{"id":218191,"links":{},"created":"2025-01-19T01:18:36.197348+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00218191","sets":["1164:4061:10837:10917"]},"path":["10917"],"owner":"44499","recid":"218191","title":["工場・物流センタにおける作業順序を考慮した少量学習データでの作業行動認識手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-05-30"},"_buckets":{"deposit":"174dfc6e-1ab9-4e42-ac93-dcc861afe046"},"_deposit":{"id":"218191","pid":{"type":"depid","value":"218191","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"工場・物流センタにおける作業順序を考慮した少量学習データでの作業行動認識手法の検討","author_link":["566834","566831","566833","566835","566832"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"工場・物流センタにおける作業順序を考慮した少量学習データでの作業行動認識手法の検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"行動・動作認識","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-05-30","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"株式会社東芝生産技術センター"},{"subitem_text_value":"株式会社東芝生産技術センター"}]},"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/218191/files/IPSJ-UBI22074012.pdf","label":"IPSJ-UBI22074012.pdf"},"date":[{"dateType":"Available","dateValue":"2024-05-30"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-UBI22074012.pdf","filesize":[{"value":"1.6 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"36"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"d0e0a51c-bae4-412f-9a68-e29f9f778195","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"吉村, 直也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"前川, 卓也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"原, 隆浩"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"和田, 篤"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"浪岡, 保男"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11838947","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":"2188-8698","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"工場や物流センタではネジ締め作業や検品作業・梱包作業など，複雑で変則的な作業を人間の作業者が担っており，この作業者の作業状況を把握するために行動認識技術の適用が検討されている．しかし，作業員ごとに担当の作業が異なるため，ある作業員から取得した学習データを他の作業員に転用できないなど，学習データの収集コストに大きな課題がある．そこで本研究では，限られたラベル付きデータで作業行動を認識するためのニューラルネットワーク Lightweight Ordered-work Segmentation Network (LOS-Net) を提案する．既存のニューラルネットワークを用いた行動認識モデルは，高い認識性能を達成するためには大量のラベル付きデータを必要とする．しかし，作業工程には行動の順序が事前に決められているなどの特徴がある．LOS-Net では作業順序のような事前知識に着目し，(1) 効率的に長期的なコンテキストを抽出するためのモジュール，(2) 連続する行動ラベルの境界を正確に推定するためのモジュール，(3) 作業順序を用いて推定結果を修正するモジュールを導入し，限られた学習データでも高い精度で作業工程を認識できる．提案手法を実際の工場や物流センタで収集した 11 人分のデータを用いて評価し，提案手法の有効性を確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ユビキタスコンピューティングシステム（UBI）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-05-30","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"12","bibliographicVolumeNumber":"2022-UBI-74"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T15:14:14.627863+00:00"}