{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00238523","sets":["1164:2735:11468:11707"]},"path":["11707"],"owner":"44499","recid":"238523","title":["主成分分析のためのOQDS法の実装方法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-08-29"},"_buckets":{"deposit":"b71cbb6a-2a3c-4a72-b736-8f89f48890ba"},"_deposit":{"id":"238523","pid":{"type":"depid","value":"238523","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"主成分分析のためのOQDS法の実装方法の提案","author_link":["653163","653162","653161","653160"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"主成分分析のためのOQDS法の実装方法の提案"},{"subitem_title":"Proposed implementation of the OQDS Method for Principal Component Analysis","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2024-08-29","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"奈良女子大学大学院人間文化総合科学研究科"},{"subitem_text_value":"奈良女子大学研究院生活情報通信科学領域"},{"subitem_text_value":"福井大学"},{"subitem_text_value":"大阪成蹊大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Nara Women's University Graduate School of Humanities and Sciences","subitem_text_language":"en"},{"subitem_text_value":"Nara Women's University Research Group of Information and Communication Technology for Life","subitem_text_language":"en"},{"subitem_text_value":"University of Fukui","subitem_text_language":"en"},{"subitem_text_value":"Osaka Seikei University","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/238523/files/IPSJ-MPS24150003.pdf","label":"IPSJ-MPS24150003.pdf"},"date":[{"dateType":"Available","dateValue":"2026-08-29"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS24150003.pdf","filesize":[{"value":"974.1 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"adbde82b-a959-42ac-8da7-bba2485aa063","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"千代延, 未帆"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"髙田, 雅美"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"木村, 欣司"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中村, 佳正"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","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":"2188-8833","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿では，一部の特異値と特異ベクトルのみを計算するための手法を提案する．主成分分析 (PCA:Principal Component Analysis) では，大きいほうから数個の特異値と特異ベクトルが必要になる．一般的には，拡大行列に対する 2 分法と逆反復法を組み合わせることによって求められるが，glued Kimura 行列のように計算精度が劣る行列が存在する．そこで，本稿では OQDS（Orthogonal QD with Shift）法を用いる．OQDS 法は，計算途中で行列が分割されなければ，下 2 重対角行列の小さいほうから数個の特異値と右特異ベクトルを高精度に計算できる．Split が生じる場合，小さい特異値がどちらのブロック行列に含まれるかは明らかではないため，主成分分析に OQDS 法を適用するためには Split への対応を考える必要がある．よって，本研究では Split の影響を受けずに，小さい方から数個の特異値と右特異ベクトルを得るための OQDS 法の実装方法を提案する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-08-29","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"2024-MPS-150"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T08:32:28.215456+00:00","created":"2025-01-19T01:41:48.305289+00:00","links":{},"id":238523}