{"created":"2025-01-19T00:58:15.921738+00:00","updated":"2025-01-20T00:05:50.957946+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00192562","sets":["1164:4061:9376:9607"]},"path":["9607"],"owner":"44499","recid":"192562","title":["携帯端末位置履歴を用いた階層ディリクレ混合回帰モデルに基づく活動人口予測"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-11-27"},"_buckets":{"deposit":"1108abb6-98bd-4568-bbcf-1196aefb7bf6"},"_deposit":{"id":"192562","pid":{"type":"depid","value":"192562","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"携帯端末位置履歴を用いた階層ディリクレ混合回帰モデルに基づく活動人口予測","author_link":["449598","449596","449595","449600","449597","449599"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"携帯端末位置履歴を用いた階層ディリクレ混合回帰モデルに基づく活動人口予測"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"認識と予測","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2018-11-27","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工業大学情報理工学院情報工学系"},{"subitem_text_value":"東京工業大学情報理工学院情報工学系"},{"subitem_text_value":"ヤフー株式会社Yahoo! JAPAN研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, School of Engineering, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, School of Engineering, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Yahoo Japan Corporation, Yahoo! JAPAN Research","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/192562/files/IPSJ-UBI18060015.pdf","label":"IPSJ-UBI18060015.pdf"},"date":[{"dateType":"Available","dateValue":"2020-11-27"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-UBI18060015.pdf","filesize":[{"value":"2.2 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":"36"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"9bb64994-379e-4fb1-a01c-2aa76bda23fe","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"下坂, 正倫"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"早川, 裕太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"坪内, 孝太"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masamichi, Shimosaka","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuta, Hayakawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kota, Tsubouchi","creatorNameLang":"en"}],"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":"近年の携帯端末の普及により，端末の位置履歴情報を用いた都市における人々の活動を解析することが盛んである．特に都市の活動人口を予測することは，都市計画や人員配置の観点から重要となる．この問題に対して，曜日や天気といった要因を説明変数とした回帰手法が近年盛んに研究されている．これまで提案された双線形回帰に基づく手法は複数の特徴の組み合わせを考慮した予測が可能である．一方で解析対象となる地域に対して独立に予測を行っており，例えば地域間の関係性に着目した分析を具現化しようとすると，地域毎に独立したモデル化は安定しないことが知られている．そこで，本研究ではこの問題を解決するため，予測モデルの事前分布に階層ディリクレ過程 (HDP) を適用した，HDP 混合回帰モデルを提案する．HDP は複数分布に共通するパラメータを生成が可能な性質を持つため，パラメータとデータをそれぞれ共有し安定性を高めつつ，解析対象の地域ごとに特化した予測モデルの構築が可能となる．携帯電話により取得された 3200 万件を超える位置履歴データを用いて，大規模かつ高精細なメッシュ上での活動人口予測の比較実験を行い，提案手法が既存手法と比較し安定した学習が可能であり，特にデータの少ない地域に対しても高精度なモデリングを可能にすることを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","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":"2018-11-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"15","bibliographicVolumeNumber":"2018-UBI-60"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":192562,"links":{}}