{"created":"2025-01-19T01:29:50.042096+00:00","updated":"2025-01-19T11:14:34.721899+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00230212","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"230212","title":["適応的遷移確率モデルを導入した隠れマルコフモデルに基づくリカレント確率ニューラルネット"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"56b505d7-5a3c-4d48-b90f-cd91673fd885"},"_deposit":{"id":"230212","pid":{"type":"depid","value":"230212","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"適応的遷移確率モデルを導入した隠れマルコフモデルに基づくリカレント確率ニューラルネット","author_link":["619379","619378","619377"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"適応的遷移確率モデルを導入した隠れマルコフモデルに基づくリカレント確率ニューラルネット"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2023-02-16","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":"横浜国大"},{"subitem_text_value":"神奈川県立産業技術総合研究所"},{"subitem_text_value":"横浜国大"}]},"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/230212/files/IPSJ-Z85-6W-04.pdf","label":"IPSJ-Z85-6W-04.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-6W-04.pdf","filesize":[{"value":"550.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"682bd388-c602-4829-af77-2d6d8451bef8","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"嘉山, 敢太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"迎田, 隆幸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"島, 圭介"}],"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":"生体信号に対するパターン識別ではデータの時間変化を考慮した学習によって識別精度向上が期待でき，リカレントニューラルネットや隠れマルコフモデルなど様々な手法が提案されてきた．一方，膨大な学習データが必要であることや統計的制約によりパラメータ推定が困難になるなどの課題が存在する．本研究では，状態遷移確率が適応的に変化する新たな隠れマルコフモデルを提案し，それを内包するリカレント確率ニューラルネットを構築した．提案法は長・短期記憶を可能にするユニットを有し，長期的な時間変化を考慮しつつ，少量の学習データから高精度な識別を可能とする．実験ではベンチマークデータの分類を行い，提案法の有効性を示した．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"854","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"853","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":230212,"links":{}}