{"id":240171,"updated":"2025-01-19T08:03:39.469674+00:00","links":{},"created":"2025-01-19T01:44:12.700076+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00240171","sets":["6164:6165:6640:11802"]},"path":["11802"],"owner":"44499","recid":"240171","title":["GANを用いた時系列データの異常検知における異常度算出方法についての考察"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-19"},"_buckets":{"deposit":"fa7e7c4e-f9a0-4054-b3d7-56b4944fdd1f"},"_deposit":{"id":"240171","pid":{"type":"depid","value":"240171","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"GANを用いた時系列データの異常検知における異常度算出方法についての考察","author_link":["658538","658537","658539","658540"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"GANを用いた時系列データの異常検知における異常度算出方法についての考察"},{"subitem_title":"Consideration of Anomaly Score Calculation Method in Anomaly Detection of Time Series Data Using GAN","subitem_title_language":"en"}]},"item_type_id":"18","publish_date":"2024-06-19","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"お茶の水女子大学"},{"subitem_text_value":"お茶の水女子大学／中央大学"},{"subitem_text_value":"津田塾大学"},{"subitem_text_value":"お茶の水女子大学"}]},"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/240171/files/IPSJ-DICOMO2024055.pdf","label":"IPSJ-DICOMO2024055.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2024055.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"de77ebfc-8626-45b3-9595-0cc16a0df2b9","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"森, 仁美"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"丸, 千尋"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"中野, 美由紀"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小口, 正人"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"異常検知の技術は，ネットワークの不正アクセスの検知，医療診断，製造業における部品検査など様々な分野において用いられており，盛んに研究が行われている．深層学習モデルによる高精度な異常検知手法の中でも，GANを使用するものは，対象データの複雑な特徴の抽出や様々なデータ形式への柔軟な適応が可能である．GANを用いる場合，再構築誤差と識別誤差の2つの指標を用いて異常度が算出される．再構築誤差は異常検知対象のデータとGANのGeneratorによる再構築データとの差分，識別誤差はDiscriminatorの判定結果である．本稿では，時系列データに対してMAD-GANとEfficient GANを融合したGANを用いて異常検知を実施し，異常度算出時に使用される2つの指標の比率に着目して，各指標が異常検知精度に及ぼす影響を評価した．また，異常検知対象のデータに関する条件を変えて実験を行い，結果を比較した上で考察を行った．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"423","bibliographic_titles":[{"bibliographic_title":"マルチメディア，分散，協調とモバイルシンポジウム2024論文集"}],"bibliographicPageStart":"418","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-19","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}