{"updated":"2025-01-20T03:39:56.536033+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00183420","sets":["1164:4619:9026:9245"]},"path":["9245"],"owner":"11","recid":"183420","title":["身体動作の個人差に対してロバストな特徴量空間評価関数の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-09-08"},"_buckets":{"deposit":"d67b4886-e82f-4468-bd09-9a97cd55348a"},"_deposit":{"id":"183420","pid":{"type":"depid","value":"183420","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"身体動作の個人差に対してロバストな特徴量空間評価関数の提案","author_link":["402450","402452","402457","402454","402455","402453","402456","402451"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"身体動作の個人差に対してロバストな特徴量空間評価関数の提案"},{"subitem_title":"On Evaluation Function for Feature Space Considered Robustness to Individual Difference of Human Activities","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2017-09-08","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工業高等専門学校電気工学科"},{"subitem_text_value":"豊橋技術科学大学"},{"subitem_text_value":"長岡技術科学大学大学院工学研究科情報・経営システム工学専攻"},{"subitem_text_value":"東京工業高等専門学校電気工学科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Electrical Engineering, National Institute of Technology, Tokyo College","subitem_text_language":"en"},{"subitem_text_value":"Toyohashi University of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Information and Management Systems Engineering, Nagaoka University of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Electrical Engineering, National Institute of Technology, Tokyo College","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/183420/files/IPSJ-CVIM17208001.pdf","label":"IPSJ-CVIM17208001.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM17208001.pdf","filesize":[{"value":"699.9 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"5c13db0a-e068-447f-bb2d-fc29bfa8c4af","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"森, 雅也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"秋月, 拓磨"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高橋, 弘毅"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大前, 佑斗"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masaya, Mori","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuma, Akiduki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hirotaka, Takahashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuto, Omae","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，慣性センサと機械学習を併用した身体動作の自動判定が盛んに行われている．一般に，身体動作には個人差があり，同じ動作でも被験者毎に得られるデータは異なる．以上より，精度の高い判定器を構築するためには，潜在的な判別誤差が生じにくく，個人差が空間上に表れにくい特徴量空間を選出するための指標が必要である．そのため本研究では，これらを重視する特徴量空間の評価関数を提案する．提案手法は，個別の被験者毎の身体動作に対して，それらの発生する確率を正規分布とカーネル分布から構成し，それらを活用して判別誤差の発生頻度を評価する．そして被験者全員の評価の平均と標準偏差を計算し，それらが最小と評価された特徴量空間を最適とみなす手法である．本研究は，身体動作判定を異常値検知問題へと帰着させた場合での適用を想定したものである．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Recently, various human activity recognitions by using inertial measurement units and machine learning are investigated. In general, even if the subjects carry out same activity, the data form sensors are different behavior by the individual difference. To develop a classifier model of the higher quality, the index for the feature space to suppress the classification error and individual difference is required. Therefore, we propose an evaluation function for the feature space considered the robustness to the individual difference of the human activities. In our method, we calculate the probability distributions (Gauss distribution and Kernel distribution) to occur the human activities for each subject. By using these probability distributions, we evaluate the possibility for the classification error. After that, the mean and standard deviation for the evaluation of all subjects are calculated, and we regard the evaluated minimum value as the optimal feature space. This proposed method supposes the application of the human activity recognition to anomaly detection problem.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2017-09-08","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2017-CVIM-208"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:50:56.699727+00:00","id":183420,"links":{}}