{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00215381","sets":["6504:10735:10810"]},"path":["10810"],"owner":"44499","recid":"215381","title":["脳波・心拍変動指標による感情推定の特徴量比較および機械学習による精度評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-04"},"_buckets":{"deposit":"72475c9c-5937-435c-936a-2f05e1f16eff"},"_deposit":{"id":"215381","pid":{"type":"depid","value":"215381","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"脳波・心拍変動指標による感情推定の特徴量比較および機械学習による精度評価","author_link":["554532","554531","554533","554534"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"脳波・心拍変動指標による感情推定の特徴量比較および機械学習による精度評価"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"インタフェース","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2021-03-04","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"芝浦工大"},{"subitem_text_value":"芝浦工大"},{"subitem_text_value":"芝浦工大"},{"subitem_text_value":"芝浦工大"}]},"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/215381/files/IPSJ-Z83-1ZA-01.pdf","label":"IPSJ-Z83-1ZA-01.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-29"}],"format":"application/pdf","filename":"IPSJ-Z83-1ZA-01.pdf","filesize":[{"value":"411.4 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"0cc8ae0a-44c0-447c-86fc-afeb3409d2e0","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"鈴木, 圭"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"松原, 良太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tipporn, Laohakangvalvit"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"菅谷, みどり"}],"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_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，人の感情推定技術の研究が数多くされており，感性評価やUX向上へと応用されている．浦部らは脳波指標と心拍変動指標を特徴量とし，感情の主観評価を正解ラベルとして機械学習をすることで，高い推定精度を得ることができることを示した．しかし，浦部らは，特徴量の抽出や選択が十分ではないため，さらなる精度向上の余地がある．そこで本研究では，移動平均の算出や周波数解析による特徴量抽出，分散分析やランダムフォレストの重要度による特徴量選択を行い，その結果を参考に機械学習モデルを構築した.その結果、層化5交差検証において，浦部らの手法では精度が61%であるのに対して，提案手法では100%となる結果を得た．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"104","bibliographic_titles":[{"bibliographic_title":"第83回全国大会講演論文集"}],"bibliographicPageStart":"103","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":215381,"updated":"2025-01-19T16:11:22.044699+00:00","links":{},"created":"2025-01-19T01:16:09.082252+00:00"}