{"created":"2025-01-19T00:46:55.812853+00:00","updated":"2025-01-20T05:30:37.598225+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00177367","sets":["6164:6165:6640:9062"]},"path":["9062"],"owner":"11","recid":"177367","title":["個人差のない特徴量を用いた水分摂取量推定手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-07-06"},"_buckets":{"deposit":"479caef7-7b5f-4d8d-8a24-0ece8214d001"},"_deposit":{"id":"177367","pid":{"type":"depid","value":"177367","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"個人差のない特徴量を用いた水分摂取量推定手法の検討","author_link":["376191","376190","376189"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"個人差のない特徴量を用いた水分摂取量推定手法の検討"}]},"item_type_id":"18","publish_date":"2016-07-06","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":"静岡大学大学院総合科学技術研究科"},{"subitem_text_value":"静岡大学学術院情報学領域"},{"subitem_text_value":"静岡大学学術院情報学領域／JSTさきがけ"}]},"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/177367/files/IPSJ-DICOMO2016264.pdf","label":"IPSJ-DICOMO2016264.pdf"},"date":[{"dateType":"Available","dateValue":"2016-07-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2016264.pdf","filesize":[{"value":"1.9 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"be01dee7-32e6-466c-ac86-5a9cda20082c","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山田, 侑太朗"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"西村, 雅史"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"峰野, 博史"}],"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":"超高齢社会を迎えた日本では，介護負担の増大が課題であり，介護負担を軽減するために高齢者の健康管理の自動記録に関するサービスやシステムの提案が行われてきた．しかし，高齢者の健康管理に必要な項目の一つである水分摂取量については現在自動化が行われておらず，介護者の負担となっていた．筆者らは，嚥下音を計測し，水分摂取量を推定する手法の研究を進めてきたが，一日分の合計水分摂取量推定では，被験者毎の推定誤差が大きく，不特定の被験者に対する水分摂取量推定に適した共通的な特徴量を抽出しきれていない課題があった．本研究では，個人差の課題について行動分類で用いた判別器を HMM (Hidden Markov Model) に変更し嚥下行動の抽出精度を向上させるだけでなく，LLD (Low Level Descriptor) 特徴量セットに含まれる特徴量の中でも，音の大きさや波形に比べ個人差が少なく嚥下量に相関性の高いと考えられる MFCC (Mel-Frequency Cepstrum Coefficients) や継続時間に着目して水分摂取量推定の高精度化を図る．実験では従来手法と比べ，提案手法で各被験者で 1 日分の目安から 500ml の誤差にまで下げることができ，MFCC や継続時間は，音の大きさに比べ共通かつ適切な特徴量であったと確認できた．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1820","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2016論文集"}],"bibliographicPageStart":"1814","bibliographicIssueDates":{"bibliographicIssueDate":"2016-07-06","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2016"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":177367,"links":{}}