{"_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": ["user-ytu"]}, "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": "\u003cp\u003eIn\u0026nbsp; today\u0026rsquo;s\u0026nbsp; era\u0026nbsp; of\u0026nbsp; World\u0026nbsp; Wide\u0026nbsp; Web,\u0026nbsp; there\u0026nbsp; is\u0026nbsp; a\u003cbr\u003e\ntremendous\u0026nbsp; proliferation\u0026nbsp; in\u0026nbsp; the\u0026nbsp; amount\u0026nbsp; of\u0026nbsp; digitized\u0026nbsp; text\u003cbr\u003e\ndocuments. As there is huge collection of documents on the web,\u003cbr\u003e\nthere\u0026nbsp; is\u0026nbsp; a\u0026nbsp; need\u0026nbsp; of\u0026nbsp; grouping\u0026nbsp; the\u0026nbsp; set\u0026nbsp; of\u0026nbsp; documents\u0026nbsp; into\u0026nbsp; clusters.\u003cbr\u003e\nDocument\u0026nbsp; clustering\u0026nbsp; plays\u0026nbsp; an\u0026nbsp; important\u0026nbsp; role\u0026nbsp; in\u0026nbsp; effectively\u003cbr\u003e\nnavigating\u0026nbsp; and\u0026nbsp; organizing\u0026nbsp; the\u0026nbsp; documents.\u0026nbsp; K-Means\u0026nbsp; clustering\u003cbr\u003e\nalgorithm\u0026nbsp; is\u0026nbsp; the\u0026nbsp; most\u0026nbsp; commonly\u0026nbsp; document\u0026nbsp; clustering\u0026nbsp; algorithm\u003cbr\u003e\nbecause it can be easily implemented and is the most efficient one\u003cbr\u003e\nin\u0026nbsp; terms\u0026nbsp; of\u0026nbsp; execution\u0026nbsp; times.\u0026nbsp; The\u0026nbsp; major\u0026nbsp; problem\u0026nbsp; with\u0026nbsp; this\u003cbr\u003e\nalgorithm is that it is quite sensitive to selection of initial cluster\u003cbr\u003e\ncentroids. The algorithm takes the initial cluster center arbitrarily\u003cbr\u003e\nso it does not always promise good clustering results. If the initial\u003cbr\u003e\ncentroids\u0026nbsp; are\u0026nbsp; incorrectly\u0026nbsp; determined,\u0026nbsp; the\u0026nbsp; remaining\u0026nbsp; data\u0026nbsp; points\u003cbr\u003e\nwith the same similarity scores may fall into the different clusters\u003cbr\u003e\ninstead of the same cluster. To overcome this problem,\u0026nbsp;\u0026nbsp; modified\u003cbr\u003e\nK-Means\u0026nbsp; approach\u0026nbsp; is\u0026nbsp; proposed\u0026nbsp; to\u0026nbsp; improve\u0026nbsp; the\u0026nbsp; quality\u0026nbsp; of\u003cbr\u003e\nclustering\u0026nbsp; in\u0026nbsp; this\u0026nbsp; paper.\u0026nbsp;\u0026nbsp;\u0026nbsp; Unlike\u0026nbsp; the\u0026nbsp; traditional\u0026nbsp; K-Means\u003cbr\u003e\nclustering, the proposed K-Means method can generate the most\u003cbr\u003e\ncompact and stable clustering results based on maximum distance\u003cbr\u003e\ninitial centroids points instead of random initial centroid points.\u003cbr\u003e\nMoreover,\u0026nbsp; the\u0026nbsp; similar\u0026nbsp; data\u0026nbsp; points\u0026nbsp; are\u0026nbsp; clustered\u0026nbsp; based\u0026nbsp; on\u003cbr\u003e\nmaximum probability distribution of data points.\u0026nbsp; Therefore, the\u003cbr\u003e\nproposed method is more effective and converges to more accurate\u003cbr\u003e\nclusters than original K-Means clustering method. In this paper,\u003cbr\u003e\nexperimental\u0026nbsp; results\u0026nbsp; are\u0026nbsp; presented\u0026nbsp; in\u0026nbsp; F-measure\u0026nbsp; using\u0026nbsp; 20-News\u003cbr\u003e\nGroup standard dataset.\u003c/p\u003e"}]}, "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", "download_preview_message": "", "file_order": 0, "filename": "Modified K-Means for Document Clustering System-2016.pdf", "filesize": [{"value": "311 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "mimetype": "application/pdf", "size": 311000.0, "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"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000003116", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-07-04"}, "publish_date": "2019-07-04", "publish_status": "0", "recid": "3116", "relation": {}, "relation_version_is_last": true, "title": ["Modified K-Means for Document Clustering System"], "weko_shared_id": -1}