv:2406.10708</a> <span> [<a href="https://arxiv.org/pdf/2406.10708">pdf</a>, <a href="https://arxiv.org/format/2406.10708">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="Databases">cs.DB</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"> MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perception </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">M. Mahbubur Rahman</a>, <a href="/search/cs?searchtype=author&query=Yataka%2C+R">Ryoma Yataka</a>, <a href="/search/cs?searchtype=author&query=Kato%2C+S">Sorachi Kato</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+P+P">Pu Perry Wang</a>, <a href="/search/cs?searchtype=author&query=Li%2C+P">Peizhao Li</a>, <a href="/search/cs?searchtype=author&query=Cardace%2C+A">Adriano Cardace</a>, <a href="/search/cs?searchtype=author&query=Boufounos%2C+P">Petros Boufounos</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="2406.10708v2-abstract-short" style="display: inline;"> Compared with an extensive list of automotive radar datasets that support autonomous driving, indoor radar datasets are scarce at a smaller scale in the format of low-resolution radar point clouds and usually under an open-space single-room setting. In this paper, we scale up indoor radar data collection using multi-view high-resolution radar heatmap in a multi-day, multi-room, and multi-subject s… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10708v2-abstract-full').style.display = 'inline'; document.getElementById('2406.10708v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10708v2-abstract-full" style="display: none;"> Compared with an extensive list of automotive radar datasets that support autonomous driving, indoor radar datasets are scarce at a smaller scale in the format of low-resolution radar point clouds and usually under an open-space single-room setting. In this paper, we scale up indoor radar data collection using multi-view high-resolution radar heatmap in a multi-day, multi-room, and multi-subject setting, with an emphasis on the diversity of environment and subjects. Referred to as the millimeter-wave multi-view radar (MMVR) dataset, it consists of $345$K multi-view radar frames collected from $25$ human subjects over $6$ different rooms, $446$K annotated bounding boxes/segmentation instances, and $7.59$ million annotated keypoints to support three major perception tasks of object detection, pose estimation, and instance segmentation, respectively. For each task, we report performance benchmarks under two protocols: a single subject in an open space and multiple subjects in several cluttered rooms with two data splits: random split and cross-environment split over $395$ 1-min data segments. We anticipate that MMVR facilitates indoor radar perception development for indoor vehicle (robot/humanoid) navigation, building energy management, and elderly care for better efficiency, user experience, and safety. The MMVR dataset is available at https://doi.org/10.5281/zenodo.12611978. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10708v2-abstract-full').style.display = 'none'; document.getElementById('2406.10708v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 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">26 pages, 25 figures, 10 tables; See https://doi.org/10.5281/zenodo.12611978 to access the MMVR dataset</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.08534">arXiv:2406.08534</a> <span> [<a href="https://arxiv.org/pdf/2406.08534">pdf</a>, <a href="https://arxiv.org/ps/2406.08534">ps</a>, <a href="https://arxiv.org/format/2406.08534">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Optimizing Container Loading and Unloading through Dual-Cycling and Dockyard Rehandle Reduction Using a Hybrid Genetic Algorithm </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mahfuzur Rahman</a>, <a href="/search/cs?searchtype=author&query=Jahin%2C+M+A">Md Abrar Jahin</a>, <a href="/search/cs?searchtype=author&query=Islam%2C+M+S">Md. Saiful Islam</a>, <a href="/search/cs?searchtype=author&query=Mridha%2C+M+F">M. F. Mridha</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="2406.08534v1-abstract-short" style="display: inline;"> This paper addresses the optimization of container unloading and loading operations at ports, integrating quay-crane dual-cycling with dockyard rehandle minimization. We present a unified model encompassing both operations: ship container unloading and loading by quay crane, and the other is reducing dockyard rehandles while loading the ship. We recognize that optimizing one aspect in isolation ca… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.08534v1-abstract-full').style.display = 'inline'; document.getElementById('2406.08534v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.08534v1-abstract-full" style="display: none;"> This paper addresses the optimization of container unloading and loading operations at ports, integrating quay-crane dual-cycling with dockyard rehandle minimization. We present a unified model encompassing both operations: ship container unloading and loading by quay crane, and the other is reducing dockyard rehandles while loading the ship. We recognize that optimizing one aspect in isolation can lead to suboptimal outcomes due to interdependencies. Specifically, optimizing unloading sequences for minimal operation time may inadvertently increase dockyard rehandles during loading and vice versa. To address this NP-hard problem, we propose a hybrid genetic algorithm (GA) QCDC-DR-GA comprising one-dimensional and two-dimensional GA components. Our model, QCDC-DR-GA, consistently outperforms four state-of-the-art methods in maximizing dual cycles and minimizing dockyard rehandles. Compared to those methods, it reduced 15-20% of total operation time for large vessels. Statistical validation through a two-tailed paired t-test confirms the superiority of QCDC-DR-GA at a 5% significance level. The approach effectively combines QCDC optimization with dockyard rehandle minimization, optimizing the total unloading-loading time. Results underscore the inefficiency of separately optimizing QCDC and dockyard rehandles. Fragmented approaches, such as QCDC Scheduling Optimized by bi-level GA and GA-ILSRS (Scenario 2), show limited improvement compared to QCDC-DR-GA. As in GA-ILSRS (Scenario 1), neglecting dual-cycle optimization leads to inferior performance than QCDC-DR-GA. This emphasizes the necessity of simultaneously considering both aspects for optimal resource utilization and overall operational efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.08534v1-abstract-full').style.display = 'none'; document.getElementById('2406.08534v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.05151">arXiv:2406.05151</a> <span> [<a href="https://arxiv.org/pdf/2406.05151">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> CredSec: A Blockchain-based Secure Credential Management System for University Adoption </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Habib%2C+M+A">Md. Ahsan Habib</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mostafijur Rahman</a>, <a href="/search/cs?searchtype=author&query=Neom%2C+N+H">Nieb Hasan Neom</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="2406.05151v1-abstract-short" style="display: inline;"> University education play a critical role in shaping intellectual and professional development of the individuals and contribute significantly to the advancement of knowledge and society. Generally, university authority has a direct control of students result making and stores the credential in their local dedicated server. So, there is chance to alter the credential and also have a very high poss… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05151v1-abstract-full').style.display = 'inline'; document.getElementById('2406.05151v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05151v1-abstract-full" style="display: none;"> University education play a critical role in shaping intellectual and professional development of the individuals and contribute significantly to the advancement of knowledge and society. Generally, university authority has a direct control of students result making and stores the credential in their local dedicated server. So, there is chance to alter the credential and also have a very high possibility to encounter various threats and different security attacks. To resolve these, we propose a blockchain based secure credential management system (BCMS) for efficiently storing, managing and recovering credential without involving the university authority. The proposed BCMS incorporates a modified two factor encryption (m2FE) technique, a combination of RSA cryptosystem and a DNA encoding to ensure credential privacy and an enhanced authentication scheme for teachers and students. Besides, to reduce size of the cipher credential and its conversion time, we use character to integer (C2I) table instead of ASCII table. Finally, the experimental result and analysis of the BCMS illustrate the effectiveness over state of the art works. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05151v1-abstract-full').style.display = 'none'; document.getElementById('2406.05151v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages, 7 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/2406.00367">arXiv:2406.00367</a> <span> [<a href="https://arxiv.org/pdf/2406.00367">pdf</a>, <a href="https://arxiv.org/format/2406.00367">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> </div> </div> <p class="title is-5 mathjax"> RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mostafizer Rahman</a>, <a href="/search/cs?searchtype=author&query=Shiplu%2C+A+I">Ariful Islam Shiplu</a>, <a href="/search/cs?searchtype=author&query=Watanobe%2C+Y">Yutaka Watanobe</a>, <a href="/search/cs?searchtype=author&query=Alam%2C+M+A">Md. Ashad Alam</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="2406.00367v1-abstract-short" style="display: inline;"> Effectively analyzing the comments to uncover latent intentions holds immense value in making strategic decisions across various domains. However, several challenges hinder the process of sentiment analysis including the lexical diversity exhibited in comments, the presence of long dependencies within the text, encountering unknown symbols and words, and dealing with imbalanced datasets. Moreover,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00367v1-abstract-full').style.display = 'inline'; document.getElementById('2406.00367v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00367v1-abstract-full" style="display: none;"> Effectively analyzing the comments to uncover latent intentions holds immense value in making strategic decisions across various domains. However, several challenges hinder the process of sentiment analysis including the lexical diversity exhibited in comments, the presence of long dependencies within the text, encountering unknown symbols and words, and dealing with imbalanced datasets. Moreover, existing sentiment analysis tasks mostly leveraged sequential models to encode the long dependent texts and it requires longer execution time as it processes the text sequentially. In contrast, the Transformer requires less execution time due to its parallel