{"updated":"2025-01-21T15:47:31.851549+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00090967","sets":["1164:4061:7115:7116"]},"path":["7116"],"owner":"11","recid":"90967","title":["時間帯と同行者の状況変化に追従した歩幅推定手法の提案と評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2013-03-07"},"_buckets":{"deposit":"4c940815-3394-4587-baf7-2f9c9a4206b8"},"_deposit":{"id":"90967","pid":{"type":"depid","value":"90967","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"時間帯と同行者の状況変化に追従した歩幅推定手法の提案と評価","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"時間帯と同行者の状況変化に追従した歩幅推定手法の提案と評価"},{"subitem_title":"An Adaptive Step Length Reasoning for Time Periods and Members of a User's Party","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"行動認識・状況推定","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2013-03-07","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"明石工業高等専門学校専攻科機械・電子システム工学専攻"},{"subitem_text_value":"明石工業高等専門学校電気情報工学科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Advanced Course of Mechanical and Electronic System Engineering, Advanced Course of Akashi National Colleage of Technology.","subitem_text_language":"en"},{"subitem_text_value":"Electrical and Computer Engineering, Akashi National Colleage 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/90967/files/IPSJ-UBI13037032.pdf"},"date":[{"dateType":"Available","dateValue":"2015-03-07"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-UBI13037032.pdf","filesize":[{"value":"1.4 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":"36"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"922fd4e8-da8f-440b-842a-690175e81447","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2013 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"三宅, 孝幸"},{"creatorName":"新井, イスマイル"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takayuki, Miyake","creatorNameLang":"en"},{"creatorName":"Ismail, Arai","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11838947","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"屋内測位手法の 1 つである歩行者向けデッドレコニングにおいて，歩数・歩幅・進行方向の正確な推定は不可欠である．本研究ではこれらの推定のうち，特に歩幅推定の精度向上を目的とする．従来の歩幅推定手法は，事前に手作業によるパラメータ入力や，学習を行なっておく必要があるといった問題がある．さらに，歩幅は歩行する時間帯や同行者の有無など，様々な要因に影響を受け，変化すると考えられるため，これらの手法が日々の変化に十分対応できているとは言えない．そこで，端末に搭載されている加速度センサ・GPS を用いて，デッドレコニング開始前に歩幅を自動学習することによって，事前のパラメータ入力を必要とせず，日々の変化に追従した歩幅推定手法を提案する．そして，同行者数が変化した場合や，歩行する時間帯が変化した場合における歩幅変化について検証を行った．検証の結果，単独歩行時の平均絶対誤差は約 2.81cm，同行者数変化に追従する歩幅計算式を用いた場合の平均絶対誤差は，概ね 3～4cm となった．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"PDR(Pedestrian Dead Reckoning) requires to estimate the exact step count, step length and direction. This study aimed to improve the accuracy of the step length reasoning. The conventional PDRs require a pre-learning such as walking several hundreds meters and manually input parameters. Furthermore, the conventional PDRs don't adapt to circumstance variations such as time periods, a number of users companion. To solve these problems, we propose the step length reasoning method which is automatically learning step length from the GPS before starting PDR. As a result of evaluation, mean absolute error of step length becomes about 2.81 cm when walking alone, about 3 cm to 4 cm when using the proposed method.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告ユビキタスコンピューティングシステム（UBI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2013-03-07","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"32","bibliographicVolumeNumber":"2013-UBI-37"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:40:21.432141+00:00","id":90967,"links":{}}