{"links":{},"id":2005050,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02005050","sets":["6164:6165:6640:1752804461720"]},"path":["1752804461720"],"owner":"11","recid":"2005050","title":["機械学習を用いた蟻コロニー最適化による多目的時間依存オリエンテーリング問題の解法"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2025-06-18"},"_buckets":{"deposit":"6ccedcce-fd20-47cf-b759-9a3d981b7a54"},"_deposit":{"id":"2005050","pid":{"type":"depid","value":"2005050","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"機械学習を用いた蟻コロニー最適化による多目的時間依存オリエンテーリング問題の解法","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"機械学習を用いた蟻コロニー最適化による多目的時間依存オリエンテーリング問題の解法","subitem_title_language":"ja"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"交通データ分析","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2025-06-18","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":"早大"},{"subitem_text_value":"早大"},{"subitem_text_value":"早大"},{"subitem_text_value":"ゼンリンデータコム"},{"subitem_text_value":"早大"},{"subitem_text_value":"早大"}]},"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/2005050/files/IPSJ-DICOMO2025025.pdf","label":"IPSJ-DICOMO2025025.pdf"},"date":[{"dateType":"Available","dateValue":"2027-06-18"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2025025.pdf","filesize":[{"value":"8.3 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":"0f0f511c-23f7-4043-8b80-a6c995fdfda7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2025 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"梶, 翔真"}]},{"creatorNames":[{"creatorName":"梶本, 大"}]},{"creatorNames":[{"creatorName":"野口, 竜弥"}]},{"creatorNames":[{"creatorName":"高山, 敏典"}]},{"creatorNames":[{"creatorName":"鮑, 思雅"}]},{"creatorNames":[{"creatorName":"戸川, 望"}]}]},"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":"本稿では，機械学習を用いた移動時間予測モデルを蟻コロニー最適化 (Ant Colony Optimization: ACO) に統合することで，多目的時間依存オリエンテーリング問題 (Multi-Objective Time-Dependent Orienteering Problem: MOTDOP) を高速に求解するアルゴリズムを提案する．提案手法は，機械学習を用いた移動時間予測モデルによって移動時間を高速かつ高精度に予測する．さらに，ACO の経路構築の際に各移動時間取得ステップに移動時間予測モデルを組み込むことで，移動時間の変動を反映した経路探索を実現し，動的かつ多目的な旅程最適化を可能とする．評価実験では，京都市内の POI を対象としたデータセットで評価を実施し，詳細経路探索 API を用いて ACO による求解を行う従来手法に比べ，提案手法は約 550 倍～ 600 倍の計算時間短縮を達成しつつ，同等のスコアを維持できることを明らかにした．また，提案手法がユーザが重視する価値観に基づき柔軟な経路設計が可能であることも示され，提案手法の実用性と柔軟性を確認した．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"200","bibliographic_titles":[{"bibliographic_title":"マルチメディア，分散，協調とモバイル(DICOMO2025)シンポジウム2025論文集"}],"bibliographicPageStart":"192","bibliographicIssueDates":{"bibliographicIssueDate":"2025-06-18","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2025"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-10-23T04:28:10.250036+00:00","updated":"2025-10-23T04:51:01.484238+00:00"}