{"id":200911,"updated":"2025-01-19T21:12:01.622001+00:00","links":{},"created":"2025-01-19T01:04:22.938174+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00200911","sets":["1164:3027:9664:9908"]},"path":["9908"],"owner":"44499","recid":"200911","title":["エッジセンサのための能動学習を用いた車両状態識別モデル更新手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-12-03"},"_buckets":{"deposit":"810a11fc-c7aa-46dc-affd-45dddfc491c9"},"_deposit":{"id":"200911","pid":{"type":"depid","value":"200911","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"エッジセンサのための能動学習を用いた車両状態識別モデル更新手法","author_link":["489555","489556","489559","489558","489557","489554"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"エッジセンサのための能動学習を用いた車両状態識別モデル更新手法"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"運転","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2019-12-03","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京電機大学"},{"subitem_text_value":"NTTコミュニケーション科学基礎研究所"},{"subitem_text_value":"NTTコミュニケーション科学基礎研究所"},{"subitem_text_value":"NTTコミュニケーション科学基礎研究所"},{"subitem_text_value":"東京電機大学"},{"subitem_text_value":"NTTコミュニケーション科学基礎研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Tokyo Denki Uniersity","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories","subitem_text_language":"en"},{"subitem_text_value":"Tokyo Denki Uniersity","subitem_text_language":"en"},{"subitem_text_value":"NTT Communication Science Laboratories","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/200911/files/IPSJ-HCI19185018.pdf","label":"IPSJ-HCI19185018.pdf"},"date":[{"dateType":"Available","dateValue":"2021-12-03"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-HCI19185018.pdf","filesize":[{"value":"862.9 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":"33"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"df15bd70-2317-48f4-a6a0-b5a60ab195ae","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"安齋, 凌介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"水谷, 伸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"白井, 良成"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大塚, 琢馬"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"岩井, 将行"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"岸野, 泰恵"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA1221543X","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":"2188-8760","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"機械学習によって状況を識別してその結果を送信するエッジセンサでは，環境の変化に応じて識別モデルを逐次的に更新する必要がある．しかし，ネットワーク帯域の制約や，ラベリングにかかるコストを考慮すると，すべてのデータをサーバに送信することは現実的ではない．また，すべてのデータを識別器の逐次的な更新に利用することも現実的ではない．そこで我々は，能動学習を利用し識別器の精度を向上させる可能性の高いデータのみを送信する手法を提案する．ここで精度向上の可能性が高いデータというのは，既存のモデルによる識別境界付近のデータのことである．さらに本研究では，ごみ収集車に搭載したエッジセンサのデータを用いた車両の状態推定の課題に対して検証を行い，提案手法とランダムにデータを選択する場合とを比較して，提案手法が効率よく識別器の精度を向上させられることを確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ヒューマンコンピュータインタラクション（HCI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-12-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"18","bibliographicVolumeNumber":"2019-HCI-185"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}