{"created":"2020-08-30T13:56:20.888250+00:00","id":3116,"links":{},"metadata":{"_buckets":{"deposit":"033d64ba-46ea-44db-a6f9-1ecffc6ed024"},"_deposit":{"id":"3116","owners":[],"pid":{"revision_id":0,"type":"recid","value":"3116"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/3116","sets":["1582963413512:1596119372420"]},"communities":["ytu"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Modified K-Means for Document Clustering System","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"<p>In&nbsp; today&rsquo;s&nbsp; era&nbsp; of&nbsp; World&nbsp; Wide&nbsp; Web,&nbsp; there&nbsp; is&nbsp; a<br>\ntremendous&nbsp; proliferation&nbsp; in&nbsp; the&nbsp; amount&nbsp; of&nbsp; digitized&nbsp; text<br>\ndocuments. As there is huge collection of documents on the web,<br>\nthere&nbsp; is&nbsp; a&nbsp; need&nbsp; of&nbsp; grouping&nbsp; the&nbsp; set&nbsp; of&nbsp; documents&nbsp; into&nbsp; clusters.<br>\nDocument&nbsp; clustering&nbsp; plays&nbsp; an&nbsp; important&nbsp; role&nbsp; in&nbsp; effectively<br>\nnavigating&nbsp; and&nbsp; organizing&nbsp; the&nbsp; documents.&nbsp; K-Means&nbsp; clustering<br>\nalgorithm&nbsp; is&nbsp; the&nbsp; most&nbsp; commonly&nbsp; document&nbsp; clustering&nbsp; algorithm<br>\nbecause it can be easily implemented and is the most efficient one<br>\nin&nbsp; terms&nbsp; of&nbsp; execution&nbsp; times.&nbsp; The&nbsp; major&nbsp; problem&nbsp; with&nbsp; this<br>\nalgorithm is that it is quite sensitive to selection of initial cluster<br>\ncentroids. The algorithm takes the initial cluster center arbitrarily<br>\nso it does not always promise good clustering results. If the initial<br>\ncentroids&nbsp; are&nbsp; incorrectly&nbsp; determined,&nbsp; the&nbsp; remaining&nbsp; data&nbsp; points<br>\nwith the same similarity scores may fall into the different clusters<br>\ninstead of the same cluster. To overcome this problem,&nbsp;&nbsp; modified<br>\nK-Means&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;&nbsp;&nbsp; Unlike&nbsp; the&nbsp; traditional&nbsp; K-Means<br>\nclustering, the proposed K-Means method can generate the most<br>\ncompact and stable clustering results based on maximum distance<br>\ninitial centroids points instead of random initial centroid points.<br>\nMoreover,&nbsp; the&nbsp; similar&nbsp; data&nbsp; points&nbsp; are&nbsp; clustered&nbsp; based&nbsp; on<br>\nmaximum probability distribution of data points.&nbsp; Therefore, the<br>\nproposed method is more effective and converges to more accurate<br>\nclusters than original K-Means clustering method. In this paper,<br>\nexperimental&nbsp; results&nbsp; are&nbsp; presented&nbsp; in&nbsp; F-measure&nbsp; using&nbsp; 20-News<br>\nGroup standard dataset.</p>"}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"Document clustering"},{"interim":"F-measure"},{"interim":"Initial centroid"},{"interim":"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":"Modified K-Means for Document Clustering System-2016.pdf","filesize":[{"value":"311 Kb"}],"format":"application/pdf","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/3116/files/Modified K-Means for Document Clustering System-2016.pdf"},"version_id":"6026e71d-9240-4bb0-99cb-d5f012f59eab"}]},"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":"2016-10-01"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"10.5281/zenodo.3268423"},"item_title":"Modified K-Means for Document Clustering System","item_type_id":"21","owner":"1","path":["1596119372420"],"publish_date":"2019-07-04","publish_status":"0","recid":"3116","relation_version_is_last":true,"title":["Modified K-Means for Document Clustering System"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T05:47:05.798017+00:00"}