{"id":2001024,"created":"2025-02-25T07:51:34.885245+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02001024","sets":["1164:3980:11909:1740468540611"]},"path":["1740468540611"],"owner":"80578","recid":"2001024","title":["モデルブリッジを用いたミクロレベルの交通シミュレーションデータ同化の高速化"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2025-03-05"},"_buckets":{"deposit":"e3c9dd54-bf03-4009-bef4-c5cbe5332be6"},"_deposit":{"id":"2001024","pid":{"type":"depid","value":"2001024","revision_id":0},"owners":[80578],"status":"published","created_by":80578},"item_title":"モデルブリッジを用いたミクロレベルの交通シミュレーションデータ同化の高速化","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"モデルブリッジを用いたミクロレベルの交通シミュレーションデータ同化の高速化","subitem_title_language":"ja"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"交通シミュレーションと自動運転","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2025-03-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"産業技術総合研究所人工知能研究センター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"AIST","subitem_text_language":"en"},{"subitem_text_value":"AIST","subitem_text_language":"en"},{"subitem_text_value":"AIST","subitem_text_language":"en"},{"subitem_text_value":"AIST","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/2001024/files/IPSJ-ITS25100016.pdf","label":"IPSJ-ITS25100016.pdf"},"date":[{"dateType":"Available","dateValue":"2027-03-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ITS25100016.pdf","filesize":[{"value":"2.6 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":"37"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"bb0be84a-44d9-423b-bc77-96e6c406c6fe","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2025 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"重中,秀介"}]},{"creatorNames":[{"creatorName":"西田,遼"}]},{"creatorNames":[{"creatorName":"山崎,啓介"}]},{"creatorNames":[{"creatorName":"大西,正輝"}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11515904","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":"2188-8965","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"ミクロ交通シミュレーションは，個別の車両動作や車両間の相互作用を詳細にモデル化する強力なツールである．このシミュレーションは，道路の流量や密度の解析に加え，特定車両の移動時間やエネルギー消費量の評価にも役立つ．ただし，ミクロ交通シミュレーションを現実世界で効果的に活用するためには，モデルの精度向上が不可欠である．データ同化は，観測データとシミュレーション結果の誤差を最小化することで，シミュレーションのパラメータを調整し，モデルの精度向上に役立つ手法である．しかし，数万台規模の車両動作を扱う場合，シミュレーションの実行に膨大な計算負荷がかかるため，少数のパラメータであっても最適値の探索が困難となる．本研究では，ミクロ交通シミュレーションの代わりに，交通量から車両速度を表現するマクロ交通シミュレーションを構成し，2つの関係を学習するモデルブリッジ法を適用することで，超高速なパラメータ探索を実現する手法を提案する．提案手法は，人工的に生成した都市交通10シナリオのパラメータ推定実験において，観測データとの類似度，パラメータ推定精度，および実行時間の全ての指標において，既存手法を上回る性能を示した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告高度交通システムとスマートコミュニティ（ITS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2025-03-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"16","bibliographicVolumeNumber":"2025-ITS-100"}]},"relation_version_is_last":true,"weko_creator_id":"80578"},"updated":"2025-02-25T07:51:39.059564+00:00","links":{}}