Disk Failure Prediction based on Multi-layer Domain Adaptive Learning

<!DOCTYPE html> <html lang="en"> <head>  <link href="https://fonts.googleapis.com/icon?family=Material+Icons" rel="stylesheet"> <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.0.13/css/all.css" integrity="sha384-DNOHZ68U8hZfKXOrtjWvjxusGo9WQnrNx2sqG0tfsghAvtVlRW3tvkXWZh58N9jp" crossorigin="anonymous"> <link href="https://fonts.googleapis.com/css?family=Roboto" rel="stylesheet">  <link type="text/css" rel="stylesheet" href="../css/materialize.min.css" media="screen,projection" /> <link type="text/css" rel="stylesheet" href="../css/main.css" /> <script src="https://ajax.googleapis.com/ajax/libs/jquery/2.2.0/jquery.min.js"></script> <link rel="icon" type="image/png" href="../aircc.png">  <html xmlns="http://www.w3.org/1999/xhtml"> <head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"> <title>Disk Failure Prediction based on Multi-layer Domain Adaptive Learning</title>  <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <meta http-equiv="X-UA-Compatible" content="ie=edge"> <meta name="title" content="Underwater Detection of Ancient Pottery Sherds Using Deep Learning"> <meta name="description" content="Large scale data storage is susceptible to failure. As disks are damaged and replaced, traditional machine learning models, which rely on historical data to make predictions, struggle to accurately predict disk failures. This paper presents a novel method for predicting disk failures by leveraging multi-layer domain adaptive learning techniques. First, disk data with numerous faults is selected as the source domain, and disk data with fewer faults is selected as the target domain. A training of the feature extraction network is performed with the selected origin and destination domains. The contrast between the two domains facilitates the transfer of diagnostic knowledge from the domain of source and target. According to the experimental findings, it has been demonstrated that the proposed technique can generate a reliable prediction model and improve the ability to predict failures on disk data with few failure samples. "> <meta name="keywords" content="Disk failure prediction, Transfer learning, Domain adaptation, Distance metric, Proceedings, Computer science, Technology"/>   <meta name="dc.title" content="Disk Failure Prediction based on Multi-layer Domain Adaptive Learning"> <meta name="citation_authors" content="Guangfu Gao"> <meta name="citation_authors" content="Peng Wu"> <meta name="citation_authors" content="Hussain Dawood"> <meta name="dc.type" content="Article"> <meta name="dc.source" content="International Journal on Cybernetics & Informatics (IJCI) Vol. 12, No.06"> <meta name="dc.date" content="2023/10/07"> <meta name="dc.identifier" content="10.5121/ijci.2023.120603"> <meta name="dc.publisher" content="AIRCC Publishing Corporation"> <meta name="dc.rights" content="http://creativecommons.org/licenses/by/3.0/"> <meta name="dc.format" content="application/pdf"> <meta name="dc.language" content="en"> <meta name="dc.description" content="Large scale data storage is susceptible to failure. As disks are damaged and replaced, traditional machine learning models, which rely on historical data to make predictions, struggle to accurately predict disk failures. This paper presents a novel method for predicting disk failures by leveraging multi-layer domain adaptive learning techniques. First, disk data with numerous faults is selected as the source domain, and disk data with fewer faults is selected as the target domain. A training of the feature extraction network is performed with the selected origin and destination domains. The contrast between the two domains facilitates the transfer of diagnostic knowledge from the domain of source and target. According to the experimental findings, it has been demonstrated that the proposed technique can generate a reliable prediction model and improve the ability to predict failures on disk data with few failure samples. "/> <meta name="dc.subject" content="Disk failure prediction"> <meta name="dc.subject" content="Transfer learning"> <meta name="dc.subject" content="Domain adaptation"> <meta name="dc.subject" content="Distance metric"> <meta name="dc.subject" content=" Proceedings"> <meta name="dc.subject" content="Computer Science"> <meta name="dc.subject" content=" Technology">   <meta name="prism.publicationName" content="International Journal on Cybernetics & Informatics (IJCI) "> <meta name="prism.publicationDate" content="2023/10/07"> <meta name="prism.volume" content="12"> <meta name="prism.number" content="06"> <meta name="prism.section" content="Article"> <meta name="prism.startingPage" content="21">   <meta name="citation_journal_title" content="International Journal on Cybernetics & Informatics (IJCI) "> <meta name="citation_publisher" content="AIRCC Publishing