{"created":"2020-08-30T13:54:33.074699+00:00","id":3101,"links":{},"metadata":{"_buckets":{"deposit":"3e307aa6-01b1-4570-90a6-506632d707ab"},"_deposit":{"id":"3101","owners":[],"pid":{"revision_id":0,"type":"recid","value":"3101"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/3101","sets":["1582963413512:1596119372420"]},"communities":["ytu"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Efficient Document Clustering System Basedon Probability Distribution ofK-Means(PD K-Means) Model","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"<p>In document clustering system, some documents with the same similarity scores may fall into different clusters instead of same cluster due to calculate similarity distance between pairs of documents based on geometric measurements.&nbsp; To tackle this point, probability distribution of KMeans (PD K-Means) algorithm is proposed. In this system, documents are clustered based on proposed probability distribution equation instead of similarity measure between objects. It can also solve initial centroids problems of K-Means by using Systematic Selection of Initial Centroid (SSIC) approach. So, it not only can generate compact and stable results but also eliminates initial cluster problem of K-Means. According to the experiment, F-measure values increase about 0.28 in 20NewsGroup dataset, 0.26 in R8 and 0.14 in R52 from Reuter21578 datasets. The evaluations demonstrate that the proposed solution outperforms than original method and can be applied for various standard and unsupervised datasets.</p>"}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"Initial  Centroid"},{"interim":"Probability Distribution"},{"interim":"PD K-Means"},{"interim":"SSIC"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2019-06-27"}],"displaytype":"preview","filename":"Efficient Document Clustering System Basedon Probability Distribution ofK-Means(PD K-Means) Model Tin Thu Zar Win (Ph D IJSHRE journal).pdf","filesize":[{"value":"152 Kb"}],"format":"application/pdf","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/3101/files/Efficient Document Clustering System Basedon Probability Distribution ofK-Means(PD K-Means) Model Tin Thu Zar Win (Ph D IJSHRE journal).pdf"},"version_id":"e03b8248-2272-4fea-bc1f-76b772cb83cc"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"Issue 8","subitem_journal_title":"International Journal of Software & Hardware Research in Engineering","subitem_pages":"pp. 1-6","subitem_volume":"Volume 5"}]},"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":"Nang Aye Aye Htwe"},{"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":"Journal article"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2017-10-06"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"10.5281/zenodo.3131916"},"item_title":"Efficient Document Clustering System Basedon Probability Distribution ofK-Means(PD K-Means) Model","item_type_id":"21","owner":"1","path":["1596119372420"],"publish_date":"2019-06-27","publish_status":"0","recid":"3101","relation_version_is_last":true,"title":["Efficient Document Clustering System Basedon Probability Distribution ofK-Means(PD K-Means) Model"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T05:46:24.369171+00:00"}