Robustness of NMF Algorithms Under Different Noises | EAI Endorsed Transactions on Internet of Things

<!DOCTYPE html> <html lang="en-US" xml:lang="en-US"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title> Robustness of NMF Algorithms Under Different Noises | EAI Endorsed Transactions on Internet of Things </title> <link rel="icon" href="https://publications.eai.eu/public/journals/6/favicon_en_US.png"> <meta name="generator" content="Open Journal Systems 3.3.0.18"> <link rel="schema.DC" href="http://purl.org/dc/elements/1.1/" /> <meta name="DC.Creator.PersonalName" content="Mengyao Kang"/> <meta name="DC.Creator.PersonalName" content="Jiawei Zhao"/> <meta name="DC.Creator.PersonalName" content="Zheng Han"/> <meta name="DC.Date.created" scheme="ISO8601" content="2023-06-22"/> <meta name="DC.Date.dateSubmitted" scheme="ISO8601" content="2023-04-21"/> <meta name="DC.Date.issued" scheme="ISO8601" content="2023-06-28"/> <meta name="DC.Date.modified" scheme="ISO8601" content="2023-06-28"/> <meta name="DC.Description" xml:lang="en" content="In machine learning, datasets are often disturbed by different noises. The Nonnegative Matrix Factorization (NMF) algorithm provides a robust method to deal with noise, which will signiﬁcantly improve the efﬁciency of machine learning. In this investigation, the standard NMF algorithm and L2,1-Norm Based NMF algorithm are studied by designing experiments on different noise types, noise levels, and datasets. Furthermore, Relative Reconstruction Errors (RRE), accuracy, and Normalized Mutual Information (NMI) are used to evaluate the robustness of the two algorithms. In this experiment, there is no signiﬁcant difference in performance between the two algorithms, while L2,1-Norm Based NMF algorithm shows relatively small advantages."/> <meta name="DC.Format" scheme="IMT" content="application/pdf"/> <meta name="DC.Identifier" content="3271"/> <meta name="DC.Identifier.pageNumber" content="e4"/> <meta name="DC.Identifier.DOI" content="10.4108/eetiot.v9i1.3271"/> <meta name="DC.Identifier.URI" content="https://publications.eai.eu/index.php/IoT/article/view/3271"/> <meta name="DC.Language" scheme="ISO639-1" content="en"/> <meta name="DC.Rights" content="Copyright (c) 2023 EAI Endorsed Transactions on Internet of Things"/> <meta name="DC.Rights" content="https://creativecommons.org/licenses/by/3.0/"/> <meta name="DC.Source" content="EAI Endorsed Transactions on Internet of Things"/> <meta name="DC.Source.ISSN" content="2414-1399"/> <meta name="DC.Source.Issue" content="1"/> <meta name="DC.Source.Volume" content="9"/> <meta name="DC.Source.URI" content="https://publications.eai.eu/index.php/IoT"/> <meta name="DC.Subject" xml:lang="en" content="NMF"/> <meta name="DC.Title" content="Robustness of NMF Algorithms Under Different Noises"/> <meta name="DC.Type" content="Text.Serial.Journal"/> <meta name="DC.Type.articleType" content="Research article"/> <meta name="gs_meta_revision" content="1.1"/> <meta name="citation_journal_title" content="EAI Endorsed Transactions on Internet of Things"/> <meta name="citation_journal_abbrev" content="EAI Endorsed Trans IoT"/> <meta name="citation_issn" content="2414-1399"/> <meta name="citation_author" content="Mengyao Kang"/> <meta name="citation_author_institution" content="University of Sydney "/> <meta name="citation_author" content="Jiawei Zhao"/> <meta name="citation_author_institution" content="University of Sydney "/> <meta name="citation_author" content="Zheng Han"/> <meta name="citation_author_institution" content="University of Sydney "/> <meta name="citation_title" content="Robustness of NMF Algorithms Under Different Noises"/> <meta name="citation_language" content="en"/> <meta name="citation_date" content="2023/06/22"/> <meta name="citation_volume" content="9"/> <meta name="citation_issue" content="1"/> <meta name="citation_firstpage" content="e4"/> <meta name="citation_lastpage" content="e4"/> <meta name="citation_doi" content="10.4108/eetiot.v9i1.3271"/> <meta name="citation_abstract_html_url" content="https://publications.eai.eu/index.php/IoT/article/view/3271"/> <meta name="citation_keywords" xml:lang="en" content="Machine Learning"/> <meta name="citation_keywords" xml:lang="en" content="Nonnegative matrix factorization"/> <meta name="citation_keywords" xml:lang="en" content="Robustness of algorithm"/> <meta name="citation_keywords" xml:lang="en" content="NMF"/> <meta name="citation_pdf_url" content="https://publications.eai.eu/index.php/IoT/article/download/3271/2389"/> <meta name="citation_reference" content="Deng, X., Ma, Y., & Dong, M. (2016). A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN. Pattern Recognition Letters, 79, 8-17."/> <meta name="citation_reference" content="Díaz, A., & Steele, D. (2021). Analysis of the robustness of NMF algorithms. arXiv preprint arXiv:2106.02213."/> <meta name="citation_reference" content="Kong, D., Ding, C., & Huang, H. (2011, October). Robust nonnegative matrix factorization using l21-norm. In Proceedings of the 20th ACM international conference on Information and knowledge management (pp. 673-682)."/> <meta name="citation_reference" content="Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788-791."