{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00240153","sets":["6164:6165:6640:11802"]},"path":["11802"],"owner":"44499","recid":"240153","title":["加速度及び生理センサデータセットからのLLMを用いた看護師ストレス推定の試み"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-19"},"_buckets":{"deposit":"444e1310-8383-4b6d-8d7b-40e016978460"},"_deposit":{"id":"240153","pid":{"type":"depid","value":"240153","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"加速度及び生理センサデータセットからのLLMを用いた看護師ストレス推定の試み","author_link":["658480","658479","658478","658477"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"加速度及び生理センサデータセットからのLLMを用いた看護師ストレス推定の試み"},{"subitem_title":"Toward Detecting Nurse Stress Using LLM from Accelerometer and Physiological Sensor Dataset","subitem_title_language":"en"}]},"item_type_id":"18","publish_date":"2024-06-19","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":"九州工業大学大学院生命体工学研究科"},{"subitem_text_value":"九州工業大学大学院生命体工学研究科"},{"subitem_text_value":"九州工業大学大学院生命体工学研究科"},{"subitem_text_value":"九州工業大学大学院生命体工学研究科"}]},"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/240153/files/IPSJ-DICOMO2024037.pdf","label":"IPSJ-DICOMO2024037.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2024037.pdf","filesize":[{"value":"991.6 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":"59d085ce-9ee8-4fe1-89d5-1c5159cdd82f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"三宅, 直哉"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"金子, 晴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Elsen, Ronando"}],"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":"本稿では，「ウェアラブルデバイスとLLM」を用いてストレス推定を行う．内容としては，ウェアラブルデバイスから取得した情報を基に看護師のストレス推定を行う．データセットから加速度及び皮膚電気活動（EDA)， 心拍数（HR）， および皮膚温度（TEMP)の生理センサデータセットを用いてストレス推定を行う．前処理にて，時間窓切り出し処理を行い，交差検証を用いて機械学習を行う．そして，RF，GB，kNNのみとそれらを基にLLMを用いて機械学習を行う．学習した結果を評価する．結果として，Random ForestとLarge Language Modelの組み合わせでは，予測正答率が82.53から82.57%に0.04%上昇したことが見られた．一方で，k-Nearest NeighborとLarge Language Modelの組み合わせにおいては予測正答率が80.38から80.25%に0.13%下降したことが見られた．特徴量重要度では，EDAが一般では重要視されており，LLMでも重要視されていることがわかった．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"263","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2024論文集"}],"bibliographicPageStart":"258","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-19","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":240153,"updated":"2025-01-19T08:03:58.201657+00:00","links":{},"created":"2025-01-19T01:44:10.896200+00:00"}