processing nature. In this work, we introduce a novel hybrid deep learning model, RoBERTa-BiLSTM, which combines the Robustly Optimized BERT Pretraining Approach (RoBERTa) with Bidirectional Long Short-Term Memory (BiLSTM) networks. RoBERTa is utilized to generate meaningful word embedding vectors, while BiLSTM effectively captures the contextual semantics of long-dependent texts. The RoBERTa-BiLSTM hybrid model leverages the strengths of both sequential and Transformer models to enhance performance in sentiment analysis. We conducted experiments using datasets from IMDb, Twitter US Airline, and Sentiment140 to evaluate the proposed model against existing state-of-the-art methods. Our experimental findings demonstrate that the RoBERTa-BiLSTM model surpasses baseline models (e.g., BERT, RoBERTa-base, RoBERTa-GRU, and RoBERTa-LSTM), achieving accuracies of 80.74%, 92.36%, and 82.25% on the Twitter US Airline, IMDb, and Sentiment140 datasets, respectively. Additionally, the model achieves F1-scores of 80.73%, 92.35%, and 82.25% on the same datasets, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00367v1-abstract-full').style.display = 'none'; document.getElementById('2406.00367v1-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, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.16740">arXiv:2405.16740</a> <span> [<a href="https://arxiv.org/pdf/2405.16740">pdf</a>, <a href="https://arxiv.org/format/2405.16740">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> </div> </div> <p class="title is-5 mathjax"> PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mostafijur Rahman</a>, <a href="/search/cs?searchtype=author&query=Munir%2C+M">Mustafa Munir</a>, <a href="/search/cs?searchtype=author&query=Jha%2C+D">Debesh Jha</a>, <a href="/search/cs?searchtype=author&query=Bagci%2C+U">Ulas Bagci</a>, <a href="/search/cs?searchtype=author&query=Marculescu%2C+R">Radu Marculescu</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="2405.16740v1-abstract-short" style="display: inline;"> The Segment Anything Model (SAM), originally designed for general-purpose segmentation tasks, has been used recently for polyp segmentation. Nonetheless, fine-tuning SAM with data from new imaging centers or clinics poses significant challenges. This is because this necessitates the creation of an expensive and time-intensive annotated dataset, along with the potential for variability in user prom… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16740v1-abstract-full').style.display = 'inline'; document.getElementById('2405.16740v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.16740v1-abstract-full" style="display: none;"> The Segment Anything Model (SAM), originally designed for general-purpose segmentation tasks, has been used recently for polyp segmentation. Nonetheless, fine-tuning SAM with data from new imaging centers or clinics poses significant challenges. This is because this necessitates the creation of an expensive and time-intensive annotated dataset, along with the potential for variability in user prompts during inference. To address these issues, we propose a robust fine-tuning technique, PP-SAM, that allows SAM to adapt to the polyp segmentation task with limited images. To this end, we utilize variable perturbed bounding box prompts (BBP) to enrich the learning context and enhance the model's robustness to BBP perturbations during inference. Rigorous experiments on polyp segmentation benchmarks reveal that our variable BBP perturbation significantly improves model resilience. Notably, on Kvasir, 1-shot fine-tuning boosts the DICE score by 20% and 37% with 50 and 100-pixel BBP perturbations during inference, respectively. Moreover, our experiments show that 1-shot, 5-shot, and 10-shot PP-SAM with 50-pixel perturbations during inference outperform a recent state-of-the-art (SOTA) polyp segmentation method by 26%, 7%, and 5% DICE scores, respectively. Our results motivate the broader applicability of our PP-SAM for other medical imaging tasks with limited samples. Our implementation is available at https://github.com/SLDGroup/PP-SAM. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.16740v1-abstract-full').style.display = 'none'; document.getElementById('2405.16740v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 9 figures, Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.06880">arXiv:2405.06880</a> <span> [<a href="https://arxiv.org/pdf/2405.06880">pdf</a>, <a href="https://arxiv.org/format/2405.06880">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"> EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mostafijur Rahman</a>, <a href="/search/cs?searchtype=author&query=Munir%2C+M">Mustafa Munir</a>, <a href="/search/cs?searchtype=author&query=Marculescu%2C+R">Radu Marculescu</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="2405.06880v1-abstract-short" style="display: inline;"> An efficient and effective decoding mechanism is crucial in medical image segmentation, especially in scenarios with limited computational resources. However, these decoding mechanisms usually come with high computational costs. To address this concern, we introduce EMCAD, a new efficient multi-scale convolutional attention decoder, designed to optimize both performance and computational efficienc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06880v1-abstract-full').style.display = 'inline'; document.getElementById('2405.06880v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.06880v1-abstract-full" style="display: none;"> An efficient and effective decoding mechanism is crucial in medical image segmentation, especially in scenarios with limited computational resources. However, these decoding mechanisms usually come with high computational costs. To address this concern, we introduce EMCAD, a new efficient multi-scale convolutional attention decoder, designed to optimize both performance and computational efficiency. EMCAD leverages a unique multi-scale depth-wise convolution block, significantly enhancing feature maps through multi-scale convolutions. EMCAD also employs channel, spatial, and grouped (large-kernel) gated attention mechanisms, which are highly effective at capturing intricate spatial relationships while focusing on salient regions. By employing group and depth-wise convolution, EMCAD is very efficient and scales well (e.g., only 1.91M parameters and 0.381G FLOPs are needed when using a standard encoder). Our rigorous evaluations across 12 datasets that belong to six medical image segmentation tasks reveal that EMCAD achieves state-of-the-art (SOTA) performance with 79.4% and 80.3% reduction in #Params and #FLOPs, respectively. Moreover, EMCAD's adaptability to different encoders and versatility across segmentation tasks further establish EMCAD as a promising tool, advancing the field towards more efficient and accurate medical image analysis. Our implementation is available at https://github.com/SLDGroup/EMCAD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06880v1-abstract-full').style.display = 'none'; document.getElementById('2405.06880v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">14 pages, 5 figures, 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.06849">arXiv:2405.06849</a> <span> [<a href="https://arxiv.org/pdf/2405.06849">pdf</a>, <a href="https://arxiv.org/format/2405.06849">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="Artificial Intelligence">cs.AI</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"> GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Munir%2C+M">Mustafa Munir</a>, <a href="/search/cs?searchtype=author&query=Avery%2C+W">William Avery</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mostafijur Rahman</a>, <a href="/search/cs?searchtype=author&query=Marculescu%2C+R">Radu Marculescu</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="2405.06849v1-abstract-short" style="display: inline;"> Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06849v1-abstract-full').style.display = 'inline'; document.getElementById('2405.06849v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.06849v1-abstract-full" style="display: none;"> Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNN-GNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06849v1-abstract-full').style.display = 'none'; document.getElementById('2405.06849v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 May, 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">Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2405.06166">arXiv:2405.06166</a> <span> [<a href="https://arxiv.org/pdf/2405.06166">pdf</a>, <a href="https://arxiv.org/format/2405.06166">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"> MDNet: Multi-Decoder Network for Abdominal CT Organs Segmentation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jha%2C+D">Debesh Jha</a>, <a href="/search/cs?searchtype=author&query=Tomar%2C+N+K">Nikhil Kumar Tomar</a>, <a href="/search/cs?searchtype=author&query=Biswas%2C+K">Koushik Biswas</a>, <a href="/search/cs?searchtype=author&query=Durak%2C+G">Gorkem Durak</a>, <a href="/search/cs?searchtype=author&query=Antalek%2C+M">Matthew Antalek</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zheyuan Zhang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+B">Bin Wang</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mostafijur Rahman</a>, <a href="/search/cs?searchtype=author&query=Pan%2C+H">Hongyi Pan</a>, <a href="/search/cs?searchtype=author&query=Medetalibeyoglu%2C+A">Alpay Medetalibeyoglu</a>, <a href="/search/cs?searchtype=author&query=Velichko%2C+Y">Yury Velichko</a>, <a href="/search/cs?searchtype=author&query=Ladner%2C+D">Daniela Ladner</a>, <a href="/search/cs?searchtype=author&query=Borhani%2C+A">Amir Borhani</a>, <a href="/search/cs?searchtype=author&query=Bagci%2C+U">Ulas Bagci</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="2405.06166v1-abstract-short" style="display: inline;"> Accurate segmentation of organs from abdominal CT scans is essential for clinical applications such as diagnosis, treatment planning, and patient monitoring. To handle challenges of heterogeneity in organ shapes, sizes, and complex anatomical relationships, we propose a \textbf{\textit{\ac{MDNet}}}, an encoder-decoder network that uses the pre-trained \textit{MiT-B2} as the encoder and multiple di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06166v1-abstract-full').style.display = 'inline'; document.getElementById('2405.06166v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.06166v1-abstract-full" style="display: none;"> Accurate segmentation of organs from abdominal CT scans is essential for clinical applications such as diagnosis, treatment planning, and patient monitoring. To handle challenges of heterogeneity in organ shapes, sizes, and complex anatomical relationships, we propose a \textbf{\textit{\ac{MDNet}}}, an encoder-decoder network that uses the pre-trained \textit{MiT-B2} as the encoder and multiple different decoder networks. Each decoder network is connected to a different part of the encoder via a multi-scale feature enhancement dilated block. With each decoder, we increase the depth of the network iteratively and refine segmentation masks, enriching feature maps by integrating previous