/> <meta name="citation_reference" content="Shen, X., Zhang, X., Lan, L., Liao, Q., & Luo, Z. (2019). Another robust NMF: rethinking the hyperbolic tangent function and locality constraint. IEEE Access, 7, 31089-31102."/> <meta name="og:site_name" content="EAI Endorsed Transactions on Internet of Things"/> <meta name="og:type" content="article"/> <meta name="og:title" content="Robustness of NMF Algorithms Under Different Noises"/> <meta name="og:description" content="In machine learning, datasets are often disturbed by different noises. The Nonnegative Matrix Factorization (NMF) algorithm provides a robust method to deal with noise, which will signiﬁcantly improve the efﬁciency of machine learning. In this investigation, the standard NMF algorithm and L2,1-Norm Based NMF algorithm are studied by designing experiments on different noise types, noise levels, and datasets. Furthermore, Relative Reconstruction Errors (RRE), accuracy, and Normalized Mutual Information (NMI) are used to evaluate the robustness of the two algorithms. In this experiment, there is no signiﬁcant difference in performance between the two algorithms, while L2,1-Norm Based NMF algorithm shows relatively small advantages. "/> <meta name="og:url" content="https://publications.eai.eu/index.php/IoT/article/view/3271"/> <meta name="og:locale" content="en_US"/> <meta name="og:image" content=""/> <meta name="article:published_time" content="2023-06-22"/> <meta name="article:tag" content="Machine Learning"/> <meta name="article:tag" content="Nonnegative matrix factorization"/> <meta name="article:tag" content="Robustness of algorithm"/> <meta name="article:tag" content="NMF"/> <link rel="alternate" type="application/atom+xml" href="https://publications.eai.eu/index.php/IoT/gateway/plugin/AnnouncementFeedGatewayPlugin/atom"> <link rel="alternate" type="application/rdf+xml" href="https://publications.eai.eu/index.php/IoT/gateway/plugin/AnnouncementFeedGatewayPlugin/rss"> <link rel="alternate" type="application/rss+xml" href="https://publications.eai.eu/index.php/IoT/gateway/plugin/AnnouncementFeedGatewayPlugin/rss2"> <link rel="stylesheet" href="https://publications.eai.eu/index.php/IoT/$$$call$$$/page/page/css?name=stylesheet" type="text/css" /><link rel="stylesheet" href="https://publications.eai.eu/index.php/IoT/$$$call$$$/page/page/css?name=font" type="text/css" /><link rel="stylesheet" href="https://publications.eai.eu/lib/pkp/styles/fontawesome/fontawesome.css?v=3.3.0.18" type="text/css" /><style type="text/css">.pkp_structure_head { background: center / cover no-repeat url("https://publications.eai.eu/public/journals/6/homepageImage_en_US.png");}</style><link rel="stylesheet" href="https://publications.eai.eu/plugins/generic/citations/css/citations.css?v=3.3.0.18" type="text/css" /> </head> <body class="pkp_page_article pkp_op_view" dir="ltr"> <div class="pkp_structure_page"> <header class="pkp_structure_head" id="headerNavigationContainer" role="banner"> <nav class="cmp_skip_to_content" aria-label="Jump to content links"> <a href="#pkp_content_main">Skip to main content</a> <a href="#siteNav">Skip to main navigation menu</a> <a href="#pkp_content_footer">Skip to site footer</a> </nav> <div class="pkp_head_wrapper"> <div class="pkp_site_name_wrapper"> <button class="pkp_site_nav_toggle"> <span>Open Menu</span> </button> <div class="pkp_site_name"> <a href=" https://publications.eai.eu/index.php/IoT/index " class="is_text">EAI Endorsed Transactions on Internet of Things</a> </div> </div> <nav class="pkp_site_nav_menu" aria-label="Site Navigation"> <a id="siteNav"></a> <div class="pkp_navigation_primary_row"> <div class="pkp_navigation_primary_wrapper"> <ul id="navigationPrimary" class="pkp_navigation_primary pkp_nav_list"> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/index"> Home </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/about"> About </a> <ul> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/about"> About the Journal </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/about/submissions"> Submissions </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/about/editorialTeam"> Editorial Team </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/indexing"> Indexing </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/open-access"> Open Access Information </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/benefits"> Benefits of EAI Transactions </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/about/privacy"> Privacy Statement </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/about/contact"> Contact </a> </li> </ul> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/issue/current"> Current </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/issue/archive"> Archives </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/special-issues"> Special Issues </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/ethics"> Publication Ethics </a> </li> <li class=""> <a href="https://publications.eai.eu/index.php/IoT/announcement"> Announcements </a> </li> </ul> <div class="pkp_navigation_search_wrapper"> <a href="https://publications.eai.eu/index.php/IoT/search" class="pkp_search pkp_search_desktop"> <span class="fa fa-search" aria-hidden="true"></span> Search </a> </div> </div> </div> <div class="pkp_navigation_user_wrapper" id="navigationUserWrapper"> <ul id="navigationUser" class="pkp_navigation_user