{"created":"2025-01-19T01:12:51.487617+00:00","updated":"2025-01-19T17:42:21.551987+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00211719","sets":["1164:5352:10544:10612"]},"path":["10612"],"owner":"44499","recid":"211719","title":["機械学習を用いたfNIRSの解析手法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-06-21"},"_buckets":{"deposit":"02a98496-546a-48e6-867d-71212f8e0622"},"_deposit":{"id":"211719","pid":{"type":"depid","value":"211719","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"機械学習を用いたfNIRSの解析手法の提案","author_link":["538358","538354","538353","538356","538355","538357"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"機械学習を用いたfNIRSの解析手法の提案"},{"subitem_title":"Proposal of an Analysis Method for fNIRS Using Machine Learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ニューロコンピューティング","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-06-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"早稲田大学大学院人間科学研究科"},{"subitem_text_value":"早稲田大学大学院人間科学研究科"},{"subitem_text_value":"早稲田大学大学院人間科学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Reiji Ohkuma","subitem_text_language":"en"},{"subitem_text_value":"Yuto Kurihara","subitem_text_language":"en"},{"subitem_text_value":"Reiko Osu","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/211719/files/IPSJ-BIO21066016.pdf","label":"IPSJ-BIO21066016.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-BIO21066016.pdf","filesize":[{"value":"2.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"41"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"506561b3-cb20-4c29-a2ee-479e5dd681ab","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 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":"大隈, 玲志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"栗原, 勇人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大須, 理英子"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Reiji, Ohkuma","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuto, Kurihara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Reiko, Osu","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12055912","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":"2188-8590","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"fNIRS (機能的近赤外分光法) は，脳機能イメージング技術としては比較的新しく，研究数が他の脳機能イメージングより少ないため，解析手法が確立していない．従来の fNIRS の解析手法では，前処理の段階でパラメータ数が多く，解析結果がパラメータに依存してしまう問題がある．そこで我々は，機械学習の分類問題とその特徴量の重要度をもとに，パラメータ数が少ない fNIRS による脳の賦活部位を特定する新たな解析手法を提案した．本研究では，機械学習の分類器としてランダムフォレストを使用した．提案手法を用いて計算課題を解く脳活動を解析したところ，従来の解析方法による結果と近しい結果が得ることができた．よって，機械学習の特徴量重要度による解析は有用であると考えられる．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Conventional analysis methods for fNIRS require a large number of parameters in preprocessing, and the analysis results depend on the parameters. We proposed a new analysis method for identifying activated brain regions using fNIRS with a small number of parameters, based on the classification by machine learning and the importance of the features. In this study, we used Random Forest as a machine learning classifier. When we analyzed the brain activity of solving a computational task using the proposed method, the results were similar to those obtained by the conventional analysis method. Although there are some issues to be solved, we believe that the analysis by features importance of machine learning is useful.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告バイオ情報学（BIO）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-06-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"16","bibliographicVolumeNumber":"2021-BIO-66"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":211719,"links":{}}