decoders' feature maps. To refine the feature map further, we also utilize the predicted masks from the previous decoder to the current decoder to provide spatial attention across foreground and background regions. MDNet effectively refines the segmentation mask with a high dice similarity coefficient (DSC) of 0.9013 and 0.9169 on the Liver Tumor segmentation (LiTS) and MSD Spleen datasets. Additionally, it reduces Hausdorff distance (HD) to 3.79 for the LiTS dataset and 2.26 for the spleen segmentation dataset, underscoring the precision of MDNet in capturing the complex contours. Moreover, \textit{\ac{MDNet}} is more interpretable and robust compared to the other baseline models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.06166v1-abstract-full').style.display = 'none'; document.getElementById('2405.06166v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.15451">arXiv:2404.15451</a> <span> [<a href="https://arxiv.org/pdf/2404.15451">pdf</a>, <a href="https://arxiv.org/format/2404.15451">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> </div> </div> <p class="title is-5 mathjax"> CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Cai%2C+H">Hongyi Cai</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Mahdinur Rahman</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Jingyu Wu</a>, <a href="/search/cs?searchtype=author&query=Deng%2C+Y">Yulun Deng</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="2404.15451v1-abstract-short" style="display: inline;"> Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection. However, the currently existing models generally focus on the Encoder-side Transformer to extract features, from which decoder improvement can bring further potential with well-designed architecture. We propose CFPFormer, a novel decoder… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15451v1-abstract-full').style.display = 'inline'; document.getElementById('2404.15451v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.15451v1-abstract-full" style="display: none;"> Feature pyramids have been widely adopted in convolutional neural networks (CNNs) and transformers for tasks like medical image segmentation and object detection. However, the currently existing models generally focus on the Encoder-side Transformer to extract features, from which decoder improvement can bring further potential with well-designed architecture. We propose CFPFormer, a novel decoder block that integrates feature pyramids and transformers. Specifically, by leveraging patch embedding, cross-layer feature concatenation, and Gaussian attention mechanisms, CFPFormer enhances feature extraction capabilities while promoting generalization across diverse tasks. Benefiting from Transformer structure and U-shaped Connections, our introduced model gains the ability to capture long-range dependencies and effectively up-sample feature maps. Our model achieves superior performance in detecting small objects compared to existing methods. We evaluate CFPFormer on medical image segmentation datasets and object detection benchmarks (VOC 2007, VOC2012, MS-COCO), demonstrating its effectiveness and versatility. On the ACDC Post-2017-MICCAI-Challenge online test set, our model reaches exceptionally impressive accuracy, and performed well compared with the original decoder setting in Synapse multi-organ segmentation dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15451v1-abstract-full').style.display = 'none'; document.getElementById('2404.15451v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 23 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.07831">arXiv:2404.07831</a> <span> [<a href="https://arxiv.org/pdf/2404.07831">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> </div> </div> <p class="title is-5 mathjax"> Protected QR Code-based Anti-counterfeit System for Pharmaceutical Manufacturing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aulia%2C+M+M">Md Masruk Aulia</a>, <a href="/search/cs?searchtype=author&query=Saha%2C+N">Nitol Saha</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mostafizur Rahman</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="2404.07831v3-abstract-short" style="display: inline;"> The pharmaceutical manufacturing faces critical challenges due to the global threat of counterfeit drugs. This paper proposes a new approach of protected QR codes to secure unique product information for safeguarding the pharmaceutical supply chain. The proposed solution integrates secure QR code generation and encrypted data transmission to establish a comprehensive anti-counterfeit ecosystem. Th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07831v3-abstract-full').style.display = 'inline'; document.getElementById('2404.07831v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.07831v3-abstract-full" style="display: none;"> The pharmaceutical manufacturing faces critical challenges due to the global threat of counterfeit drugs. This paper proposes a new approach of protected QR codes to secure unique product information for safeguarding the pharmaceutical supply chain. The proposed solution integrates secure QR code generation and encrypted data transmission to establish a comprehensive anti-counterfeit ecosystem. The protected QR codes encapsulate product information that cannot be identified using traditional QR code scanners which protect the information against replication and tampering. The system is developed with scalability in mind, which can be easily implemented without introducing any additional modification in the traditional supply chain. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.07831v3-abstract-full').style.display = 'none'; document.getElementById('2404.07831v3-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.03606">arXiv:2404.03606</a> <span> [<a href="https://arxiv.org/pdf/2404.03606">pdf</a>, <a href="https://arxiv.org/format/2404.03606">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</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"> Analyzing Musical Characteristics of National Anthems in Relation to Global Indices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hasan%2C+S+M+R">S M Rakib Hasan</a>, <a href="/search/cs?searchtype=author&query=Dhakal%2C+A">Aakar Dhakal</a>, <a href="/search/cs?searchtype=author&query=Siddiqua%2C+M+A">Ms. Ayesha Siddiqua</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Mominur Rahman</a>, <a href="/search/cs?searchtype=author&query=Islam%2C+M+M">Md Maidul Islam</a>, <a href="/search/cs?searchtype=author&query=Chowdhury%2C+M+A+R">Mohammed Arfat Raihan Chowdhury</a>, <a href="/search/cs?searchtype=author&query=Swapno%2C+S+M+M+R">S M Masfequier Rahman Swapno</a>, <a href="/search/cs?searchtype=author&query=Nobel%2C+S+N">SM Nuruzzaman Nobel</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="2404.03606v1-abstract-short" style="display: inline;"> Music plays a huge part in shaping peoples' psychology and behavioral patterns. This paper investigates the connection between national anthems and different global indices with computational music analysis and statistical correlation analysis. We analyze national anthem musical data to determine whether certain musical characteristics are associated with peace, happiness, suicide rate, crime rate… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03606v1-abstract-full').style.display = 'inline'; document.getElementById('2404.03606v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.03606v1-abstract-full" style="display: none;"> Music plays a huge part in shaping peoples' psychology and behavioral patterns. This paper investigates the connection between national anthems and different global indices with computational music analysis and statistical correlation analysis. We analyze national anthem musical data to determine whether certain musical characteristics are associated with peace, happiness, suicide rate, crime rate, etc. To achieve this, we collect national anthems from 169 countries and use computational music analysis techniques to extract pitch, tempo, beat, and other pertinent audio features. We then compare these musical characteristics with data on different global indices to ascertain whether a significant correlation exists. Our findings indicate that there may be a correlation between the musical characteristics of national anthems and the indices we investigated. The implications of our findings for music psychology and policymakers interested in promoting social well-being are discussed. This paper emphasizes the potential of musical data analysis in social research and offers a novel perspective on the relationship between music and social indices. The source code and data are made open-access for reproducibility and future research endeavors. It can be accessed at http://bit.ly/na_code. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.03606v1-abstract-full').style.display = 'none'; document.getElementById('2404.03606v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01347">arXiv:2404.01347</a> <span> [<a href="https://arxiv.org/pdf/2404.01347">pdf</a>, <a href="https://arxiv.org/format/2404.01347">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</span> </div> </div> <p class="title is-5 mathjax"> Mining Sequential Patterns in Uncertain Databases Using Hierarchical Index Structure </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roy%2C+K+K">Kashob Kumar Roy</a>, <a href="/search/cs?searchtype=author&query=Moon%2C+M+H+H">Md Hasibul Haque Moon</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mahmudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+C+F">Chowdhury Farhan Ahmed</a>, <a href="/search/cs?searchtype=author&query=Leung%2C+C+K">Carson K. Leung</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="2404.01347v1-abstract-short" style="display: inline;"> In this uncertain world, data uncertainty is inherent in many applications and its importance is growing drastically due to the rapid development of modern technologies. Nowadays, researchers have paid more attention to mine patterns in uncertain databases. A few recent works attempt to mine frequent uncertain sequential patterns. Despite their success, they are incompetent to reduce the number of… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01347v1-abstract-full').style.display = 'inline'; document.getElementById('2404.01347v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01347v1-abstract-full" style="display: none;"> In this uncertain world, data uncertainty is inherent in many applications and its importance is growing drastically due to the rapid development of modern technologies. Nowadays, researchers have paid more attention to mine patterns in uncertain databases. A few recent works attempt to mine frequent uncertain sequential patterns. Despite their success, they are incompetent to reduce the number of false-positive pattern generation in their mining process and maintain the patterns efficiently. In this paper, we propose multiple theoretically tightened pruning upper bounds that remarkably reduce the mining space. A novel hierarchical structure is introduced to maintain the patterns in a space-efficient way. Afterward, we develop a versatile framework for mining uncertain sequential patterns that