pkp_nav_list"> <li class="profile"> <a href="https://publications.eai.eu/index.php/IoT/user/register"> Register </a> </li> <li class="profile"> <a href="https://publications.eai.eu/index.php/IoT/login"> Login </a> </li> </ul> </div> </nav> </div> </header> <div class="pkp_structure_content has_sidebar"> <div class="pkp_structure_main" role="main"> <a id="pkp_content_main"></a> <div class="page page_article"> <nav class="cmp_breadcrumbs" role="navigation" aria-label="You are here:"> <ol> <li> <a href="https://publications.eai.eu/index.php/IoT/index"> Home </a> <span class="separator">/</span> </li> <li> <a href="https://publications.eai.eu/index.php/IoT/issue/archive"> Archives </a> <span class="separator">/</span> </li> <li> <a href="https://publications.eai.eu/index.php/IoT/issue/view/390"> Vol. 9 No. 1 (2023): EAI Endorsed Transactions on Internet of Things </a> <span class="separator">/</span> </li> <li class="current" aria-current="page"> <span aria-current="page"> Research article </span> </li> </ol> </nav> <article class="obj_article_details"> <h1 class="page_title"> Robustness of NMF Algorithms Under Different Noises </h1> <div class="row"> <div class="main_entry"> <section class="item authors"> <h2 class="pkp_screen_reader">Authors</h2> <ul class="authors"> <li> <span class="name"> Mengyao Kang </span> <span class="affiliation"> University of Sydney <a href="https://ror.org/0384j8v12"><?xml version="1.0" encoding="UTF-8" standalone="no"?>  <svg xmlns:i="&ns_ai;" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:svg="http://www.w3.org/2000/svg" xmlns="http://www.w3.org/2000/svg" xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" version="1.1" id="Layer_1" x="0px" y="0px" viewBox="0 0 23.4225 16.696501" xml:space="preserve" sodipodi:docname="rorId.svg" inkscape:version="0.92.5 (2060ec1f9f, 2020-04-08)" width="23.422501" height="16.696501"><metadata id="metadata93"><rdf:RDF><cc:Work rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs id="defs91" /><sodipodi:namedview pagecolor="#ffffff" bordercolor="#666666" borderopacity="1" objecttolerance="10" gridtolerance="10" guidetolerance="10" inkscape:pageopacity="0" inkscape:pageshadow="2" inkscape:window-width="1880" inkscape:window-height="1016" id="namedview89" showgrid="true" showguides="false" inkscape:zoom="1" inkscape:cx="-177.76975" inkscape:cy="13.962506" inkscape:window-x="40" inkscape:window-y="27" inkscape:window-maximized="1" inkscape:current-layer="Layer_1" /> <switch id="switch86" transform="matrix(0.15,0,0,0.15,-0.7305,-0.624)"> <foreignObject requiredExtensions="http://ns.adobe.com/AdobeIllustrator/10.0/" x="0" y="0" width="1" height="1"> </foreignObject> <g i:extraneous="self" id="g84"> <polygon class="strorId0" points="68.65,4.16 56.52,22.74 44.38,4.16 " id="polygon72" style="fill:#53baa1" /> <polygon class="strorId0" points="119.41,4.16 107.28,22.74 95.14,4.16 " id="polygon74" style="fill:#53baa1" /> <polygon class="strorId0" points="44.38,115.47 56.52,96.88 68.65,115.47 " id="polygon76" style="fill:#53baa1" /> <polygon class="strorId0" points="95.14,115.47 107.28,96.88 119.41,115.47 " id="polygon78" style="fill:#53baa1" /> <g id="g82"> <path class="st1" d="m 145.53,63.71 c 4.3,-0.8 7.57,-2.71 9.8,-5.72 2.24,-3.01 3.35,-6.67 3.35,-10.96 0,-3.56 -0.62,-6.52 -1.85,-8.9 -1.23,-2.38 -2.9,-4.27 -4.99,-5.68 -2.09,-1.4 -4.53,-2.41 -7.31,-3.01 -2.78,-0.6 -5.72,-0.9 -8.81,-0.9 h -23.56 v 18.83 c -0.19,-0.55 -0.39,-1.09 -0.61,-1.63 -1.63,-3.95 -3.91,-7.32 -6.84,-10.1 -2.93,-2.78 -6.39,-4.92 -10.41,-6.41 -4.01,-1.49 -8.4,-2.24 -13.16,-2.24 -4.76,0 -9.14,0.75 -13.16,2.24 -4.01,1.49 -7.48,3.63 -10.41,6.41 -2.62,2.49 -4.72,5.46 -6.3,8.9 -0.23,-2.47 -0.81,-4.61 -1.74,-6.41 -1.23,-2.38 -2.9,-4.27 -4.99,-5.68 -2.09,-1.4 -4.53,-2.41 -7.31,-3.01 -2.78,-0.6 -5.72,-0.9 -8.81,-0.9 H 4.87 V 89.42 H 18.28 V 65.08 H 24.9 L 37.63,89.42 H 53.71 L 38.24,63.71 c 4.3,-0.8 7.57,-2.71 9.8,-5.72 0.1,-0.14 0.19,-0.29 0.29,-0.43 -0.02,0.47 -0.03,0.94 -0.03,1.42 0,4.87 0.82,9.29 2.45,13.24 1.63,3.95 3.91,7.32 6.84,10.1 2.92,2.78 6.39,4.92 10.41,6.41 4.01,1.49 8.4,2.24 13.16,2.24 4.76,0 9.14,-0.75 13.16,-2.24 4.01,-1.49 7.48,-3.63 10.41,-6.41 2.92,-2.78 5.2,-6.15 6.84,-10.1 0.22,-0.53 0.42,-1.08 0.61,-1.63 v 18.83 h 13.41 V 65.08 h 6.62 l 12.73,24.34 h 16.08 z M 36.39,50.81 c -0.72,0.92 -1.62,1.59 -2.71,2.02 -1.09,0.43 -2.31,0.69 -3.65,0.77 -1.35,0.09 -2.62,0.13 -3.83,0.13 H 18.29 V 39.89 h 8.77 c 1.2,0 2.44,0.09 3.7,0.26 1.26,0.17 2.38,0.5 3.35,0.99 0.97,0.49 1.78,1.19 2.41,2.11 0.63,0.92 0.95,2.15 0.95,3.7 0,1.65 -0.36,2.94 -1.08,3.86 z m 62.35,16.04 c -0.89,2.38 -2.16,4.44 -3.83,6.19 -1.66,1.75 -3.65,3.11 -5.98,4.09 -2.32,0.98 -4.92,1.46 -7.78,1.46 -2.87,0 -5.46,-0.49 -7.78,-1.46 -2.32,-0.97 -4.31,-2.34 -5.98,-4.09 -1.66,-1.75 -2.94,-3.81 -3.83,-6.19 -0.89,-2.38 -1.33,-5 -1.33,-7.87 0,-2.81 0.44,-5.42 1.33,-7.83 0.89,-2.41 2.16,-4.48 3.83,-6.23 1.66,-1.75 3.65,-3.11 5.98,-4.09 2.32,-0.97 4.91,-1.46 7.78,-1.46 2.87,0 5.46,0.49 7.78,1.46 2.32,0.97 4.31,2.34 5.98,4.09 1.66,1.75 2.94,3.83 3.83,6.23 0.89,2.41 1.33,5.02 1.33,7.83 0,2.87 -0.44,5.49 -1.33,7.87 z m 44.94,-16.04 c -0.72,0.92 -1.62,1.59 -2.71,2.02 -1.09,0.43 -2.31,0.69 -3.65,0.77 -1.35,0.09 -2.62,0.13 -3.83,0.13 h -7.91 V 39.89 h 8.77 c 1.2,0 2.44,0.09 3.7,0.26 1.26,0.17 2.38,0.5 3.35,0.99 0.97,0.49 1.78,1.19 2.41,2.11 0.63,0.92 0.95,2.15 0.95,3.7 0,1.65 -0.36,2.94 -1.08,3.86 z" id="path80" inkscape:connector-curvature="0" style="fill:#202826" /> </g> </g> </switch> </svg> </a> </span> </li> <li> <span class="name"> Jiawei Zhao </span> <span class="affiliation"> University of Sydney <a href="https://ror.org/0384j8v12"><?xml version="1.0" encoding="UTF-8" standalone="no"?