{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00213094","sets":["6164:6165:6640:10712"]},"path":["10712"],"owner":"44499","recid":"213094","title":["低粒度な分岐回路電力データを用いた家庭内行動認識手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-06-23"},"_buckets":{"deposit":"0bcd3f9a-f3c7-4ece-b49d-2bf2418862a1"},"_deposit":{"id":"213094","pid":{"type":"depid","value":"213094","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"低粒度な分岐回路電力データを用いた家庭内行動認識手法","author_link":["544641","544643","544644","544640","544642"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"低粒度な分岐回路電力データを用いた家庭内行動認識手法"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"行動認識","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2021-06-23","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":"大阪大学"},{"subitem_text_value":"大阪大学"},{"subitem_text_value":"大阪大学"},{"subitem_text_value":"大阪大学"},{"subitem_text_value":"京都橘大学"}]},"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/213094/files/IPSJ-DICOMO2021196.pdf","label":"IPSJ-DICOMO2021196.pdf"},"date":[{"dateType":"Available","dateValue":"2023-06-23"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2021196.pdf","filesize":[{"value":"1.3 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":"44"}],"accessrole":"open_date","version_id":"1eced56c-716e-440f-ac47-d2427302378d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"田中, 福治"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"石津, 紘太朗"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"水本, 旭洋"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山口, 弘純"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"東野, 輝夫"}],"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":"本研究では，HEMS 住宅分電盤から得られる分岐回路別の 30 分毎の累計消費電力情報のみから家庭内行動推定を行う手法を提案する．提案手法では，起床，就寝，調理，洗濯，皿洗い，入浴，洗面行動の 7 行動を推定対象とし，30 分毎にどの行動が行われていたかを推定する．これに対し，まず各行動に最も関係すると想定される分岐を特定するとともに，家電の電源の ON/OFF で明確に特定できる行動については当該分岐電力の利用の有無を用いて推定する．その他の行動に関しては，推定対象時間スロット前後の複数時間スロットに対し，当該分岐の電力量から抽出した特徴量を用い，ランダムフォレストにより各行動の有無を推定するモデルを構築する．また，転移学習により家庭間の差異に適応する方法もあわせて提案する．17 家庭の 1 年分の HEMS 計測データを連携企業の協力で入手し，うち夏および冬の 2 ヵ月間の計 16 万エントリ以上のデータに，複数人による行動ラベル付与を行ったデータを用いて学習および推定実験を実施した．その結果，起床は 63.4%，就寝は 54.2%，入浴は 81.6%，洗面は 86.5% のF値でそれぞれ認識できていることを確認した．また入浴の推定に関して 3 日以上の対象家庭のデータを用いて転移学習を行うことで精度が向上することを確認した．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1399","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2021論文集"}],"bibliographicPageStart":"1391","bibliographicIssueDates":{"bibliographicIssueDate":"2021-06-23","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":213094,"updated":"2025-01-19T17:16:43.454586+00:00","links":{},"created":"2025-01-19T01:14:00.463607+00:00"}