{"created":"2025-01-19T01:04:53.515467+00:00","updated":"2025-01-19T20:56:19.528476+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00202320","sets":["6164:6165:6640:10055"]},"path":["10055"],"owner":"44499","recid":"202320","title":["行動認識における表現学習モデルと個人依存に関する考察"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-06-26"},"_buckets":{"deposit":"b2142109-2c33-4a91-8f29-fd632da6bfcf"},"_deposit":{"id":"202320","pid":{"type":"depid","value":"202320","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"行動認識における表現学習モデルと個人依存に関する考察","author_link":["496342","496343"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"行動認識における表現学習モデルと個人依存に関する考察"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"行動認識","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2019-06-26","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"福井大学大学院工学研究科"},{"subitem_text_value":"石川工業高等専門学校電子情報工学科"}]},"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/202320/files/IPSJ-DICOMO2019048.pdf","label":"IPSJ-DICOMO2019048.pdf"},"date":[{"dateType":"Available","dateValue":"2021-06-26"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2019048.pdf","filesize":[{"value":"836.0 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"624420f3-96b1-4173-9db5-536224b5870a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"長谷川, 達人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"越野, 亮"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"センシングによる行動認識研究が広く行われているが，個人依存性が問題になることがある．センサデータを用いた行動認識について幅広くサーベイした結果，CNN（Convolutional Neural Network）を用いた表現学習モデルによる行動認識について十分な検討がなされていなかった．そこで本研究では，画像認識分野で研究が進んでいるCNNモデルをベースに，行動認識における表現学習モデルの有効性の検証実験を行った．行動認識のベンチマークデータセットに対して，HC（Hand-crafted）特徴量を用いたDNN，シンプルなCNNモデル，AlexNet，FCN，VGG，ResNet，SENet等10種類のモデルに対して，訓練データの多様性を変化させて6種類，ランダム性を考慮して10セットで，計600回深層学習モデルを訓練し推定精度検証を行った．その結果，訓練データに被験者を多く確保できる場合には，SE-VGGが最も高い精度を達成することを明らかにした．更に，訓練データを十分に確保できない場合にはHC特徴量が有効に働くことや，HC特徴量は個人依存の影響を比較的強く受けることも明らかにした．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"338","bibliographic_titles":[{"bibliographic_title":"マルチメディア,分散協調とモバイルシンポジウム2019論文集"}],"bibliographicPageStart":"328","bibliographicIssueDates":{"bibliographicIssueDate":"2019-06-26","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2019"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":202320,"links":{}}