{"created":"2025-01-19T00:50:39.108458+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00183099","sets":["1164:8228:9066:9231"]},"path":["9231"],"owner":"11","recid":"183099","title":["Data Augmentationを用いた少数寝姿体圧データからの高精度姿勢識別DNN構築"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-08-17"},"_buckets":{"deposit":"8e2a5a88-d969-4295-be3c-8576a3f0f0bd"},"_deposit":{"id":"183099","pid":{"type":"depid","value":"183099","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Data Augmentationを用いた少数寝姿体圧データからの高精度姿勢識別DNN構築","author_link":["400713","400714","400712","400715"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Data Augmentationを用いた少数寝姿体圧データからの高精度姿勢識別DNN構築"},{"subitem_title":"A Study of Data Augmentation to Build High Performance DNN for In-bed Posture Classification","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"状況認識技術","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2017-08-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋大学情報学研究科"},{"subitem_text_value":"名古屋大学情報学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Nagoya University","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/183099/files/IPSJ-ASD17009011.pdf","label":"IPSJ-ASD17009011.pdf"},"date":[{"dateType":"Available","dateValue":"2019-08-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ASD17009011.pdf","filesize":[{"value":"2.7 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":"49"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"2cdf5b44-4e89-4bf3-b48d-fc207e4abcfc","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"榎堀, 優"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"間瀬, 健二"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yu, Enokibori","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kenji, Mase","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1271737X","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":"2188-8698","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"褥瘡予防などを筆頭に，就寝時の体圧データの応用が研究されており，その一つに寝姿勢の識別がある．就寝時の体圧データは，低解像度の画像と見なせるため，深層学習の一手法である CNN による識別が有効であると考えられるが，1 回の睡眠実験で得られる就寝姿勢数は，深層学習に用いるには少ない．我々の実験の実測値では，19 名の各 4 時間の睡眠で 224 姿勢であった．学習 ・ 検証 ・ テストに等分割するとすると，学習データ数は高々 72 点弱であり，SVM などを用いた既存手法以下の精度しか得られなかった．そこで本研究では Data Augumentation とそのパラメータ調整によって，少数データと深層学習による高精度寝姿識別機の作成を試みた．シアー変換，拡大縮小，回転，人体長軸方向移動，人体短軸方向移動についてパラメータを探索したところ，人体長軸 ・ 短軸方向に軸長の 40%，20% の移動による Data Augumentation によって仰臥位 ・ 左右腹臥位の 3 姿勢において 99.7% の識別精度を達成した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告高齢社会デザイン（ASD）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2017-08-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"11","bibliographicVolumeNumber":"2017-ASD-9"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":183099,"updated":"2025-01-20T03:48:43.137798+00:00","links":{}}