{"id":193886,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00193886","sets":["581:9633:9634"]},"path":["9634"],"owner":"44499","recid":"193886","title":["交通状況把握のための運転行動の時系列性を考慮した車両挙動分析手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-01-15"},"_buckets":{"deposit":"ed2e394b-36fd-4bf5-9bf0-8954c60a1980"},"_deposit":{"id":"193886","pid":{"type":"depid","value":"193886","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"交通状況把握のための運転行動の時系列性を考慮した車両挙動分析手法","author_link":["455237","455238","455239","455240"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"交通状況把握のための運転行動の時系列性を考慮した車両挙動分析手法"},{"subitem_title":"A Method for Analyzing Vehicle Behaviors Considering a Sequence of Driving Actions towards Grasping Traffic Situations","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集：未来の暮らしを支えるパーベイシブシステムと高度交通システム（推薦論文）] プローブ情報システム，車両挙動，運転行動，センシング，SAX（Symbolic Aggregate Approximation）","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2019-01-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"公立はこだて未来大学大学院システム情報科学研究科"},{"subitem_text_value":"公立はこだて未来大学システム情報科学部"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Systems Information Science, Future University Hakodate","subitem_text_language":"en"},{"subitem_text_value":"School of Systems Information Science, Future University Hakodate","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/193886/files/IPSJ-JNL6001011.pdf","label":"IPSJ-JNL6001011.pdf"},"date":[{"dateType":"Available","dateValue":"2021-01-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6001011.pdf","filesize":[{"value":"3.2 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"bfde2660-0c15-4cac-a6e0-e4a38fcb7d4a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"横山, 達也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"白石, 陽"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tatsuya, Yokoyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoh, Shiraishi","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_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":"ドライバは道路上の交通状況によって快適な運転を妨げられることがある．たとえば右折待ちをしている車列が走行経路上に存在する場合，その車列の後続車両は急な減速や車線変更を強いられることがある．このような状況を回避するには，走行予定経路上の交通状況をドライバが事前に把握する必要がある．そこで本論文では，こうした交通状況を形成する車群の挙動を把握するための車両挙動推定に向けた車両挙動分析手法を提案する．ここで車両挙動を，ドライバの運転行動の時系列から構成されるものと定義する．運転行動の時系列性から車両挙動を分析することは，車群の挙動の把握に有用であると考える．本研究では，車載スマートフォンで収集したセンサデータにSAX（Symbolic Aggregate Approximation）を適用することで，時系列データを文字列へ変換する．そして，自然言語処理技術であるN-gramにより，車両挙動を表す文字列から運転行動を部分文字列として抽出し，BoW（Bag of Words）モデルとして車両挙動を表現することで，運転行動の時系列性を考慮した車両挙動分析を行う．評価実験として，BoWモデルを用いたSVM（Support Vector Machine）による車両挙動の分類精度を5分割交差検定で評価した結果，F値が8割以上となり，提案手法の有効性が示唆された．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Traffic situations on a traveling route can hinder comfortable driving. For example, inefficient driving is forced on a succeeding vehicle's driver by a line of vehicles waiting for turning left or right. Drivers need to grasp traffic situations on their traveling route to avoid the situations in advance. Therefore, this paper proposes a method for analyzing vehicle behaviors to grasp the behavior of a group of vehicles forming traffic situations. We define a vehicle behavior as a sequence of driver's driving behaviors. An analysis of vehicle behaviors by using a sequence of driving behaviors will be beneficial for grasping vehicle group's behaviors. This study analyzes vehicle behaviors considering a sequence of driving behaviors. Our method collects sensor data by a smartphone mounted on a vehicle, and converts the collected time-series data to string expression by SAX (Symbolic Aggregate Approximation) and adopts the techniques of natural language processing such as N-gram and BoW (Bag of Words) model in order to express each vehicle behavior. We conducted an experiment to classify typical vehicle behaviors with BoW model by SVM (Support Vector Machine) and examined the classification accuracy by 5-fold cross validation test. The experimental results suggest that the proposed method is effective for estimating vehicle behaviors.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"100","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"87","bibliographicIssueDates":{"bibliographicIssueDate":"2019-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"60"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T23:47:14.958360+00:00","created":"2025-01-19T00:59:01.328310+00:00","links":{}}