{"created":"2025-01-19T01:13:51.566736+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00212937","sets":["6164:6165:6640:10712"]},"path":["10712"],"owner":"44499","recid":"212937","title":["学習時付加情報を用いたセンサ行動認識の精度改善"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-06-23"},"_buckets":{"deposit":"6483e60f-c8a8-4d4b-92c8-5ac577c017d6"},"_deposit":{"id":"212937","pid":{"type":"depid","value":"212937","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"学習時付加情報を用いたセンサ行動認識の精度改善","author_link":["544015","544013","544014"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"学習時付加情報を用いたセンサ行動認識の精度改善"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ユビキタスコンピューティングシステム","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2021-06-23","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":"九州工業大学"},{"subitem_text_value":"九州工業大学"},{"subitem_text_value":"九州工業大学"}]},"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/212937/files/IPSJ-DICOMO2021039.pdf","label":"IPSJ-DICOMO2021039.pdf"},"date":[{"dateType":"Available","dateValue":"2023-06-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2021039.pdf","filesize":[{"value":"1.1 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":"44"}],"accessrole":"open_date","version_id":"dede0886-721a-4aaa-8a24-7f59606966f7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"安達, 康平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Paula, Lago"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"井上, 創造"}],"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":"センサ行動認識は，「歩いている」「走っている」などのシンプルな行動は高い認識精度で認識できる一方で，看護行動などの複雑な行動は認識が難しい．解決手段として，複数のセンサを用いることが挙 げられるが，実生活においては非現実的である．近年，学習フェーズのみ追加情報を用いて学習ができる， LUPI (Learning using Privileged Information) という手法が提案されており，本研究ではセンサ行動認識に LUPI を用いる．具体的には，学習時に複数のセンサで学習して，テスト時は 1 つのセンサを利用する．検証には，公開されている 4 つのデータセットを用いた．結果として被験者ごとのランダム交差検証において最大で 35% 従来手法よりも改善した．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"292","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2021論文集"}],"bibliographicPageStart":"284","bibliographicIssueDates":{"bibliographicIssueDate":"2021-06-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":212937,"updated":"2025-01-19T17:19:37.392026+00:00","links":{}}