can effectively handle weight constraints as well. Besides, with the advent of incremental uncertain databases, existing works are not scalable. There exist several incremental sequential pattern mining algorithms, but they are limited to mine in precise databases. Therefore, we propose a new technique to adapt our framework to mine patterns when the database is incremental. Finally, we conduct extensive experiments on several real-life datasets and show the efficacy of our framework in different applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01347v1-abstract-full').style.display = 'none'; document.getElementById('2404.01347v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 March, 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">Accepted at PAKDD 2021. arXiv admin note: text overlap with arXiv:2404.00746</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.00746">arXiv:2404.00746</a> <span> [<a href="https://arxiv.org/pdf/2404.00746">pdf</a>, <a href="https://arxiv.org/format/2404.00746">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</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"> Mining Weighted Sequential Patterns in Incremental Uncertain Databases </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Roy%2C+K+K">Kashob Kumar Roy</a>, <a href="/search/cs?searchtype=author&query=Moon%2C+M+H+H">Md Hasibul Haque Moon</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mahmudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+C+F">Chowdhury Farhan Ahmed</a>, <a href="/search/cs?searchtype=author&query=Leung%2C+C+K">Carson Kai-Sang Leung</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="2404.00746v1-abstract-short" style="display: inline;"> Due to the rapid development of science and technology, the importance of imprecise, noisy, and uncertain data is increasing at an exponential rate. Thus, mining patterns in uncertain databases have drawn the attention of researchers. Moreover, frequent sequences of items from these databases need to be discovered for meaningful knowledge with great impact. In many real cases, weights of items and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00746v1-abstract-full').style.display = 'inline'; document.getElementById('2404.00746v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.00746v1-abstract-full" style="display: none;"> Due to the rapid development of science and technology, the importance of imprecise, noisy, and uncertain data is increasing at an exponential rate. Thus, mining patterns in uncertain databases have drawn the attention of researchers. Moreover, frequent sequences of items from these databases need to be discovered for meaningful knowledge with great impact. In many real cases, weights of items and patterns are introduced to find interesting sequences as a measure of importance. Hence, a constraint of weight needs to be handled while mining sequential patterns. Besides, due to the dynamic nature of databases, mining important information has become more challenging. Instead of mining patterns from scratch after each increment, incremental mining algorithms utilize previously mined information to update the result immediately. Several algorithms exist to mine frequent patterns and weighted sequences from incremental databases. However, these algorithms are confined to mine the precise ones. Therefore, we have developed an algorithm to mine frequent sequences in an uncertain database in this work. Furthermore, we have proposed two new techniques for mining when the database is incremental. Extensive experiments have been conducted for performance evaluation. The analysis showed the efficiency of our proposed framework. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00746v1-abstract-full').style.display = 'none'; document.getElementById('2404.00746v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 March, 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">Accepted to Information Science journal</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Information Sciences 582 (2022): 865-896 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.17218">arXiv:2403.17218</a> <span> [<a href="https://arxiv.org/pdf/2403.17218">pdf</a>, <a href="https://arxiv.org/format/2403.17218">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</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> <p class="title is-5 mathjax"> A Comprehensive Study of the Capabilities of Large Language Models for Vulnerability Detection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Steenhoek%2C+B">Benjamin Steenhoek</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mahbubur Rahman</a>, <a href="/search/cs?searchtype=author&query=Roy%2C+M+K">Monoshi Kumar Roy</a>, <a href="/search/cs?searchtype=author&query=Alam%2C+M+S">Mirza Sanjida Alam</a>, <a href="/search/cs?searchtype=author&query=Barr%2C+E+T">Earl T. Barr</a>, <a href="/search/cs?searchtype=author&query=Le%2C+W">Wei Le</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="2403.17218v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have demonstrated great potential for code generation and other software engineering tasks. Vulnerability detection is of crucial importance to maintaining the security, integrity, and trustworthiness of software systems. Precise vulnerability detection requires reasoning about the code, making it a good case study for exploring the limits of LLMs' reasoning capabiliti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17218v1-abstract-full').style.display = 'inline'; document.getElementById('2403.17218v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.17218v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have demonstrated great potential for code generation and other software engineering tasks. Vulnerability detection is of crucial importance to maintaining the security, integrity, and trustworthiness of software systems. Precise vulnerability detection requires reasoning about the code, making it a good case study for exploring the limits of LLMs' reasoning capabilities. Although recent work has applied LLMs to vulnerability detection using generic prompting techniques, their full capabilities for this task and the types of errors they make when explaining identified vulnerabilities remain unclear. In this paper, we surveyed eleven LLMs that are state-of-the-art in code generation and commonly used as coding assistants, and evaluated their capabilities for vulnerability detection. We systematically searched for the best-performing prompts, incorporating techniques such as in-context learning and chain-of-thought, and proposed three of our own prompting methods. Our results show that while our prompting methods improved the models' performance, LLMs generally struggled with vulnerability detection. They reported 0.5-0.63 Balanced Accuracy and failed to distinguish between buggy and fixed versions of programs in 76% of cases on average. By comprehensively analyzing and categorizing 287 instances of model reasoning, we found that 57% of LLM responses contained errors, and the models frequently predicted incorrect locations of buggy code and misidentified bug types. LLMs only correctly localized 6 out of 27 bugs in DbgBench, and these 6 bugs were predicted correctly by 70-100% of human participants. These findings suggest that despite their potential for other tasks, LLMs may fail to properly comprehend critical code structures and security-related concepts. Our data and code are available at https://figshare.com/s/78fe02e56e09ec49300b. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.17218v1-abstract-full').style.display = 'none'; document.getElementById('2403.17218v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.14565">arXiv:2402.14565</a> <span> [<a href="https://arxiv.org/pdf/2402.14565">pdf</a>, <a href="https://arxiv.org/format/2402.14565">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="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Non-Contact Acquisition of PPG Signal using Chest Movement-Modulated Radio Signals </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Filho%2C+I+J+S">Israel Jesus Santos Filho</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M+U">Muhammad Mahboob Ur Rahman</a>, <a href="/search/cs?searchtype=author&query=Laleg-Kirati%2C+T">Taous-Meriem Laleg-Kirati</a>, <a href="/search/cs?searchtype=author&query=Al-Naffouri%2C+T">Tareq Al-Naffouri</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="2402.14565v1-abstract-short" style="display: inline;"> We present for the first time a novel method that utilizes the chest movement-modulated radio signals for non-contact acquisition of the photoplethysmography (PPG) signal. Under the proposed method, a software-defined radio (SDR) exposes the chest of a subject sitting nearby to an orthogonal frequency division multiplexing signal with 64 sub-carriers at a center frequency 5.24 GHz, while another S… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14565v1-abstract-full').style.display = 'inline'; document.getElementById('2402.14565v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.14565v1-abstract-full" style="display: none;"> We present for the first time a novel method that utilizes the chest movement-modulated radio signals for non-contact acquisition of the photoplethysmography (PPG) signal. Under the proposed method, a software-defined radio (SDR) exposes the chest of a subject sitting nearby to an orthogonal frequency division multiplexing signal with 64 sub-carriers at a center frequency 5.24 GHz, while another SDR in the close vicinity collects the modulated radio signal reflected off the chest. This way, we construct a custom dataset by collecting 160 minutes of labeled data (both raw radio data as well as the reference PPG signal) from 16 healthy young subjects. With this, we first utilize principal component analysis for dimensionality reduction of the radio data. Next, we denoise the radio signal and reference PPG signal using wavelet technique, followed by segmentation and Z-score normalization. We then synchronize the radio and PPG segments using cross-correlation method. Finally, we proceed to the waveform translation (regression) task, whereby we first convert the radio and PPG segments into frequency domain using discrete cosine transform (DCT), and then learn the non-linear regression between them. Eventually, we reconstruct the synthetic PPG signal by taking inverse DCT of the output of regression block, with a mean absolute error of 8.1294. The synthetic PPG waveform has a great clinical significance as it could be used for non-contact performance assessment of cardiovascular and respiratory systems of patients suffering from infectious diseases, e.g., covid19. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14565v1-abstract-full').style.display = 'none'; document.getElementById('2402.14565v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 February, 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">5 pages, 5 figures, under review with a conference</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.09795">arXiv:2402.09795</a> <span> [<a href="https://arxiv.org/pdf/2402.09795">pdf</a>, <a href="https://arxiv.org/format/2402.09795">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Databases">cs.DB</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.inffus.2023.102004">10.1016/j.inffus.2023.102004 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> An advanced data fabric architecture leveraging homomorphic encryption and federated learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rieyan%2C+S+A">Sakib Anwar Rieyan</a>, <a href="/search/cs?searchtype=author&query=News%2C+M+R+K">Md. Raisul Kabir News</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+A+B+M+M">A. B. M. Muntasir Rahman</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+S+A">Sadia Afrin Khan</a>, <a href="/search/cs?searchtype=author&query=Zaarif%2C+S+T+J">Sultan Tasneem Jawad Zaarif</a>, <a href="/search/cs?searchtype=author&query=Alam%2C+M+G+R">Md. Golam Rabiul Alam</a>, <a href="/search/cs?searchtype=author&query=Hassan%2C+M+M">Mohammad Mehedi Hassan</a>, <a href="/search/cs?searchtype=author&query=Ianni%2C+M">Michele Ianni</a>, <a href="/search/cs?searchtype=author&query=Fortino%2C+G">Giancarlo Fortino</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="2402.09795v1-abstract-short" style="display: inline;"> Data fabric is an automated and AI-driven data fusion approach to accomplish data management unification without moving data to a centralized location for solving complex data problems. In a Federated learning architecture, the global model is trained based on the learned parameters of several local models that eliminate the necessity of moving data to a centralized repository for machine learning… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09795v1-abstract-full').style.display = 'inline'; document.getElementById('2402.09795v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.09795v1-abstract-full" style="display: none;"> Data fabric is an automated and AI-driven data fusion approach to accomplish data management unification without moving data to a centralized location for solving complex data problems. In a Federated learning architecture, the global model is trained based on the learned parameters of several local models that eliminate the necessity of moving data to a centralized repository for machine learning. This paper introduces a secure approach for medical image analysis using federated learning and partially homomorphic encryption within a distributed data fabric architecture. With this method, multiple parties can collaborate in training a machine-learning model without exchanging raw data but using the learned or fused features. The approach complies with laws and regulations such as HIPAA and GDPR, ensuring the privacy and security of the data. The study demonstrates the method's effectiveness through a case study on pituitary tumor classification, achieving a significant level of accuracy. However, the primary focus of the study is on the development and evaluation of federated learning and partially homomorphic encryption as tools for secure medical image analysis. The results highlight the potential of these techniques to be applied to other privacy-sensitive domains and contribute to the growing body of research on secure and privacy-preserving machine learning. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.09795v1-abstract-full').style.display = 'none'; document.getElementById('2402.09795v1-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">Journal ref:</span> Information Fusion, 102, 102004 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07419">arXiv:2402.07419</a> <span> [<a href="https://arxiv.org/pdf/2402.07419">pdf</a>, <a href="https://arxiv.org/format/2402.07419">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Musfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Jordan%2C+M">Matt Jordan</a>, <a href="/search/cs?searchtype=author&query=Kocaoglu%2C+M">Murat Kocaoglu</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="2402.07419v2-abstract-short" style="display: inline;"> Causal inference from observational data plays critical role in many applications in trustworthy machine learning. While sound and complete algorithms exist to compute causal effects, many of them assume access to conditional likelihoods, which is difficult to estimate for high-dimensional (particularly image) data. Researchers have alleviated this issue by simulating causal relations with neural… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07419v2-abstract-full').style.display = 'inline'; document.getElementById('2402.07419v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07419v2-abstract-full" style="display: none;"> Causal inference from observational data plays critical role in many applications in trustworthy machine learning. While sound and complete algorithms exist to compute causal effects, many of them assume access to conditional likelihoods, which is difficult to estimate for high-dimensional (particularly image) data. Researchers have alleviated this issue by simulating causal relations with neural models. However, when we have high-dimensional variables in the causal graph along with some unobserved confounders, no existing work can effectively sample from the un/conditional interventional distributions. In this work, we show how to sample from any identifiable interventional distribution given an arbitrary causal graph through a sequence of push-forward computations of conditional generative models, such as diffusion models. Our proposed algorithm follows the recursive steps of the existing likelihood-based identification algorithms to train a set of feed-forward models, and connect them in a specific way to sample from the desired distribution. We conduct experiments on a Colored MNIST dataset having both the treatment ($X$) and the target variables ($Y$) as images and sample from $P(y|do(x))$. Our algorithm also enables us to conduct a causal analysis to evaluate spurious correlations among input features of generative models pre-trained on the CelebA dataset. Finally, we generate high-dimensional interventional samples from the MIMIC-CXR dataset involving text and image variables. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07419v2-abstract-full').style.display = 'none'; document.getElementById('2402.07419v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 31 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 12 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/2402.07054">arXiv:2402.07054</a> <span> [<a href="https://arxiv.org/pdf/2402.07054">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Networking and Internet Architecture">cs.NI</span> </div> </div> <p class="title is-5 mathjax"> HNMblock: Blockchain technology powered Healthcare Network Model for epidemiological monitoring, medical systems security, and wellness </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kshetri%2C+N">Naresh Kshetri</a>, <a href="/search/cs?searchtype=author&query=Mishra%2C+R">Rahul Mishra</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mir Mehedi Rahman</a>, <a href="/search/cs?searchtype=author&query=Steigner%2C+T">Tanja Steigner</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="2402.07054v1-abstract-short" style="display: inline;"> In the ever-evolving healthcare sector, the widespread adoption of Internet of Things and wearable technologies facilitates remote patient monitoring. However, the existing client/server infrastructure poses significant security and privacy challenges, necessitating strict adherence to healthcare data regulations. To combat these issues, a decentralized approach is imperative, and blockchain techn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07054v1-abstract-full').style.display = 'inline'; document.getElementById('2402.07054v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07054v1-abstract-full" style="display: none;"> In the ever-evolving healthcare sector, the widespread adoption of Internet of Things and wearable technologies facilitates remote patient monitoring. However, the existing client/server infrastructure poses significant security and privacy challenges, necessitating strict adherence to healthcare data regulations. To combat these issues, a decentralized approach is imperative, and blockchain technology emerges as a compelling solution for strengthening Internet of Things and medical systems security. This paper introduces HNMblock, a model that elevates the realms of epidemiological monitoring, medical system security, and wellness enhancement. By harnessing the transparency and immutability inherent in blockchain, HNMblock empowers real-time, tamper-proof tracking of epidemiological data, enabling swift responses to disease outbreaks. Furthermore, it fortifies the security of medical systems through advanced cryptographic techniques and smart contracts, with a paramount focus on safeguarding patient privacy. HNMblock also fosters personalized healthcare, encouraging patient involvement and data-informed decision-making. The integration of blockchain within the healthcare domain, as exemplified by HNMblock, holds the potential to revolutionize data management, epidemiological surveillance, and wellness, as meticulously explored in this research article. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07054v1-abstract-full').style.display = 'none'; document.getElementById('2402.07054v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 February, 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, 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/2402.04575">arXiv:2402.04575</a> <span> [<a href="https://arxiv.org/pdf/2402.04575">pdf</a>, <a href="https://arxiv.org/format/2402.04575">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Can We Identify Stack Overflow Questions Requiring Code Snippets? Investigating the Cause & Effect of Missing Code Snippets </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mondal%2C+S">Saikat Mondal</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Roy%2C+C+K">Chanchal K. Roy</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="2402.04575v1-abstract-short" style="display: inline;"> On the Stack Overflow (SO) Q&A site, users often request solutions to their code-related problems (e.g., errors, unexpected behavior). Unfortunately, they often miss required code snippets during their question submission, which could prevent their questions from getting prompt and appropriate answers. In this study, we conduct an empirical study investigating the cause & effect of missing code sn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04575v1-abstract-full').style.display = 'inline'; document.getElementById('2402.04575v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.04575v1-abstract-full" style="display: none;"> On the Stack Overflow (SO) Q&A site, users often request solutions to their code-related problems (e.g., errors, unexpected behavior). Unfortunately, they often miss required code snippets during their question submission, which could prevent their questions from getting prompt and appropriate answers. In this study, we conduct an empirical study investigating the cause & effect of missing code snippets in SO questions whenever required. Here, our contributions are threefold. First, we analyze how the presence or absence of required code snippets