{"updated":"2025-01-19T11:33:47.038121+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229385","sets":["1164:3027:11083:11362"]},"path":["11362"],"owner":"44499","recid":"229385","title":["敵対的生成モデルに基づく活動人口の波形描画を用いた混雑寿命予報"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-14"},"_buckets":{"deposit":"deb18616-4634-4b0a-92d1-8833db9be08c"},"_deposit":{"id":"229385","pid":{"type":"depid","value":"229385","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"敵対的生成モデルに基づく活動人口の波形描画を用いた混雑寿命予報","author_link":["616767","616769","616768"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"敵対的生成モデルに基づく活動人口の波形描画を用いた混雑寿命予報"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"AI","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-11-14","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工業大学情報理工学院情報工学系"},{"subitem_text_value":"LINEヤフー株式会社"},{"subitem_text_value":"東京工業大学情報理工学院情報工学系"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, School of Computing, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"LY Corporation","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, School of Computing, Tokyo 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/229385/files/IPSJ-HCI23205019.pdf","label":"IPSJ-HCI23205019.pdf"},"date":[{"dateType":"Available","dateValue":"2025-11-14"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HCI23205019.pdf","filesize":[{"value":"3.6 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":"33"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"8efc7286-d144-428b-9f29-ea0b26ef71f7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"安納, 爽響"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"坪内, 孝太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"下坂, 正倫"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1221543X","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":"2188-8760","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"イベント下の群衆混雑は来訪者の動きに応じて人数の増減パターンが見られ，そのような混雑の発生から消滅までの一連の予報は，来訪者・イベント主催者双方にとって重要なアプリケーションである．既存研究では，イベント種ごとに増減パターンの共通点があることを用いて，増減の状態遷移をイベント情報から学習・予測し，これを基に訪問者の人口密度を推定している．しかし，予測された状態列からは具体的な人数変化量が分からず，そのために発生する局所的な推定の誤りが，時系列上の大きな予測誤差に繋がることが課題であった．本研究ではこの課題の対処のため，状態遷移の代わりに人口密度推移の形状をモデル化する．形状には，状態遷移の持つ増減傾向に加えて，概算的な人数の変化量や推移傾向が反映されるため，混雑の一部始終の傾向補足が可能となり，寿命予測に適していると言える．そこで，形状的特性を精緻にモデル化するため，敵対的生成ネットワーク（Generative Adversarial Nets; GAN）を用いて形状を学習・描画するフレームワークを提案する．実データと人工データで，既存の混雑予報手法と比較して，形状を直接描き出す提案手法が，より小さな誤差で混雑を予測可能であることを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ヒューマンコンピュータインタラクション（HCI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-14","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"19","bibliographicVolumeNumber":"2023-HCI-205"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:28:30.267089+00:00","id":229385,"links":{}}