>  <svg xmlns:i="&ns_ai;" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:svg="http://www.w3.org/2000/svg" xmlns="http://www.w3.org/2000/svg" xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" version="1.1" id="Layer_1" x="0px" y="0px" viewBox="0 0 23.4225 16.696501" xml:space="preserve" sodipodi:docname="rorId.svg" inkscape:version="0.92.5 (2060ec1f9f, 2020-04-08)" width="23.422501" height="16.696501"><metadata id="metadata93"><rdf:RDF><cc:Work rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs id="defs91" /><sodipodi:namedview pagecolor="#ffffff" bordercolor="#666666" borderopacity="1" objecttolerance="10" gridtolerance="10" guidetolerance="10" inkscape:pageopacity="0" inkscape:pageshadow="2" inkscape:window-width="1880" inkscape:window-height="1016" id="namedview89" showgrid="true" showguides="false" inkscape:zoom="1" inkscape:cx="-177.76975" inkscape:cy="13.962506" inkscape:window-x="40" inkscape:window-y="27" inkscape:window-maximized="1" inkscape:current-layer="Layer_1" /> <switch id="switch86" transform="matrix(0.15,0,0,0.15,-0.7305,-0.624)"> <foreignObject requiredExtensions="http://ns.adobe.com/AdobeIllustrator/10.0/" x="0" y="0" width="1" height="1"> </foreignObject> <g i:extraneous="self" id="g84"> <polygon class="strorId0" points="68.65,4.16 56.52,22.74 44.38,4.16 " id="polygon72" style="fill:#53baa1" /> <polygon class="strorId0" points="119.41,4.16 107.28,22.74 95.14,4.16 " id="polygon74" style="fill:#53baa1" /> <polygon class="strorId0" points="44.38,115.47 56.52,96.88 68.65,115.47 " id="polygon76" style="fill:#53baa1" /> <polygon class="strorId0" points="95.14,115.47 107.28,96.88 119.41,115.47 " id="polygon78" style="fill:#53baa1" /> <g id="g82"> <path class="st1" d="m 145.53,63.71 c 4.3,-0.8 7.57,-2.71 9.8,-5.72 2.24,-3.01 3.35,-6.67 3.35,-10.96 0,-3.56 -0.62,-6.52 -1.85,-8.9 -1.23,-2.38 -2.9,-4.27 -4.99,-5.68 -2.09,-1.4 -4.53,-2.41 -7.31,-3.01 -2.78,-0.6 -5.72,-0.9 -8.81,-0.9 h -23.56 v 18.83 c -0.19,-0.55 -0.39,-1.09 -0.61,-1.63 -1.63,-3.95 -3.91,-7.32 -6.84,-10.1 -2.93,-2.78 -6.39,-4.92 -10.41,-6.41 -4.01,-1.49 -8.4,-2.24 -13.16,-2.24 -4.76,0 -9.14,0.75 -13.16,2.24 -4.01,1.49 -7.48,3.63 -10.41,6.41 -2.62,2.49 -4.72,5.46 -6.3,8.9 -0.23,-2.47 -0.81,-4.61 -1.74,-6.41 -1.23,-2.38 -2.9,-4.27 -4.99,-5.68 -2.09,-1.4 -4.53,-2.41 -7.31,-3.01 -2.78,-0.6 -5.72,-0.9 -8.81,-0.9 H 4.87 V 89.42 H 18.28 V 65.08 H 24.9 L 37.63,89.42 H 53.71 L 38.24,63.71 c 4.3,-0.8 7.57,-2.71 9.8,-5.72 0.1,-0.14 0.19,-0.29 0.29,-0.43 -0.02,0.47 -0.03,0.94 -0.03,1.42 0,4.87 0.82,9.29 2.45,13.24 1.63,3.95 3.91,7.32 6.84,10.1 2.92,2.78 6.39,4.92 10.41,6.41 4.01,1.49 8.4,2.24 13.16,2.24 4.76,0 9.14,-0.75 13.16,-2.24 4.01,-1.49 7.48,-3.63 10.41,-6.41 2.92,-2.78 5.2,-6.15 6.84,-10.1 0.22,-0.53 0.42,-1.08 0.61,-1.63 v 18.83 h 13.41 V 65.08 h 6.62 l 12.73,24.34 h 16.08 z M 36.39,50.81 c -0.72,0.92 -1.62,1.59 -2.71,2.02 -1.09,0.43 -2.31,0.69 -3.65,0.77 -1.35,0.09 -2.62,0.13 -3.83,0.13 H 18.29 V 39.89 h 8.77 c 1.2,0 2.44,0.09 3.7,0.26 1.26,0.17 2.38,0.5 3.35,0.99 0.97,0.49 1.78,1.19 2.41,2.11 0.63,0.92 0.95,2.15 0.95,3.7 0,1.65 -0.36,2.94 -1.08,3.86 z m 62.35,16.04 c -0.89,2.38 -2.16,4.44 -3.83,6.19 -1.66,1.75 -3.65,3.11 -5.98,4.09 -2.32,0.98 -4.92,1.46 -7.78,1.46 -2.87,0 -5.46,-0.49 -7.78,-1.46 -2.32,-0.97 -4.31,-2.34 -5.98,-4.09 -1.66,-1.75 -2.94,-3.81 -3.83,-6.19 -0.89,-2.38 -1.33,-5 -1.33,-7.87 0,-2.81 0.44,-5.42 1.33,-7.83 0.89,-2.41 2.16,-4.48 3.83,-6.23 1.66,-1.75 3.65,-3.11 5.98,-4.09 2.32,-0.97 4.91,-1.46 7.78,-1.46 2.87,0 5.46,0.49 7.78,1.46 2.32,0.97 4.31,2.34 5.98,4.09 1.66,1.75 2.94,3.83 3.83,6.23 0.89,2.41 1.33,5.02 1.33,7.83 0,2.87 -0.44,5.49 -1.33,7.87 z m 44.94,-16.04 c -0.72,0.92 -1.62,1.59 -2.71,2.02 -1.09,0.43 -2.31,0.69 -3.65,0.77 -1.35,0.09 -2.62,0.13 -3.83,0.13 h -7.91 V 39.89 h 8.77 c 1.2,0 2.44,0.09 3.7,0.26 1.26,0.17 2.38,0.5 3.35,0.99 0.97,0.49 1.78,1.19 2.41,2.11 0.63,0.92 0.95,2.15 0.95,3.7 0,1.65 -0.36,2.94 -1.08,3.86 z" id="path80" inkscape:connector-curvature="0" style="fill:#202826" /> </g> </g> </switch> </svg> </a> </span> </li> <li> <span class="name"> Zheng Han </span> <span class="affiliation"> University of Sydney <a href="https://ror.org/0384j8v12"><?xml version="1.0" encoding="UTF-8" standalone="no"?