affects the correlation between question types (missed code, included code after requests & had code snippets during submission) and corresponding answer meta-data (e.g., presence of an accepted answer). According to our analysis, the chance of getting accepted answers is three times higher for questions that include required code snippets during their question submission than those that missed the code. We also investigate whether the confounding factors (e.g., user reputation) affect questions receiving answers besides the presence or absence of required code snippets. We found that such factors do not hurt the correlation between the presence or absence of required code snippets and answer meta-data. Second, we surveyed 64 practitioners to understand why users miss necessary code snippets. About 60% of them agree that users are unaware of whether their questions require any code snippets. Third, we thus extract four text-based features (e.g., keywords) and build six ML models to identify the questions that need code snippets. Our models can predict the target questions with 86.5% precision, 90.8% recall, 85.3% F1-score, and 85.2% overall accuracy. Our work has the potential to save significant time in programming question-answering and improve the quality of the valuable knowledge base by decreasing unanswered and unresolved questions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.04575v1-abstract-full').style.display = 'none'; document.getElementById('2402.04575v1-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">This paper has been accepted for inclusion in the International Conference on Software Analysis, Evolution, and Reengineering (SANER 2024) technical program</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.03046">arXiv:2402.03046</a> <span> [<a href="https://arxiv.org/pdf/2402.03046">pdf</a>, <a href="https://arxiv.org/format/2402.03046">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> </div> </div> <p class="title is-5 mathjax"> Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Huang%2C+S">Shengyi Huang</a>, <a href="/search/cs?searchtype=author&query=Gallou%C3%A9dec%2C+Q">Quentin Gallou茅dec</a>, <a href="/search/cs?searchtype=author&query=Felten%2C+F">Florian Felten</a>, <a href="/search/cs?searchtype=author&query=Raffin%2C+A">Antonin Raffin</a>, <a href="/search/cs?searchtype=author&query=Dossa%2C+R+F+J">Rousslan Fernand Julien Dossa</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yanxiao Zhao</a>, <a href="/search/cs?searchtype=author&query=Sullivan%2C+R">Ryan Sullivan</a>, <a href="/search/cs?searchtype=author&query=Makoviychuk%2C+V">Viktor Makoviychuk</a>, <a href="/search/cs?searchtype=author&query=Makoviichuk%2C+D">Denys Makoviichuk</a>, <a href="/search/cs?searchtype=author&query=Danesh%2C+M+H">Mohamad H. Danesh</a>, <a href="/search/cs?searchtype=author&query=Roum%C3%A9gous%2C+C">Cyril Roum茅gous</a>, <a href="/search/cs?searchtype=author&query=Weng%2C+J">Jiayi Weng</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Chufan Chen</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Masudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Ara%C3%BAjo%2C+J+G+M">Jo茫o G. M. Ara煤jo</a>, <a href="/search/cs?searchtype=author&query=Quan%2C+G">Guorui Quan</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+D">Daniel Tan</a>, <a href="/search/cs?searchtype=author&query=Klein%2C+T">Timo Klein</a>, <a href="/search/cs?searchtype=author&query=Charakorn%2C+R">Rujikorn Charakorn</a>, <a href="/search/cs?searchtype=author&query=Towers%2C+M">Mark Towers</a>, <a href="/search/cs?searchtype=author&query=Berthelot%2C+Y">Yann Berthelot</a>, <a href="/search/cs?searchtype=author&query=Mehta%2C+K">Kinal Mehta</a>, <a href="/search/cs?searchtype=author&query=Chakraborty%2C+D">Dipam Chakraborty</a>, <a href="/search/cs?searchtype=author&query=KG%2C+A">Arjun KG</a>, <a href="/search/cs?searchtype=author&query=Charraut%2C+V">Valentin Charraut</a> , et al. (8 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="2402.03046v1-abstract-short" style="display: inline;"> In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely available. As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone. We present Open RL Benchmark, a set of fully tracked RL experiments, i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03046v1-abstract-full').style.display = 'inline'; document.getElementById('2402.03046v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.03046v1-abstract-full" style="display: none;"> In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely available. As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone. We present Open RL Benchmark, a set of fully tracked RL experiments, including not only the usual data such as episodic return, but also all algorithm-specific and system metrics. Open RL Benchmark is community-driven: anyone can download, use, and contribute to the data. At the time of writing, more than 25,000 runs have been tracked, for a cumulative duration of more than 8 years. Open RL Benchmark covers a wide range of RL libraries and reference implementations. Special care is taken to ensure that each experiment is precisely reproducible by providing not only the full parameters, but also the versions of the dependencies used to generate it. In addition, Open RL Benchmark comes with a command-line interface (CLI) for easy fetching and generating figures to present the results. In this document, we include two case studies to demonstrate the usefulness of Open RL Benchmark in practice. To the best of our knowledge, Open RL Benchmark is the first RL benchmark of its kind, and the authors hope that it will improve and facilitate the work of researchers in the field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03046v1-abstract-full').style.display = 'none'; document.getElementById('2402.03046v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 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">Under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.01021">arXiv:2402.01021</a> <span> [<a href="https://arxiv.org/pdf/2402.01021">pdf</a>, <a href="https://arxiv.org/format/2402.01021">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> </div> </div> <p class="title is-5 mathjax"> Towards Understanding the Challenges of Bug Localization in Deep Learning Systems </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Jahan%2C+S">Sigma Jahan</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+M+B">Mehil B. Shah</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</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="2402.01021v1-abstract-short" style="display: inline;"> Software bugs cost the global economy billions of dollars annually and claim ~50\% of the programming time from software developers. Locating these bugs is crucial for their resolution but challenging. It is even more challenging in deep-learning systems due to their black-box nature. Bugs in these systems are also hidden not only in the code but also in the models and training data, which might m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01021v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01021v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01021v1-abstract-full" style="display: none;"> Software bugs cost the global economy billions of dollars annually and claim ~50\% of the programming time from software developers. Locating these bugs is crucial for their resolution but challenging. It is even more challenging in deep-learning systems due to their black-box nature. Bugs in these systems are also hidden not only in the code but also in the models and training data, which might make traditional debugging methods less effective. In this article, we conduct a large-scale empirical study to better understand the challenges of localizing bugs in deep-learning systems. First, we determine the bug localization performance of four existing techniques using 2,365 bugs from deep-learning systems and 2,913 from traditional software. We found these techniques significantly underperform in localizing deep-learning system bugs. Second, we evaluate how different bug types in deep learning systems impact bug localization. We found that the effectiveness of localization techniques varies with bug type due to their unique challenges. For example, tensor bugs were more accessible to locate due to their structural nature, while all techniques struggled with GPU bugs due to their external dependencies. Third, we investigate the impact of bugs' extrinsic nature on localization in deep-learning systems. We found that deep learning bugs are often extrinsic and thus connected to artifacts other than source code (e.g., GPU, training data), contributing to the poor performance of existing localization methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01021v1-abstract-full').style.display = 'none'; document.getElementById('2402.01021v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 February, 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/2401.15043">arXiv:2401.15043</a> <span> [<a href="https://arxiv.org/pdf/2401.15043">pdf</a>, <a href="https://arxiv.org/format/2401.15043">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="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.jbi.2024.104727">10.1016/j.jbi.2024.104727 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mushfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Irbaz%2C+M+S">Mohammad Sabik Irbaz</a>, <a href="/search/cs?searchtype=author&query=North%2C+K">Kai North</a>, <a href="/search/cs?searchtype=author&query=Williams%2C+M+S">Michelle S. Williams</a>, <a href="/search/cs?searchtype=author&query=Zampieri%2C+M">Marcos Zampieri</a>, <a href="/search/cs?searchtype=author&query=Lybarger%2C+K">Kevin Lybarger</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="2401.15043v3-abstract-short" style="display: inline;"> Objective: The reading level of health educational materials significantly influences the understandability and accessibility of the information, particularly for minoritized populations. Many patient educational resources surpass the reading level and complexity of widely accepted standards. There is a critical need for high-performing text simplification models in health information to enhance d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.15043v3-abstract-full').style.display = 'inline'; document.getElementById('2401.15043v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.15043v3-abstract-full" style="display: none;"> Objective: The reading level of health educational materials significantly influences the understandability and accessibility of the information, particularly for minoritized populations. Many patient educational resources surpass the reading level and complexity of widely accepted standards. There is a critical need for high-performing text simplification models in health information to enhance dissemination and literacy. This need is particularly acute in cancer education, where effective prevention and screening education can substantially reduce morbidity and mortality. Methods: We introduce Simplified Digestive Cancer (SimpleDC), a parallel corpus of cancer education materials tailored for health text simplification