{"created":"2025-01-19T01:28:21.464893+00:00","updated":"2025-01-19T11:35:39.136312+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229230","sets":["1164:4619:11188:11420"]},"path":["11420"],"owner":"44499","recid":"229230","title":["組合せ最適化問題の画像表現による解法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-09"},"_buckets":{"deposit":"ebb37504-29f6-459f-be62-27fe08333dbd"},"_deposit":{"id":"229230","pid":{"type":"depid","value":"229230","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"組合せ最適化問題の画像表現による解法","author_link":["616058","616059","616057","616056"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"組合せ最適化問題の画像表現による解法"}]},"item_type_id":"4","publish_date":"2023-11-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州大学工学部電気情報工学科"},{"subitem_text_value":"九州大学大学院システム情報科学府"},{"subitem_text_value":"九州大学大学院システム情報科学府"},{"subitem_text_value":"九州大学大学院システム情報科学府"}]},"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/229230/files/IPSJ-CVIM23235010.pdf","label":"IPSJ-CVIM23235010.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM23235010.pdf","filesize":[{"value":"2.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"63b4cdc7-a409-4618-aed5-5e022fca9671","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 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":"石山, 遼"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"白川, 嵩大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"内田, 誠一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"松尾, 信之介"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"組合せ最適化問題とは定められた制約下で評価値が最良となる組合せ方法を選択する問題である．本稿ではその一例として，グラフ理論における組合せ最適化問題である巡回セールスマン問題を取り上げる．これは，複数の都市をそれぞれ１回通過する最短閉路を求める問題である．換言すれば，全都市を頂点とする完全グラフのうち，最短閉路に対応する部分グラフを求める問題となる．本研究では，この完全グラフに対応する距離行列から，部分グラフを表現する隣接行列への変換を，一種の画像変換問題として捉え，それを機械学習の枠組みで実現する．すなわち，要素が 2 次元的に配列される行列を，その要素の値を画素値とする画像と見なす．この発想に基づき，巡回セールスマン問題のようなグラフ最適化問題を画像変換問題として扱うこととする．グラフベースのニューラルネットワーク(GNN) との比較実験を行い，画像解析による有効性を実証した．さらに，画像に対して特有の前所理を組込むことにより，精度が向上することを確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2023-CVIM-235"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229230,"links":{}}