{"created":"2020-08-30T13:56:28.136341+00:00","id":3117,"links":{},"metadata":{"_buckets":{"deposit":"8e653531-25ce-4ec3-944f-28a3de73ffd3"},"_deposit":{"id":"3117","owners":[],"pid":{"revision_id":0,"type":"recid","value":"3117"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/3117","sets":["1582963413512:1596119372420"]},"communities":["ytu"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Systematic Selection of Initial Centroid for K-Means Document  Clustering System","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"<p>As the number of electronic documents generated<br>\nfrom&nbsp; worldwide&nbsp; source&nbsp; increases,&nbsp; it&nbsp; is&nbsp; hard&nbsp; to&nbsp; manually<br>\norganize,&nbsp; analyze&nbsp; and&nbsp; present&nbsp; these&nbsp; documents&nbsp; efficiently.<br>\nDocument&nbsp; clustering&nbsp; is&nbsp; one&nbsp; of&nbsp; the&nbsp; traditionally&nbsp; data&nbsp; mining<br>\ntechniques and an unsupervised learning paradigm. Fast and<br>\nhigh&nbsp; quality&nbsp; document&nbsp; clustering&nbsp; algorithms&nbsp; play&nbsp; an<br>\nimportant&nbsp; role&nbsp; in&nbsp; helping&nbsp; users&nbsp; to&nbsp; effectively&nbsp; navigate,<br>\nsummarize and organize the information. K-Means algorithm<br>\nis&nbsp; the&nbsp; most&nbsp; commonly&nbsp; used&nbsp; partitioned&nbsp; clustering&nbsp; algorithm<br>\nbecause it can be easily implemented and is the most efficient<br>\none in terms of execution times. However, the major problem<br>\nwith&nbsp; this&nbsp; algorithm&nbsp; is&nbsp; that&nbsp; it&nbsp; is&nbsp; sensitive&nbsp; to&nbsp; the&nbsp; selection&nbsp; of<br>\ninitial&nbsp; centroid&nbsp; and&nbsp; may&nbsp; converge&nbsp; to&nbsp; local&nbsp; optima.&nbsp; The<br>\nalgorithm takes the initial cluster centre arbitrarily so it does<br>\nnot always guarantee good clustering results. Different initial<br>\ncluster&nbsp; centres&nbsp; often&nbsp; lead&nbsp; to&nbsp; different&nbsp; clustering&nbsp; and&nbsp; thus<br>\nprovide unstable clustering results. To overcome this problem,&nbsp; &nbsp;<br>\nSystematic Selection of Initial Centroid for K-Means (SSIC K-<br>\nMeans)&nbsp; approach&nbsp; is&nbsp; proposed&nbsp; to&nbsp; improve&nbsp; the&nbsp; quality&nbsp; of<br>\nclustering&nbsp; in&nbsp; this&nbsp; paper.&nbsp; Unlike&nbsp; the&nbsp; traditional&nbsp; K-Means<br>\nclustering, the proposed SSIC K-Means method can generate<br>\nthe&nbsp; most&nbsp; compact&nbsp; and&nbsp; stable&nbsp; clustering&nbsp; results&nbsp; based&nbsp; on<br>\nmaximum distance initial centroids points instead of random<br>\ninitial centroid points. In this paper, experimental results are<br>\npresented&nbsp; in&nbsp; F-measures&nbsp; using&nbsp; 20&nbsp; Newsgroup&nbsp; standard<br>\ndatasets.&nbsp; The&nbsp; evaluations&nbsp; demonstrate&nbsp; that&nbsp; the&nbsp; proposed<br>\nsolution outperforms the other initialization methods and can<br>\nbe applied for other various standard datasets.</p>"}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"Document clustering"},{"interim":"Data mining"},{"interim":"K-Means"},{"interim":"Initial centroid"},{"interim":"SSIC K-Means"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2019-07-04"}],"displaytype":"preview","filename":"Systematic Selection of Initial Centroid for K-Means Document Clustering System.pdf","filesize":[{"value":"251 Kb"}],"format":"application/pdf","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/3117/files/Systematic Selection of Initial Centroid for K-Means Document Clustering System.pdf"},"version_id":"aa0b4c3e-0c8d-4e66-925c-d5edd590e0ad"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"","subitem_journal_title":"","subitem_pages":"","subitem_volume":""}]},"item_1583103147082":{"attribute_name":"Conference papers","attribute_value_mlt":[{"subitem_acronym":"","subitem_c_date":"","subitem_conference_title":"","subitem_part":"","subitem_place":"","subitem_session":"","subitem_website":""}]},"item_1583103211336":{"attribute_name":"Books/reports/chapters","attribute_value_mlt":[{"subitem_book_title":"","subitem_isbn":"","subitem_pages":"","subitem_place":"","subitem_publisher":""}]},"item_1583103233624":{"attribute_name":"Thesis/dissertations","attribute_value_mlt":[{"subitem_awarding_university":"","subitem_supervisor(s)":[{"subitem_supervisor":""}]}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Tin Thu Zar Win"},{"subitem_authors_fullname":"Moe Moe Aye"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Conference paper"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2016-12-29"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"10.5281/zenodo.3268434"},"item_title":"Systematic Selection of Initial Centroid for K-Means Document  Clustering System","item_type_id":"21","owner":"1","path":["1596119372420"],"publish_date":"2019-07-04","publish_status":"0","recid":"3117","relation_version_is_last":true,"title":["Systematic Selection of Initial Centroid for K-Means Document  Clustering System"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T05:47:14.691127+00:00"}