research, comprising educational content from the American Cancer Society, Centers for Disease Control and Prevention, and National Cancer Institute. Utilizing SimpleDC alongside the existing Med-EASi corpus, we explore Large Language Model (LLM)-based simplification methods, including fine-tuning, reinforcement learning (RL), reinforcement learning with human feedback (RLHF), domain adaptation, and prompt-based approaches. Our experimentation encompasses Llama 2 and GPT-4. A novel RLHF reward function is introduced, featuring a lightweight model adept at distinguishing between original and simplified texts, thereby enhancing the model's effectiveness with unlabeled data. Results: Fine-tuned Llama 2 models demonstrated high performance across various metrics. Our innovative RLHF reward function surpassed existing RL text simplification reward functions in effectiveness. The results underscore that RL/RLHF can augment fine-tuning, facilitating model training on unlabeled text and improving performance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.15043v3-abstract-full').style.display = 'none'; document.getElementById('2401.15043v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 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">Published in Journal of Biomedical Informatics, Volume 158, October 2024, 104727</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11410">arXiv:2401.11410</a> <span> [<a href="https://arxiv.org/pdf/2401.11410">pdf</a>, <a href="https://arxiv.org/format/2401.11410">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Agricultural Recommendation System based on Deep Learning: A Multivariate Weather Forecasting Approach </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zubair%2C+M">Md Zubair</a>, <a href="/search/cs?searchtype=author&query=Salim%2C+M+S">Md. Shahidul Salim</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mehrab Mustafy Rahman</a>, <a href="/search/cs?searchtype=author&query=Basher%2C+M+J+I">Mohammad Jahid Ibna Basher</a>, <a href="/search/cs?searchtype=author&query=Imran%2C+S">Shahin Imran</a>, <a href="/search/cs?searchtype=author&query=Sarker%2C+I+H">Iqbal H. Sarker</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="2401.11410v3-abstract-short" style="display: inline;"> Agriculture plays a fundamental role in driving economic growth and ensuring food security for populations around the world. Although labor-intensive agriculture has led to steady increases in food grain production in many developing countries, it is frequently challenged by adverse weather conditions, including heavy rainfall, low temperatures, and drought. These factors substantially hinder food… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11410v3-abstract-full').style.display = 'inline'; document.getElementById('2401.11410v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11410v3-abstract-full" style="display: none;"> Agriculture plays a fundamental role in driving economic growth and ensuring food security for populations around the world. Although labor-intensive agriculture has led to steady increases in food grain production in many developing countries, it is frequently challenged by adverse weather conditions, including heavy rainfall, low temperatures, and drought. These factors substantially hinder food production, posing significant risks to global food security. In order to have a profitable, sustainable, and farmer-friendly agricultural practice, this paper proposes a context-based crop recommendation system powered by a weather forecast model. For implementation purposes, we have considered the whole territory of Bangladesh. With extensive evaluation, the multivariate Stacked Bi-LSTM (three Bi-LSTM layers with a time Distributed layer) Network is employed as the weather forecasting model. The proposed weather model can forecast Rainfall, Temperature, Humidity, and Sunshine for any given location in Bangladesh with an average R-Squared value of 0.9824, and the model outperforms other state-of-the-art LSTM models. These predictions guide our system in generating viable farming decisions. Additionally, our full-fledged system is capable of alerting the farmers about extreme weather conditions so that preventive measures can be undertaken to protect the crops. Finally, the system is also adept at making knowledge-based crop suggestions for flood and drought-prone regions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11410v3-abstract-full').style.display = 'none'; document.getElementById('2401.11410v3-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 21 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">18 pages, 16 figures and 13 tables. Two figures and one table have been added to this version</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.11358">arXiv:2401.11358</a> <span> [<a href="https://arxiv.org/pdf/2401.11358">pdf</a>, <a href="https://arxiv.org/format/2401.11358">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> </div> </div> <p class="title is-5 mathjax"> ANNA: A Deep Learning Based Dataset in Heterogeneous Traffic for Autonomous Vehicles </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kamal%2C+M">Mahedi Kamal</a>, <a href="/search/cs?searchtype=author&query=Fariha%2C+T">Tasnim Fariha</a>, <a href="/search/cs?searchtype=author&query=Zinia%2C+A+K">Afrina Kabir Zinia</a>, <a href="/search/cs?searchtype=author&query=Syed%2C+M+A">Md. Abu Syed</a>, <a href="/search/cs?searchtype=author&query=Khan%2C+F+H">Fahim Hasan Khan</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md. Mahbubur Rahman</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="2401.11358v1-abstract-short" style="display: inline;"> Recent breakthroughs in artificial intelligence offer tremendous promise for the development of self-driving applications. Deep Neural Networks, in particular, are being utilized to support the operation of semi-autonomous cars through object identification and semantic segmentation. To assess the inadequacy of the current dataset in the context of autonomous and semi-autonomous cars, we created a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11358v1-abstract-full').style.display = 'inline'; document.getElementById('2401.11358v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.11358v1-abstract-full" style="display: none;"> Recent breakthroughs in artificial intelligence offer tremendous promise for the development of self-driving applications. Deep Neural Networks, in particular, are being utilized to support the operation of semi-autonomous cars through object identification and semantic segmentation. To assess the inadequacy of the current dataset in the context of autonomous and semi-autonomous cars, we created a new dataset named ANNA. This study discusses a custom-built dataset that includes some unidentified vehicles in the perspective of Bangladesh, which are not included in the existing dataset. A dataset validity check was performed by evaluating models using the Intersection Over Union (IOU) metric. The results demonstrated that the model trained on our custom dataset was more precise and efficient than the models trained on the KITTI or COCO dataset concerning Bangladeshi traffic. The research presented in this paper also emphasizes the importance of developing accurate and efficient object detection algorithms for the advancement of autonomous vehicles. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.11358v1-abstract-full').style.display = 'none'; document.getElementById('2401.11358v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.08035">arXiv:2401.08035</a> <span> [<a href="https://arxiv.org/pdf/2401.08035">pdf</a>, <a href="https://arxiv.org/format/2401.08035">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> BanglaNet: Bangla Handwritten Character Recognition using Ensembling of Convolutional Neural Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Saha%2C+C">Chandrika Saha</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Mostafijur Rahman</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="2401.08035v2-abstract-short" style="display: inline;"> Handwritten character recognition is a crucial task because of its abundant applications. The recognition task of Bangla handwritten characters is especially challenging because of the cursive nature of Bangla characters and the presence of compound characters with more than one way of writing. In this paper, a classification model based on the ensembling of several Convolutional Neural Networks (… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08035v2-abstract-full').style.display = 'inline'; document.getElementById('2401.08035v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.08035v2-abstract-full" style="display: none;"> Handwritten character recognition is a crucial task because of its abundant applications. The recognition task of Bangla handwritten characters is especially challenging because of the cursive nature of Bangla characters and the presence of compound characters with more than one way of writing. In this paper, a classification model based on the ensembling of several Convolutional Neural Networks (CNN), namely, BanglaNet is proposed to classify Bangla basic characters, compound characters, numerals, and modifiers. Three different models based on the idea of state-of-the-art CNN models like Inception, ResNet, and DenseNet have been trained with both augmented and non-augmented inputs. Finally, all these models are averaged or ensembled to get the finishing model. Rigorous experimentation on three benchmark Bangla handwritten characters datasets, namely, CMATERdb, BanglaLekha-Isolated, and Ekush has exhibited significant recognition accuracies compared to some recent CNN-based research. The top-1 recognition accuracies obtained are 98.40%, 97.65%, and 97.32%, and the top-3 accuracies are 99.79%, 99.74%, and 99.56% for CMATERdb, BanglaLekha-Isolated, and Ekush datasets respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.08035v2-abstract-full').style.display = 'none'; document.getElementById('2401.08035v2-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 15 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.05452">arXiv:2401.05452</a> <span> [<a href="https://arxiv.org/pdf/2401.05452">pdf</a>, <a href="https://arxiv.org/format/2401.05452">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"> Cuff-less Arterial Blood Pressure Waveform Synthesis from Single-site PPG using Transformer & Frequency-domain Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nawaz%2C+M+W">Muhammad Wasim Nawaz</a>, <a href="/search/cs?searchtype=author&query=Tahir%2C+M+A">Muhammad Ahmad Tahir</a>, <a href="/search/cs?searchtype=author&query=Mehmood%2C+A">Ahsan Mehmood</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M+U">Muhammad Mahboob Ur Rahman</a>, <a href="/search/cs?searchtype=author&query=Riaz%2C+K">Kashif Riaz</a>, <a href="/search/cs?searchtype=author&query=Abbasi%2C+Q+H">Qammer H. Abbasi</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="2401.05452v2-abstract-short" style="display: inline;"> We develop and evaluate two novel purpose-built deep learning (DL) models for synthesis of the arterial blood pressure (ABP) waveform in a cuff-less manner, using a single-site photoplethysmography (PPG) signal. We train and evaluate our DL models on the data of 209 subjects from the public UCI dataset on cuff-less blood pressure (CLBP) estimation. Our transformer model consists of an encoder-deco… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05452v2-abstract-full').style.display = 'inline'; document.getElementById('2401.05452v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.05452v2-abstract-full" style="display: none;"> We develop and evaluate two novel purpose-built deep learning (DL) models for synthesis of the arterial blood pressure (ABP) waveform in a cuff-less manner, using a single-site photoplethysmography (PPG) signal. We train and evaluate our DL models on the data of 209 subjects from the public UCI dataset on cuff-less blood pressure (CLBP) estimation. Our transformer model consists of an encoder-decoder pair that incorporates positional encoding, multi-head attention, layer normalization, and dropout techniques for ABP waveform synthesis. Secondly, under our frequency-domain (FD) learning approach, we first obtain the discrete cosine transform (DCT) coefficients of the PPG and ABP signals, and then learn a linear/non-linear (L/NL) regression between them. The transformer model (FD L/NL model) synthesizes the ABP waveform with a mean absolute error (MAE) of 3.01 (4.23). Further, the synthesis of ABP waveform also allows us to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP) values. To this end, the transformer model reports an MAE of 3.77 mmHg and 2.69 mmHg, for SBP and DBP, respectively. On the other hand, the FD L/NL method reports an MAE of 4.37 mmHg and 3.91 mmHg, for SBP and DBP, respectively. Both methods fulfill the AAMI criterion. As for the BHS criterion, our transformer model (FD L/NL regression model) achieves grade A (grade B). <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.05452v2-abstract-full').style.display = 'none'; document.getElementById('2401.05452v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 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">8 pages, 3 figures, 2 tables, submitted for review and 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/2401.03069">arXiv:2401.03069</a> <span> [<a href="https://arxiv.org/pdf/2401.03069">pdf</a>, <a href="https://arxiv.org/format/2401.03069">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shah%2C+M+B">Mehil B. Shah</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</a>, <a href="/search/cs?searchtype=author&query=Khomh%2C+F">Foutse Khomh</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="2401.03069v4-abstract-short" style="display: inline;"> Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles. Despite substantial advancements in deep learning techniques, little research has focused on reproducing deep learning bugs, which is an essential step for the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03069v4-abstract-full').style.display = 'inline'; document.getElementById('2401.03069v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.03069v4-abstract-full" style="display: none;"> Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles. Despite substantial advancements in deep learning techniques, little research has focused on reproducing deep learning bugs, which is an essential step for their resolution. Existing literature suggests that only 3% of deep learning bugs are reproducible, underscoring the need for further research. Objective: This paper examines the reproducibility of deep learning bugs. We identify edit actions and useful information that could improve the reproducibility of deep learning bugs. Method: First, we construct a dataset of 668 deep-learning bugs from Stack Overflow and GitHub across three frameworks and 22 architectures. Second, out of the 668 bugs, we select 165 bugs using stratified sampling and attempt to determine their reproducibility. While reproducing these bugs, we identify edit actions and useful information for their reproduction. Third, we used the Apriori algorithm to identify useful information and edit actions required to reproduce specific types of bugs. Finally, we conducted a user study involving 22 developers to assess the effectiveness of our findings in real-life settings. Results: We successfully reproduced 148 out of 165 bugs attempted. We identified ten edit actions and five useful types of component information that can help us reproduce the deep learning bugs. With the help of our findings, the developers were able to reproduce 22.92% more bugs and reduce their reproduction time by 24.35%. Conclusions: Our research addresses the critical issue of deep learning bug reproducibility. Practitioners and researchers can leverage our findings to improve deep learning bug reproducibility. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.03069v4-abstract-full').style.display = 'none'; document.getElementById('2401.03069v4-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 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 at the Journal of Empirical Software Engineering (EMSE)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.01426">arXiv:2401.01426</a> <span> [<a href="https://arxiv.org/pdf/2401.01426">pdf</a>, <a href="https://arxiv.org/format/2401.01426">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Theory">cs.IT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Md Musfiqur Rahman</a>, <a href="/search/cs?searchtype=author&query=Kocaoglu%2C+M">Murat Kocaoglu</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="2401.01426v2-abstract-short" style="display: inline;"> Sound and complete algorithms have been proposed to compute identifiable causal queries using the causal structure and data. However, most of these algorithms assume accurate estimation of the data distribution, which is impractical for high-dimensional variables such as images. On the other hand, modern deep generative architectures can be trained to sample from high-dimensional distributions. Ho… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.01426v2-abstract-full').style.display = 'inline'; document.getElementById('2401.01426v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.01426v2-abstract-full" style="display: none;"> Sound and complete algorithms have been proposed to compute identifiable causal queries using the causal structure and data. However, most of these algorithms assume accurate estimation of the data distribution, which is impractical for high-dimensional variables such as images. On the other hand, modern deep generative architectures can be trained to sample from high-dimensional distributions. However, training these networks are typically very costly. Thus, it is desirable to leverage pre-trained models to answer causal queries using such high-dimensional data. To address this, we propose modular training of deep causal generative models that not only makes learning more efficient, but also allows us to utilize large, pre-trained conditional generative models. To the best of our knowledge, our algorithm, Modular-DCM is the first algorithm that, given the causal structure, uses adversarial training to learn the network weights, and can make use of pre-trained models to provably sample from any identifiable causal query in the presence of latent confounders. With extensive experiments on the Colored-MNIST dataset, we demonstrate that our algorithm outperforms the baselines. We also show our algorithm's convergence on the COVIDx dataset and its utility with a causal invariant prediction problem on CelebA-HQ. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.01426v2-abstract-full').style.display = 'none'; document.getElementById('2401.01426v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 2 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.11889">arXiv:2312.11889</a> <span> [<a href="https://arxiv.org/pdf/2312.11889">pdf</a>, <a href="https://arxiv.org/format/2312.11889">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Software Engineering">cs.SE</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"> Predicting Line-Level Defects by Capturing Code Contexts with Hierarchical Transformers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mahbub%2C+P">Parvez Mahbub</a>, <a href="/search/cs?searchtype=author&query=Rahman%2C+M+M">Mohammad Masudur Rahman</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="2312.11889v1-abstract-short" style="display: inline;"> Software defects consume 40% of the total budget in software development and cost the global economy billions of dollars every year. Unfortunately, despite the use of many software quality assurance (SQA) practices in software development (e.g., code review, continuous integration), defects may still exist in the official release of a software product. Therefore, prioritizing SQA efforts for the v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11889v1-abstract-full').style.display = 'inline'; document.getElementById('2312.11889v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.11889v1-abstract-full" style="display: none;"> Software defects consume 40% of the total budget in software development and cost the global economy billions of dollars every year. Unfortunately, despite the use of many software quality assurance (SQA) practices in software development (e.g., code review, continuous integration), defects may still exist in the official release of a software product. Therefore, prioritizing SQA efforts for the vulnerable areas of the codebase is essential to ensure the high quality of a software release. Predicting software defects at the line level could help prioritize the SQA effort but is a highly challenging task given that only ~3% of lines of a codebase could be defective. Existing works on line-level defect prediction often fall short and cannot fully leverage the line-level defect information. In this paper, we propose Bugsplorer, a novel deep-learning technique for line-level defect prediction. It leverages a hierarchical structure of transformer models to represent two types of code elements: code tokens and code lines. Unlike the existing techniques that are optimized for file-level defect prediction, Bugsplorer is optimized for a line-level defect prediction objective. Our evaluation with five performance metrics shows that Bugsplorer has a promising capability of predicting defective lines with 26-72% better accuracy than that of the state-of-the-art technique. It can rank the first 20% defective lines within the top 1-3% suspicious lines. Thus, Bugsplorer has the potential to significantly reduce SQA costs by ranking defective lines higher. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.11889v1-abstract-full').style.display = 'none'; document.getElementById('2312.11889v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2023. </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=150" class="pagination-link " aria-label="Page 4" aria-current="page">4 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=200" class="pagination-link " aria-label="Page 5" aria-current="page">5 </a> </li> <li> <a href="/search/?searchtype=author&query=Rahman%2C+M+M&start=250" class="pagination-link " aria-label="Page 6" aria-current="page">6 </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