Corporation"> <meta name="citation_authors" content="Guangfu Gao, Peng Wu and Hussain Dawood"> <meta name="citation_title" content="Disk Failure Prediction based on Multi-layer Domain Adaptive Learning"> <meta name="citation_online_date" content="2023/10/07"> <meta name="citation_issue" content="12"> <meta name="citation_firstpage" content="21"> <meta name="citation_authors" content="Guangfu Gao"> <meta name="citation_authors" content="Peng Wu"> <meta name="citation_authors" content="Hussain Dawood"> <meta name="citation_doi" content="10.5121/ijci.2023.120603"> <meta name="citation_abstract_html_url" content="https://ijcionline.com/abstract/12623ijci03"> <meta name="citation_pdf_url" content="https://ijcionline.com/paper/12/12623ijci03.pdf">   <meta property="og:site_name" content="AIRCC" /> <meta property="og:type" content="article" /> <meta property="og:url" content="https://ijcionline.com/abstract/12623ijci03"> <meta property="og:title" content="Disk Failure Prediction based on Multi-layer Domain Adaptive Learning"> <meta property="og:description" content="Large scale data storage is susceptible to failure. As disks are damaged and replaced, traditional machine learning models, which rely on historical data to make predictions, struggle to accurately predict disk failures. This paper presents a novel method for predicting disk failures by leveraging multi-layer domain adaptive learning techniques. First, disk data with numerous faults is selected as the source domain, and disk data with fewer faults is selected as the target domain. A training of the feature extraction network is performed with the selected origin and destination domains. The contrast between the two domains facilitates the transfer of diagnostic knowledge from the domain of source and target. According to the experimental findings, it has been demonstrated that the proposed technique can generate a reliable prediction model and improve the ability to predict failures on disk data with few failure samples. "/>   <meta name="twitter:card" content="Proceedings" /> <meta name="twitter:site" content="AIRCC" /> <meta name="twitter:title" content="Disk Failure Prediction based on Multi-layer Domain Adaptive Learning" /> <meta name="twitter:description" content=" Large scale data storage is susceptible to failure. As disks are damaged and replaced, traditional machine learning models, which rely on historical data to make predictions, struggle to accurately predict disk failures. This paper presents a novel method for predicting disk failures by leveraging multi-layer domain adaptive learning techniques. First, disk data with numerous faults is selected as the source domain, and disk data with fewer faults is selected as the target domain. A training of the feature extraction network is performed with the selected origin and destination domains. The contrast between the two domains facilitates the transfer of diagnostic knowledge from the domain of source and target. According to the experimental findings, it has been demonstrated that the proposed technique can generate a reliable prediction model and improve the ability to predict failures on disk data with few failure samples. "/> <meta name="twitter:image" content="https://airccse.org/img/aircc-logo1.jpg" />   <meta name="google-site-verification" content="t8rHIcM8EfjIqfQzQ0IdYIiA9JxDD0uUZAitBCzsOIw" /> <meta name="yandex-verification" content="e3d1d1a31c7141f4" />   </head> <body> <div class="navbar-fixed"> <nav class="cyan lighten-2 z-depth-5"> <div class="container"> <div class="nav-wrapper"> <ul> <li id="b-logo"> <img id="brand-logo" href="/index" class="hide-on-med-and-down" src="/img/aircc-logo1.jpg" width="60" height="60" style="vertical-align:middle"> </li> </ul> <a class="brand-logo " href="/index"><h5>IJCI <span class="hide-on-med-and-down">Conference Proceedings</span></h5></a> <a data-activates="side-nav" class="button-collapse show-on-small left"> <i class="material-icons">menu</i> </a> <ul class="right hide-on-med-and-down"> <li class=""> <a href="/index">Home</a> </li> <li class=""> <a href="/volume13">Current issue</a> </li> <li> <a href="/archives">Archives</a> </li> <li class=""> <a href="/contact">Contact</a> </li> </ul> </div> </div> </nav> </div>  <ul class="side-nav" id="side-nav"> <li> <div class="user-view arc"> <div class="background"> <img class="mobile-overlay" > </div> <a href="/index"> <i id="cl" class="material-icons cyan-text text-lighten-2 right">close</i> </a> <a href="/index"> <img class="circle" src="/img/aircc-logo1.jpg"> </a> <h5 class="">IJCI Conference Proceedings</h5> </div> </li> <li class=""> <a href="/index">Home <i class="fas fa-user"></i> </a> </li> <li class=""> <a href="/volume13">Current issue <i class="fas fa-user"></i> </a> </li> <li> <a href="/archives">Archives <i class="fas fa-user"></i> </a> </li> <li class=""> <a href="/contact">Contact <i class="fas fa-user"></i> </a> </li> </ul> <div class="fixed-action-btn" id="scrollTop"> <a class="btn btn-small btn-floating waves-effect waves-light blue lighten-1 pulse" onclick="topFunction()"> <i class="material-icons">keyboard_arrow_up</i> </a> </div>  <section class="section-main" > <div class="container"> <div class="row"> <div class="col s12 m9">  <div class="card z-depth-2"> <div class="card-content"> <h5 class="cyan-text center text-darken-1"> Disk Failure Prediction based on Multi-layer Domain Adaptive Learning </h5> </div> </div> <br> <div class="card"> <h5 id="about" class="brown-text text-darken-2 text-center" style="padding-bottom:0px">Authors</h5>  <div class="card-content"> <p class="left-text" style="text-align:justify"> Guangfu Gao<sup>1</sup>, Peng Wu<sup>1</sup> and Hussain Dawood <sup>2</sup>, <sup>1</sup>University of Jinan, China, <sup>2</sup> National Skills University, Islamabad </p> </div> </div>   <div class="card"> <h5 id="about" class="brown-text text-darken-2 text-center" style="padding-bottom:0px">Abstract</h5>  <div class="card-content"> <p class="left-text" style="text-align:justify"> Large scale data storage is susceptible to failure. As disks are damaged and replaced, traditional machine learning models, which rely on historical data to make predictions, struggle to accurately predict disk failures. This paper presents a novel method for predicting disk failures by leveraging multi-layer domain adaptive learning techniques. First, disk data with numerous faults is selected as the source domain, and disk data with fewer faults is selected as the target domain. A training of the feature extraction network is performed with the selected origin and destination domains. The contrast between the two domains facilitates the transfer of diagnostic knowledge from the domain of source and target. According to the experimental findings, it has been demonstrated that the proposed technique can generate a reliable prediction model and improve the ability to predict failures on disk data with few failure samples. </p> </div> </div> <div class="card"> <h5 id="about" class="brown-text text-darken-2 text-center" style="padding-bottom:0px">Keywords</h5>  <div class="card-content"> <p class="left-text" style="text-align:justify"> Disk failure prediction, Transfer learning, Domain adaptation, Distance metric </p> </div> </div> <div class="card-content"> <a href="/paper/12/12623ijci03.pdf" target="_blank" class="btn btn-small lighten-2 cyan lig">Full Text</a>  <a href="/volume12" target="_blank" class="btn btn-small lighten-2 cyan lig">Volume 12,Number 06</a> <a href="https://www.youtube.com/playlist?list=PL1HkUyqULCxznHOi4QhmWInZ4Gb_YrthM" target="_blank" class="btn btn-small lighten-2 cyan lig">Presentation</a> </div> </div>  <div id="side-bar" class="col s12 m3"> <div id="section-main"> <br> <br> <div class="card side cyan lighten-2"> <div class="card-content"> <ul> <li class="ax waves-effect waves-light"> <a class="white-text" href="/editorial" > <i class="material-icons left">account_circle</i>Editorial Board</a> <br> </li> <br> <br> <div class="divider"></div> <br> <li class="ax waves-effect waves-light"> <a class="white-text" href="/mostcitedarticels" > <i class="material-icons left">book</i>Most Cited Articels </a> <br> </li> <br> <br> <div class="divider"></div> <br> <li class="ax waves-effect waves-light"> <a class="white-text" href="/indexing" > <i class="material-icons left">list</i>Indexing </a> <br> </li> <br> <br> <div class="divider"></div> <br> <li class="ax waves-effect waves-light"> <a class="white-text" href="/faq" > <i class="material-icons left">help</i>FAQ </a> <br> </li> <br> <br> <div class="divider"></div> <br> </div> </div> </div> </div> </div> </div> </div> </section> <br> <br> <br> <br> <div id="txtcnt"></div>  <footer class="page-footer cyan lighten-3"> <div class="nav-wrapper"> <div class="container"> <ul> <li> <a target="_blank" href="http://airccse.org/"> <img src="/img/since2008.png" alt="since2008"></a> </li> </ul> <h6> Free Open Access Conference Proceedings <br> Computer Science & Engineering - Information Technology - Information Systems</h6> </div> <div class="footer-m col m3 s12 offset-m1"> </div> <div class="social col m3 offset-m1 s12"> </div> </div> </div> <div class="col s12 m10 offset-m1"> <div class="grey darken-3 center-align"> <small class="white-text">Designed and Developed by NNN Team</small> </div> </div> </footer> </body>  <script type="text/javascript" src="https://code.jquery.com/jquery-3.2.1.min.js"></script> <script type="text/javascript" src="/js/materialize.min.js"></script> <script src="/js/search.js"></script> <script src="/js/scrolltop.js"></script> <script src="/js/popup.js"></script> <script src="/js/main.jquery.js"></script> </html>

CINXE.COM

Disk Failure Prediction based on Multi-layer Domain Adaptive Learning