>  <svg xmlns:i="&ns_ai;" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:svg="http://www.w3.org/2000/svg" xmlns="http://www.w3.org/2000/svg" xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" version="1.1" id="Layer_1" x="0px" y="0px" viewBox="0 0 23.4225 16.696501" xml:space="preserve" sodipodi:docname="rorId.svg" inkscape:version="0.92.5 (2060ec1f9f, 2020-04-08)" width="23.422501" height="16.696501"><metadata id="metadata93"><rdf:RDF><cc:Work rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs id="defs91" /><sodipodi:namedview pagecolor="#ffffff" bordercolor="#666666" borderopacity="1" objecttolerance="10" gridtolerance="10" guidetolerance="10" inkscape:pageopacity="0" inkscape:pageshadow="2" inkscape:window-width="1880" inkscape:window-height="1016" id="namedview89" showgrid="true" showguides="false" inkscape:zoom="1" inkscape:cx="-177.76975" inkscape:cy="13.962506" inkscape:window-x="40" inkscape:window-y="27" inkscape:window-maximized="1" inkscape:current-layer="Layer_1" /> <switch id="switch86" transform="matrix(0.15,0,0,0.15,-0.7305,-0.624)"> <foreignObject requiredExtensions="http://ns.adobe.com/AdobeIllustrator/10.0/" x="0" y="0" width="1" height="1"> </foreignObject> <g i:extraneous="self" id="g84"> <polygon class="strorId0" points="68.65,4.16 56.52,22.74 44.38,4.16 " id="polygon72" style="fill:#53baa1" /> <polygon class="strorId0" points="119.41,4.16 107.28,22.74 95.14,4.16 " id="polygon74" style="fill:#53baa1" /> <polygon class="strorId0" points="44.38,115.47 56.52,96.88 68.65,115.47 " id="polygon76" style="fill:#53baa1" /> <polygon class="strorId0" points="95.14,115.47 107.28,96.88 119.41,115.47 " id="polygon78" style="fill:#53baa1" /> <g id="g82"> <path class="st1" d="m 145.53,63.71 c 4.3,-0.8 7.57,-2.71 9.8,-5.72 2.24,-3.01 3.35,-6.67 3.35,-10.96 0,-3.56 -0.62,-6.52 -1.85,-8.9 -1.23,-2.38 -2.9,-4.27 -4.99,-5.68 -2.09,-1.4 -4.53,-2.41 -7.31,-3.01 -2.78,-0.6 -5.72,-0.9 -8.81,-0.9 h -23.56 v 18.83 c -0.19,-0.55 -0.39,-1.09 -0.61,-1.63 -1.63,-3.95 -3.91,-7.32 -6.84,-10.1 -2.93,-2.78 -6.39,-4.92 -10.41,-6.41 -4.01,-1.49 -8.4,-2.24 -13.16,-2.24 -4.76,0 -9.14,0.75 -13.16,2.24 -4.01,1.49 -7.48,3.63 -10.41,6.41 -2.62,2.49 -4.72,5.46 -6.3,8.9 -0.23,-2.47 -0.81,-4.61 -1.74,-6.41 -1.23,-2.38 -2.9,-4.27 -4.99,-5.68 -2.09,-1.4 -4.53,-2.41 -7.31,-3.01 -2.78,-0.6 -5.72,-0.9 -8.81,-0.9 H 4.87 V 89.42 H 18.28 V 65.08 H 24.9 L 37.63,89.42 H 53.71 L 38.24,63.71 c 4.3,-0.8 7.57,-2.71 9.8,-5.72 0.1,-0.14 0.19,-0.29 0.29,-0.43 -0.02,0.47 -0.03,0.94 -0.03,1.42 0,4.87 0.82,9.29 2.45,13.24 1.63,3.95 3.91,7.32 6.84,10.1 2.92,2.78 6.39,4.92 10.41,6.41 4.01,1.49 8.4,2.24 13.16,2.24 4.76,0 9.14,-0.75 13.16,-2.24 4.01,-1.49 7.48,-3.63 10.41,-6.41 2.92,-2.78 5.2,-6.15 6.84,-10.1 0.22,-0.53 0.42,-1.08 0.61,-1.63 v 18.83 h 13.41 V 65.08 h 6.62 l 12.73,24.34 h 16.08 z M 36.39,50.81 c -0.72,0.92 -1.62,1.59 -2.71,2.02 -1.09,0.43 -2.31,0.69 -3.65,0.77 -1.35,0.09 -2.62,0.13 -3.83,0.13 H 18.29 V 39.89 h 8.77 c 1.2,0 2.44,0.09 3.7,0.26 1.26,0.17 2.38,0.5 3.35,0.99 0.97,0.49 1.78,1.19 2.41,2.11 0.63,0.92 0.95,2.15 0.95,3.7 0,1.65 -0.36,2.94 -1.08,3.86 z m 62.35,16.04 c -0.89,2.38 -2.16,4.44 -3.83,6.19 -1.66,1.75 -3.65,3.11 -5.98,4.09 -2.32,0.98 -4.92,1.46 -7.78,1.46 -2.87,0 -5.46,-0.49 -7.78,-1.46 -2.32,-0.97 -4.31,-2.34 -5.98,-4.09 -1.66,-1.75 -2.94,-3.81 -3.83,-6.19 -0.89,-2.38 -1.33,-5 -1.33,-7.87 0,-2.81 0.44,-5.42 1.33,-7.83 0.89,-2.41 2.16,-4.48 3.83,-6.23 1.66,-1.75 3.65,-3.11 5.98,-4.09 2.32,-0.97 4.91,-1.46 7.78,-1.46 2.87,0 5.46,0.49 7.78,1.46 2.32,0.97 4.31,2.34 5.98,4.09 1.66,1.75 2.94,3.83 3.83,6.23 0.89,2.41 1.33,5.02 1.33,7.83 0,2.87 -0.44,5.49 -1.33,7.87 z m 44.94,-16.04 c -0.72,0.92 -1.62,1.59 -2.71,2.02 -1.09,0.43 -2.31,0.69 -3.65,0.77 -1.35,0.09 -2.62,0.13 -3.83,0.13 h -7.91 V 39.89 h 8.77 c 1.2,0 2.44,0.09 3.7,0.26 1.26,0.17 2.38,0.5 3.35,0.99 0.97,0.49 1.78,1.19 2.41,2.11 0.63,0.92 0.95,2.15 0.95,3.7 0,1.65 -0.36,2.94 -1.08,3.86 z" id="path80" inkscape:connector-curvature="0" style="fill:#202826" /> </g> </g> </switch> </svg> </a> </span> </li> </ul> </section> <section class="item doi"> <h2 class="label"> DOI: </h2> <span class="value"> <a href="https://doi.org/10.4108/eetiot.v9i1.3271"> https://doi.org/10.4108/eetiot.v9i1.3271 </a> </span> </section> <section class="item keywords"> <h2 class="label"> Keywords: </h2> <span class="value"> Machine Learning, Nonnegative matrix factorization, Robustness of algorithm, NMF </span> </section> <section class="item abstract"> <h2 class="label">Abstract</h2> <p>In machine learning, datasets are often disturbed by different noises. The Nonnegative Matrix Factorization (NMF) algorithm provides a robust method to deal with noise, which will signiﬁcantly improve the efﬁciency of machine learning. In this investigation, the standard NMF algorithm and L<sub>2,1</sub>-Norm Based NMF algorithm are studied by designing experiments on different noise types, noise levels, and datasets. Furthermore, Relative Reconstruction Errors (RRE), accuracy, and Normalized Mutual Information (NMI) are used to evaluate the robustness of the two algorithms. In this experiment, there is no signiﬁcant difference in performance between the two algorithms, while L<sub>2,1</sub>-Norm Based NMF algorithm shows relatively small advantages.</p> </section> <div class="item downloads_chart"> <h3 class="label"> Downloads </h3> <div class="value"> <canvas class="usageStatsGraph" data-object-type="Submission" data-object-id="3271"></canvas> <div class="usageStatsUnavailable" data-object-type="Submission" data-object-id="3271"> Download data is not yet available. </div> </div> </div> <br data-mce-bogus="1">  <a href="https://plu.mx/plum/a/?doi=10.4108/eetiot.v9i1.3271" class="plumx-summary" data-hide-when-empty="true" data-orientation="horizontal" ></a>  <br data-mce-bogus="1"> <section class="item references"> <h2 class="label"> References </h2> <div class="value"> <p>Deng, X., Ma, Y., & Dong, M. (2016). A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN. Pattern Recognition Letters, 79, 8-17. DOI: <a