{"created":"2025-01-19T01:04:49.297304+00:00","updated":"2025-01-19T20:58:44.436224+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00201562","sets":["1164:1165:9888:10036"]},"path":["10036"],"owner":"44499","recid":"201562","title":["Quasi-Recurrent Neural Networks を用いた複合時系列データ予測"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-12-16"},"_buckets":{"deposit":"75f03570-bb21-41b6-88ab-37f465334788"},"_deposit":{"id":"201562","pid":{"type":"depid","value":"201562","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Quasi-Recurrent Neural Networks を用いた複合時系列データ予測","author_link":["493466","493463","493467","493465","493462","493464"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Quasi-Recurrent Neural Networks を用いた複合時系列データ予測"}]},"item_type_id":"4","publish_date":"2019-12-16","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"静岡県立大学経営情報イノベーション研究科"},{"subitem_text_value":"静岡県立大学経営情報イノベーション研究科"},{"subitem_text_value":"静岡県立大学経営情報イノベーション研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Management and Information of Innovation, University of Shizuoka","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Management and Information of Innovation, University of Shizuoka","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Management and Information of Innovation, University of Shizuoka","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/201562/files/IPSJ-DBS19170017.pdf","label":"IPSJ-DBS19170017.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS19170017.pdf","filesize":[{"value":"935.8 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"35379425-bb2f-4de6-b394-12f97be151c6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"坂崎, 雄一朗"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"安達, 凛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"六井, 淳"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuichiro, Sakazaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Rin, Adati","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jun, Roku","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112482","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":"2188-871X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，様々な分野で時系列データ予想を行う研究が報告されている．時系列データ予測において従来の Recurrent Neural Network よりも Convolutional Neural Network の方が高い適性があるとの報告がなされている．加えて,単一系列よりも複数系列での予測の方が精度が向上するとの報告もある．この様な知見から，本研究では複数時系列データの入力を重回帰分析により統合し，CNN を時系列データ予測向けに拡張した Quasi-Recurrent Neural Network を用いて予測対象の時系列予測を行うモデルを提案する．また，実験では時系列データの長さやネットワークのパラメータを変化させる実験を行い，予測精度の変化を検証した．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We proposed a model that integrates several types of data by multiple regression analysis and performs future prediction of target using Quasi- Recurrent Neural Network, which is one of nonlinear models. In addition,\nwe experiment to change the length of the time series data and the parameters of the nonlinear model. And the change of prediction accuracy is verified from the result.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム（DBS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-12-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"17","bibliographicVolumeNumber":"2019-DBS-170"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":201562,"links":{}}