{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231564","sets":["1164:1165:11326:11415"]},"path":["11415"],"owner":"44499","recid":"231564","title":["XAIによる教師なしクラスタリング の解釈方法について"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-12-19"},"_buckets":{"deposit":"635635e4-9120-402e-aa37-22dd39c73a79"},"_deposit":{"id":"231564","pid":{"type":"depid","value":"231564","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"XAIによる教師なしクラスタリング の解釈方法について","author_link":["625283","625281","625282","625280"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"XAIによる教師なしクラスタリング の解釈方法について"},{"subitem_title":"Interpretation of unsupervised clustering based on XAI","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"データ工学","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-12-19","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"千葉工業大学大学院先進工学研究科"},{"subitem_text_value":"千葉工業大学先進工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Advanced Engineering, Chiba Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Advanced Engineering, Chiba Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/231564/files/IPSJ-DBS23178003.pdf","label":"IPSJ-DBS23178003.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS23178003.pdf","filesize":[{"value":"1.6 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"cff027ad-2bbe-42dc-bab5-1e5e672c94b3","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"佐々木, 裕"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"齊藤, 史哲"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yu, Sasaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Fumiaki, Saitoh","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112482","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-871X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"説明可能な人工知能（XAI）は，AI システムの意思決定に透明性や解釈性を導入することを目的としており，多くの場合では XAI は分類や回帰などの教師あり学習に適用されている．一般的に産業において AI を用いる際，データにはラベルがついていない教師なしタスクであることも多い．そのため XAI 手法を教師なし学習へ適用させるためには，教師なしタスクを教師ありタスクへ変換することによって，結果について説明をあたえる方法を構築する必要がある．本研究では，クラスタリングにより疑似的なラベルを付与した SHAP を適用することで，XAI を教師なし学習に拡張することを提案する．ベンチマークデータへの適用を通じて提案法の挙動を確認し，適切に機能することを検証した．\n","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Explainable Artificial Intelligence (XAI) aims to introduce transparency and interpretability into the decision-making of AI systems, often applied in supervised learning tasks such as classification and regression. In many industrial applications of AI, tasks involve unsupervised learning where data lacks labeled information. To apply XAI techniques to unsupervised learning, it is necessary to construct methods that provide explanations for results by transforming unsupervised tasks into supervised ones. In this study, we propose an extension of XAI to unsupervised learning by applying SHAP with pseudo-labels obtained through clustering. Through the application of our proposed method to benchmark data, we validate its behavior and confirm its effective functionality.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム（DBS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-12-19","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"2023-DBS-178"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T10:43:17.511379+00:00","created":"2025-01-19T01:31:56.427587+00:00","id":231564}