href="https://doi.org/10.1016/j.patrec.2016.04.019">https://doi.org/10.1016/j.patrec.2016.04.019</a> </p> <p>Díaz, A., & Steele, D. (2021). Analysis of the robustness of NMF algorithms. arXiv preprint arXiv:2106.02213. </p> <p>Kong, D., Ding, C., & Huang, H. (2011, October). Robust nonnegative matrix factorization using l21-norm. In Proceedings of the 20th ACM international conference on Information and knowledge management (pp. 673-682). DOI: <a href="https://doi.org/10.1145/2063576.2063676">https://doi.org/10.1145/2063576.2063676</a> </p> <p>Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788-791. </p> <p>Shen, X., Zhang, X., Lan, L., Liao, Q., & Luo, Z. (2019). Another robust NMF: rethinking the hyperbolic tangent function and locality constraint. IEEE Access, 7, 31089-31102. DOI: <a href="https://doi.org/10.1109/ACCESS.2019.2903309">https://doi.org/10.1109/ACCESS.2019.2903309</a> </p> </div> </section> </div> <div class="entry_details"> <div class="item galleys"> <h2 class="pkp_screen_reader"> Downloads </h2> <ul class="value galleys_links"> <li> <a class="obj_galley_link pdf" href="https://publications.eai.eu/index.php/IoT/article/view/3271/2389"> PDF </a> </li> </ul> </div> <div class="item published"> <section class="sub_item"> <h2 class="label"> Published </h2> <div class="value"> <span>22-06-2023</span> </div> </section> </div> <div class="item citation"> <section class="sub_item citation_display"> <h2 class="label"> How to Cite </h2> <div class="value"> <div id="citationOutput" role="region" aria-live="polite"> <div class="csl-bib-body"> <div class="csl-entry"><div class="csl-left-margin">[1]</div><div class="csl-right-inline">M. Kang, J. Zhao, and Z. Han, “Robustness of NMF Algorithms Under Different Noises”, <i>EAI Endorsed Trans IoT</i>, vol. 9, no. 1, p. e4, Jun. 2023.</div></div> </div> </div> <div class="citation_formats"> <button class="cmp_button citation_formats_button" aria-controls="cslCitationFormats" aria-expanded="false" data-csl-dropdown="true"> More Citation Formats </button> <div id="cslCitationFormats" class="citation_formats_list" aria-hidden="true"> <ul class="citation_formats_styles"> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/acm-sig-proceedings?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/acm-sig-proceedings?submissionId=3271&publicationId=3273&return=json" > ACM </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/acs-nano?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/acs-nano?submissionId=3271&publicationId=3273&return=json" > ACS </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/apa?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/apa?submissionId=3271&publicationId=3273&return=json" > APA </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/associacao-brasileira-de-normas-tecnicas?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/associacao-brasileira-de-normas-tecnicas?submissionId=3271&publicationId=3273&return=json" > ABNT </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/chicago-author-date?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/chicago-author-date?submissionId=3271&publicationId=3273&return=json" > Chicago </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/harvard-cite-them-right?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/harvard-cite-them-right?submissionId=3271&publicationId=3273&return=json" > Harvard </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/ieee?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/ieee?submissionId=3271&publicationId=3273&return=json" > IEEE </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/modern-language-association?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/modern-language-association?submissionId=3271&publicationId=3273&return=json" > MLA </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/turabian-fullnote-bibliography?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/turabian-fullnote-bibliography?submissionId=3271&publicationId=3273&return=json" > Turabian </a> </li> <li> <a aria-controls="citationOutput" href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/vancouver?submissionId=3271&publicationId=3273" data-load-citation data-json-href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/get/vancouver?submissionId=3271&publicationId=3273&return=json" > Vancouver </a> </li> </ul> <div class="label"> Download Citation </div> <ul class="citation_formats_styles"> <li> <a href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/download/ris?submissionId=3271&publicationId=3273"> <span class="fa fa-download"></span> Endnote/Zotero/Mendeley (RIS) </a> </li> <li> <a href="https://publications.eai.eu/index.php/IoT/citationstylelanguage/download/bibtex?submissionId=3271&publicationId=3273"> <span class="fa fa-download"></span> BibTeX </a> </li> </ul> </div> </div> </div> </section> </div> <div class="item issue"> <section class="sub_item"> <h2 class="label"> Issue </h2> <div class="value"> <a class="title" href="https://publications.eai.eu/index.php/IoT/issue/view/390"> Vol. 9 No. 1 (2023): EAI Endorsed Transactions on Internet of Things </a> </div> </section> <section class="sub_item"> <h2 class="label"> Section </h2> <div class="value"> Research article </div> </section> <section class="sub_item"> <h2 class="label"> Categories </h2> <div class="value"> <ul class="categories"> <li><a href="https://publications.eai.eu/index.php/IoT/catalog/category/imldase">IoT, Machine Learning and Data Analytics for Smart Environment</a></li> </ul> </div> </section> </div> <div class="item copyright"> <h2 class="label"> License </h2> <p>Copyright (c) 2023 EAI Endorsed Transactions on Internet of Things</p> <a rel="license" href="https://creativecommons.org/licenses/by/3.0/"><img alt="Creative Commons License" src="//i.creativecommons.org/l/by/3.0/88x31.png" /></a><p>This work is licensed under a <a rel="license" href="https://creativecommons.org/licenses/by/3.0/">Creative Commons Attribution 3.0 Unported License</a>.