{"updated":"2025-01-20T03:23:19.939439+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00184180","sets":["1164:3865:9090:9259"]},"path":["9259"],"owner":"11","recid":"184180","title":["センサーネットワークにおける分散型深層学習の設計と実装"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-11-08"},"_buckets":{"deposit":"2cfe1ad6-974f-45fa-9692-4d8dbb5f8176"},"_deposit":{"id":"184180","pid":{"type":"depid","value":"184180","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"センサーネットワークにおける分散型深層学習の設計と実装","author_link":["406481","406480","406479","406478","406482"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"センサーネットワークにおける分散型深層学習の設計と実装"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"MBLセッション1","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2017-11-08","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":"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"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","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/184180/files/IPSJ-MBL17085025.pdf","label":"IPSJ-MBL17085025.pdf"},"date":[{"dateType":"Available","dateValue":"2019-11-08"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MBL17085025.pdf","filesize":[{"value":"6.2 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":"35"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"60c2a467-e490-4fc5-9015-e7a7c39ca826","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"福島, 悠太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"三浦, 太樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"濱谷, 尚志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山口, 弘純"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"東野, 輝夫"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11851388","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":"2188-8817","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"無線センサーネットワークにおいて，センサーに付随するマイコンの高機能化 ・ 省電力化が進めば，従来クラウドで行っていた学習や異常検出，判定などのタスク処理をセンサーネットワークにオフローディングし，データ発生場所に近い場所でそれらを効率よく行える自律的な知能センサーネットワークが実現できる．本研究では CNN を対象に，ローカルな無線センサーネットワーク内で分散実行する新しいアーキテクチャを提案し，そのための分散実行プロトコルならびにアルゴリズムを提案する．提案手法はメッシュ型の無線センサーネットワークが面的かつ定期的に取得するデータを対象とし，センサーノードに深層学習におけるユニットの役割を割り当てる．提案手法の有効性を評価するため，1,400 m² 超の実ラウンジスペースの 50 地点の温度データを用いて，通常の CNN による学習と提案手法による分散学習におけるデータ通信量と学習精度の比較を行った．その結果，十分妥当な通信量のもとで，通常の CNN と遜色ない学習精度を達成できることがわかった．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告モバイルコンピューティングとパーベイシブシステム（MBL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2017-11-08","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"25","bibliographicVolumeNumber":"2017-MBL-85"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:51:38.641961+00:00","id":184180,"links":{}}