{"updated":"2025-01-19T17:40:35.034519+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00211789","sets":["1164:10193:10565:10617"]},"path":["10617"],"owner":"44499","recid":"211789","title":["量子アニーリングによる学習データのオーバーサンプリング"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-06-24"},"_buckets":{"deposit":"6ad29cec-f158-43ed-accd-ffef2d2fb4b9"},"_deposit":{"id":"211789","pid":{"type":"depid","value":"211789","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"量子アニーリングによる学習データのオーバーサンプリング","author_link":["538747","538746","538744","538748","538749","538745"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"量子アニーリングによる学習データのオーバーサンプリング"},{"subitem_title":"Over Sampling Technique Using Quantum annealing for Supervised Machine Learning","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2021-06-24","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"株式会社日本総合研究所"},{"subitem_text_value":"NECソリューションイノベータ株式会社"},{"subitem_text_value":"日本電気株式会社"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The Japan Research Institute, Limited","subitem_text_language":"en"},{"subitem_text_value":"NEC Solution Innovators, Ltd.","subitem_text_language":"en"},{"subitem_text_value":"NEC Corporation","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/211789/files/IPSJ-QS21003014.pdf","label":"IPSJ-QS21003014.pdf"},"date":[{"dateType":"Available","dateValue":"2023-06-24"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-QS21003014.pdf","filesize":[{"value":"723.8 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":"53"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"a0260112-952a-4d6d-b98e-39e8282cb3ac","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"身野, 良寛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"柴田, 将"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中村, 暢達"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yoshihiro, Mino","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sho, Shibata","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobutatsu, Nakamura","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12894105","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":"2435-6492","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"金融取引等において，機械学習を活用した不正検知システムが導入されつつあるが，不正データが少ないために，学習データの量が十分でないことが問題となっている．量子アニーリングを用いた制限ボルツマンマシンによって，不正データに相当する学習データを生成する手法は，従来のオーバーサンプリング方式よりも確からしい学習データを増量させることができ，結果，不正検知の精度を向上できる可能性がある．本報告では，Kaggle で公開されている金融取引データに対し，量子アニーリングを使ったオーバーサンプリングを適用する検証を行い，その有効性を確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"量子ソフトウェア（QS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-06-24","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"14","bibliographicVolumeNumber":"2021-QS-3"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":211789,"created":"2025-01-19T01:12:55.446600+00:00"}