</p> <p>This is an open-access article distributed under the terms of the Creative Commons Attribution <a href="https://creativecommons.org/licenses/by/3.0/" target="_blank" rel="noopener">CC BY 3.0</a> license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.</p> </div> <div class="item addthis"> <div class="value">  <div class="addthis_toolbox addthis_default_style "> <a class="addthis_button_preferred_1"></a> <a class="addthis_button_preferred_2"></a> <a class="addthis_button_preferred_3"></a> <a class="addthis_button_preferred_4"></a> <a class="addthis_button_compact"></a> <a class="addthis_counter addthis_bubble_style"></a> </div> <script type="text/javascript" src="//s7.addthis.com/js/250/addthis_widget.js#pubid="></script>  </div> </div> </div> </div> </article> <div id="articlesBySameAuthorList"> </div> <div id="articlesBySimilarityList"> </div>  <script type="text/javascript" src="//cdn.plu.mx/widget-all.js"></script>  </div> </div> <div class="pkp_structure_sidebar left" role="complementary" aria-label="Sidebar"> <div class="pkp_block block_make_submission"> <h2 class="pkp_screen_reader"> Make a Submission </h2> <div class="content"> <a class="block_make_submission_link" href="https://publications.eai.eu/index.php/IoT/about/submissions"> Make a Submission </a> </div> </div> <div class="pkp_block block_custom" id="customblock-scimago"> <h2 class="title pkp_screen_reader">Scopus</h2> <div class="content"> <p><a href="https://www.scopus.com/sourceid/21101184660" target="_blank" rel="noopener"><img src="https://publications.eai.eu/public/site/images/admin/mceclip0.png"></a></p> </div> </div> <div class="pkp_block block_web_feed"> <h2 class="title">Current Issue</h2> <div class="content"> <ul> <li> <a href="https://publications.eai.eu/index.php/IoT/gateway/plugin/WebFeedGatewayPlugin/atom"> <img src="https://publications.eai.eu/lib/pkp/templates/images/atom.svg" alt="Atom logo"> </a> </li> <li> <a href="https://publications.eai.eu/index.php/IoT/gateway/plugin/WebFeedGatewayPlugin/rss2"> <img src="https://publications.eai.eu/lib/pkp/templates/images/rss20_logo.svg" alt="RSS2 logo"> </a> </li> <li> <a href="https://publications.eai.eu/index.php/IoT/gateway/plugin/WebFeedGatewayPlugin/rss"> <img src="https://publications.eai.eu/lib/pkp/templates/images/rss10_logo.svg" alt="RSS1 logo"> </a> </li> </ul> </div> </div> <div class="pkp_block block_twitter"> <span class="title"></span> <div class="content" > <a class="twitter-timeline" data-height="" data-link-color="" href="" data-dnt="true" data-chrome="" ></a> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script> </div> </div><div class="pkp_block block_Keywordcloud"> <h2 class="title">Keywords</h2> <div class="content" id='wordcloud'></div> <script> function randomColor() { var cores = ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf']; return cores[Math.floor(Math.random()*cores.length)]; } document.addEventListener("DOMContentLoaded", function() { var keywords = [{"text":"machine learning (ml)","size":1},{"text":"context aware","size":1},{"text":"rpl","size":1},{"text":"smart homes","size":1},{"text":"energy-e\u00ffciency","size":1},{"text":"physical layer","size":1},{"text":"bluetooth low energy","size":1},{"text":"ieee 802.15.4","size":1},{"text":"self configuration","size":1},{"text":"mobility","size":1},{"text":"resources allocation","size":1},{"text":"network management","size":1},{"text":"sensor networks","size":1},{"text":"monitoring","size":1},{"text":"flash file systems","size":1},{"text":"nand flash memory","size":1},{"text":"unicyclic block","size":1},{"text":"dynamics","size":1},{"text":"reproducible experiments","size":1},{"text":"minimal representation","size":1},{"text":"nanoparticle emission and diffusion","size":1},{"text":"carbon nanotube-graphene","size":1},{"text":"graphene","size":1},{"text":"carbon nanotube","size":1},{"text":"communication protocols","size":1},{"text":"health monitoring systems","size":1},{"text":"nanoscale communication","size":1},{"text":"wnsns","size":1},{"text":"ringer solution","size":1},{"text":"deployment","size":1},{"text":"titanium nanoparticles","size":1},{"text":"in-body area nanonetwork","size":1},{"text":"timestamp","size":1},{"text":"provenance","size":1},{"text":"wearable","size":1},{"text":"mhealth","size":1},{"text":"smartmesh ip.","size":1},{"text":"feedback erlang block","size":1},{"text":"ph distribution","size":1},{"text":"hybrid yarns","size":1},{"text":"optical buffer","size":1},{"text":"variable length packet","size":1},{"text":"continuous","size":1},{"text":"discrete","size":1},{"text":"polling","size":1},{"text":"queueing","size":1},{"text":"fiber loop","size":1},{"text":"packet send-time