{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00074607","sets":["581:6276:6451"]},"path":["6451"],"owner":"11","recid":"74607","title":["加速度センサの定常性判定による動作認識手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-06-15"},"_buckets":{"deposit":"46290045-d4cd-4a2e-a763-005885e08f91"},"_deposit":{"id":"74607","pid":{"type":"depid","value":"74607","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"加速度センサの定常性判定による動作認識手法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"加速度センサの定常性判定による動作認識手法"},{"subitem_title":"A Motion Recognition Method by Constancy Decision","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般論文","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2011-06-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"日本学術振興会特別研究員PD／神戸大学大学院工学研究科"},{"subitem_text_value":"神戸大学大学院工学研究科／科学技術振興機構さきがけ"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Research Fellow of Japan Society for the Promotion of Science / Graduate School of Engineering, Kobe University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Kobe University / PRESTO, Japan Science and Technology Agency","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/74607/files/IPSJ-JNL5206003.pdf"},"date":[{"dateType":"Available","dateValue":"2013-06-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5206003.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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"8425a0da-f481-4a21-a137-94d909c069ba","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"村尾, 和哉"},{"creatorName":"寺田, 努"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuya, Murao","creatorNameLang":"en"},{"creatorName":"Tsutomu, Terada","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":"近年，計算機の小型化・軽量化によりコンピュータを装着するウェアラブルコンピューティングに注目が集まっている．特に行動認識の分野では，加速度センサを用いたシステムが数多く提案されてきた．従来の行動認識システムで認識可能なコンテキストはその波形の形状から「座る」などの姿勢，「歩く」などの運動，「円を描く」などのジェスチャの3種類に分類できる．姿勢と運動は一定時間継続される状態であり，特徴量を用いて認識される．一方，ジェスチャは1回きりの動作であり，波形自体を用いて認識される．このような認識手法の違いから運動中のジェスチャ認識は困難とされてきた．また，従来のジェスチャ認識はジェスチャの開始点を明示するためにいったん停止したりボタンを押したりする必要があった．そこで本論文では，加速度波形の定常性を判定し，ジェスチャの部分に対してのみジェスチャ認識を行うことで姿勢，運動，ジェスチャを認識するシステムを提案する．評価結果より，5種類の運動中に行った7種類のジェスチャ認識のRecallとPrecisionは従来手法では0.75および0.59であるのに対し，提案手法では0.93および0.92と改善した．提案システムを用いることで運動中でもジェスチャによる入力や機器の操作が可能になる．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The downsizing of computers has led to wearable computing that has attracted a great deal of attention.In the area of context awareness, many context-aware systems using accelerometers have been proposed. Contexts that have been recognized are categorized into postures (e.g., sitting), behaviors (e.g., walking), and gestures (e.g., draw a circle). Postures and behaviors are states lasting for a certain length of time, which are recognized with several feature values over a window. Gestures, however, are once-off actions. It has been a challenging task to find gestures on real environments where gestures are buried in other contexts. In this paper, we propose a method that classifies contexts into postures, behaviors, and gestures by using the autocorrelation of the acceleration values and recognizes contexts with an appropriate method. We evaluated the performance of recognition for seven kinds of gestures while five kinds of behaviors; The conventional method gave recall and precision of 0.75 and 0.59 whereas our method gave 0.93 and 0.92, respectively. Our system enables a user to input by gesturing even while he or she is performing a behavior.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1979","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"1968","bibliographicIssueDates":{"bibliographicIssueDate":"2011-06-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"52"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"updated":"2025-01-21T21:30:35.738576+00:00","created":"2025-01-18T23:32:04.549285+00:00","links":{},"id":74607}