{"updated":"2025-01-19T10:01:55.632517+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00233370","sets":["581:11492:11495"]},"path":["11495"],"owner":"44499","recid":"233370","title":["データ駆動型人流シミュレーションのモデル汎化手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-15"},"_buckets":{"deposit":"30928039-6f9b-4cb8-8b44-3ef7b03043b7"},"_deposit":{"id":"233370","pid":{"type":"depid","value":"233370","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"データ駆動型人流シミュレーションのモデル汎化手法の検討","author_link":["633761","633760","633759","633758"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"データ駆動型人流シミュレーションのモデル汎化手法の検討"},{"subitem_title":"Model Generalizaiton Method for People-flow Simulation with Data Driven Approach","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文（推薦論文，特選論文）] 人流シミュレーション，モデル汎化，経路探索，深層学習，動線データ","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2024-03-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"株式会社日立製作所 研究開発グループ"},{"subitem_text_value":"株式会社日立製作所 研究開発グループ"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Hitachi, Ltd., R&D Group","subitem_text_language":"en"},{"subitem_text_value":"Hitachi, Ltd., R&D Group","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/233370/files/IPSJ-JNL6503017.pdf","label":"IPSJ-JNL6503017.pdf"},"date":[{"dateType":"Available","dateValue":"2026-03-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6503017.pdf","filesize":[{"value":"6.4 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"ee6740c7-0277-44c2-bfa8-36f1b00f0e35","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"北野, 佑"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"鍬本, 賢志"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yu, Kitano","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoshi, Kuwamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_publisher_15":{"attribute_name":"公開者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"公共施設や商業施設，工場・倉庫における人や物の動きに関するデータ（動線データ）の分析・利活用が近年注目されている．施設運用の効率化につながる施策検討において，施策効果を事前に定量評価するには，人流シミュレーションが有用だが，モデル学習に用いる動線データのレイアウトとシミュレーション時のレイアウトが大きく異なる際に従来手法の精度が低いという問題があった．この問題に対処するため，本研究では人流シミュレーションのモデル汎化手法を提案する．経路探索による学習データ拡張と，距離特徴量の1次元CNNによる深層学習モデルに基づく人流シミュレーション手法を提案し，某空港を対象としたシミュレーション精度評価を行ったところ，人密度ヒートマップに関して平均絶対誤差が10%改善されることを確認した．本手法によって得られたシミュレーションデータを統計分析することで，施策効果を定量評価することができる．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently, trajectory data, such as flow data of pedestrians or moving objects, is receiving a lot of attention for efficient operations of general facilities, such as public or commercial facilities, factories or warehouses. People-flow simulation can be used to evaluate the provisions' effects for facility management. However there is a problem of low accuracy in the case that the layout environments in measurement trajectory data and simulation data differ significantly. To address this problem, we propose a model generalization method for people-flow simulation, which takes into acount the following two components: 1) augmenting training trajectory data based on the pathfinding approach, and 2) training 1D-CNN-based prediction model considering the spatial continuity of distance features. We conducted the simulation experiments in an airport and got reduced mean absolute error by 10%, comparing with the previous method. The provisions' effects for facility management can be evaluated by statistical analysis of simulated trajectories based on our method.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"738","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"729","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"65"}]},"relation_version_is_last":true,"item_2_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.20729/00233256","subitem_identifier_reg_type":"JaLC"}]},"weko_creator_id":"44499"},"created":"2025-01-19T01:34:46.309066+00:00","id":233370,"links":{}}