accuracy","size":1},{"text":"network calculus","size":1},{"text":"network measurement","size":1}]; var totalWeight = 0; var width = 300; var height = 200; var transitionDuration = 200; var length_keywords = keywords.length; var layout = d3.layout.cloud(); layout.size([width, height]) .words(keywords) .fontSize(function(d) { return fontSize(+d.size); }) .on('end', draw); var svg = d3.select("#wordcloud").append("svg") .attr("viewBox", "0 0 " + width + " " + height) .attr("width", '100%'); function update() { var words = layout.words(); fontSize = d3.scaleLinear().range([16, 34]); if (words.length) { fontSize.domain([+words[words.length - 1].size || 1, +words[0].size]); } } keywords.forEach(function(item,index){totalWeight += item.size;}); update(); function draw(words, bounds) { var w = layout.size()[0], h = layout.size()[1]; scaling = bounds ? Math.min( w / Math.abs(bounds[1].x - w / 2), w / Math.abs(bounds[0].x - w / 2), h / Math.abs(bounds[1].y - h / 2), h / Math.abs(bounds[0].y - h / 2), ) / 2 : 1; svg .append("g") .attr( "transform", "translate(" + [w >> 1, h >> 1] + ")scale(" + scaling + ")", ) .selectAll("text") .data(words) .enter().append("text") .style("font-size", function(d) { return d.size + "px"; }) .style("font-family", 'serif') .style("fill", randomColor) .style('cursor', 'pointer') .style('opacity', 0.7) .attr('class', 'keyword') .attr("text-anchor", "middle") .attr("transform", function(d) { return "translate(" + [d.x, d.y] + ")rotate(" + d.rotate + ")"; }) .text(function(d) { return d.text; }) .on("click", function(d, i){ window.location = "https://publications.eai.eu/index.php/IoT/search?query=QUERY_SLUG".replace(/QUERY_SLUG/, encodeURIComponent(''+d.text+'')); }) .on("mouseover", function(d, i) { d3.select(this).transition() .duration(transitionDuration) .style('font-size',function(d) { return (d.size + 3) + "px"; }) .style('opacity', 1); }) .on("mouseout", function(d, i) { d3.select(this).transition() .duration(transitionDuration) .style('font-size',function(d) { return d.size + "px"; }) .style('opacity', 0.7); }) .on('resize', function() { update() }); } layout.start(); }); </script> </div> </div> </div> <div class="pkp_structure_footer_wrapper" role="contentinfo"> <a id="pkp_content_footer"></a> <div class="pkp_structure_footer"> <div class="pkp_footer_content"> <p><a href="https://eai.eu/" target="_blank" rel="noopener"><strong>European Alliance for Innovation (EAI)</strong></a> is a non-profit organization and a professional community empowering global research and innovation, promoting cooperation between European and International ICT communities around the globe.</p> </div> <div class="pkp_brand_footer" role="complementary"> <a href="https://publications.eai.eu/index.php/IoT/about/aboutThisPublishingSystem"> <img alt="More information about the publishing system, Platform and Workflow by OJS/PKP." src="https://publications.eai.eu/templates/images/ojs_brand.png"> </a> </div> </div> </div> </div> <script src="https://publications.eai.eu/lib/pkp/lib/vendor/components/jquery/jquery.min.js?v=3.3.0.18" type="text/javascript"></script><script src="https://publications.eai.eu/lib/pkp/lib/vendor/components/jqueryui/jquery-ui.min.js?v=3.3.0.18" type="text/javascript"></script><script src="https://publications.eai.eu/plugins/themes/default/js/lib/popper/popper.js?v=3.3.0.18" type="text/javascript"></script><script src="https://publications.eai.eu/plugins/themes/default/js/lib/bootstrap/util.js?v=3.3.0.18" type="text/javascript"></script><script src="https://publications.eai.eu/plugins/themes/default/js/lib/bootstrap/dropdown.js?v=3.3.0.18" type="text/javascript"></script><script src="https://publications.eai.eu/plugins/themes/default/js/main.js?v=3.3.0.18" type="text/javascript"></script><script src="https://publications.eai.eu/plugins/generic/citationStyleLanguage/js/articleCitation.js?v=3.3.0.18" type="text/javascript"></script><script src="https://d3js.org/d3.v4.js?v=3.3.0.18" type="text/javascript"></script><script src="https://cdn.jsdelivr.net/gh/holtzy/D3-graph-gallery@master/LIB/d3.layout.cloud.js?v=3.3.0.18" type="text/javascript"></script><script type="text/javascript">var pkpUsageStats = pkpUsageStats || {};pkpUsageStats.data = pkpUsageStats.data || {};pkpUsageStats.data.Submission = pkpUsageStats.data.Submission || {};pkpUsageStats.data.Submission[3271] = {"data":{"2023":{"1":0,"2":0,"3":0,"4":0,"5":0,"6":0,"7":0,"8":2,"9":1,"10":0,"11":1,"12":0},"2024":{"1":0,"2":1,"3":2,"4":0,"5":0,"6":7,"7":4,"8":7,"9":22,"10":3,"11":4,"12":0}},"label":"All Downloads","color":"79,181,217","total":54};</script><script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/2.0.1/Chart.js?v=3.3.0.18" type="text/javascript"></script><script type="text/javascript">var pkpUsageStats = pkpUsageStats || {};pkpUsageStats.locale = pkpUsageStats.locale || {};pkpUsageStats.locale.months = ["Jan","Feb","Mar","Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec"];pkpUsageStats.config = pkpUsageStats.config || {};pkpUsageStats.config.chartType = "bar";</script><script src="https://publications.eai.eu/plugins/generic/usageStats/js/UsageStatsFrontendHandler.js?v=3.3.0.18" type="text/javascript"></script> </body> </html>

CINXE.COM

Robustness of NMF Algorithms Under Different Noises | EAI Endorsed Transactions on Internet of Things