{"_buckets": {"deposit": "01d80141-3d6b-4c4e-ba76-6f3af7cafbe7"}, "_deposit": {"id": "4677", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "4677"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/4677", "sets": ["1597824273898", "user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Reducing the Size of Feature Set by Using Modified MCA", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Reducing the size of a feature set, withoutaltering the original representation, is anessential data processing step prior to applyinga learning algorithm. The removal of irrelevantand redundant information improves theperformance of machine learning algorithms. Inthis paper, Modified-Multiple CorrespondenceAnalysis (Modified-MCA) is introduced. Itintegrates the correlation and reliabilityinformation between each feature and eachclass. Moreover, the proposed methodcontributes the optimal p-value to improve thereliability. To evaluate the performance ofproposed method, experiments are carried out onten benchmark datasets. In the experiments,three classifiers namely AdaBoost, DecisionTable, JRip are used to verify that the outputfeature dataset produced by proposed methodoutperforms. Using three different classifiers isto get more accurate average classificationresults than using one classifier. The proposedModified-MCA demonstrates reducing the size ofthe feature subspace and promisingclassification results. Moreover, the resultsperforms that the propose method is better than other well-known feature selection methods;MCA, Information Gain and Relief."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Feature Selection"}, {"interim": "Correlation"}, {"interim": "Reliability"}, {"interim": "P-value"}, {"interim": "Confidence Interval"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value": []}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "Fourteenth International Conference On Computer Applications (ICCA 2016)", "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": "Khaing, Myo"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2016-02-25"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/337"}, "item_title": "Reducing the Size of Feature Set by Using Modified MCA", "item_type_id": "21", "owner": "1", "path": ["1597824273898"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000004677", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-07-03"}, "publish_date": "2019-07-03", "publish_status": "0", "recid": "4677", "relation": {}, "relation_version_is_last": true, "title": ["Reducing the Size of Feature Set by Using Modified MCA"], "weko_shared_id": -1}