{"created":"2025-01-19T01:17:47.710250+00:00","updated":"2025-01-19T15:33:02.201383+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217295","sets":["1164:1384:10896:10897"]},"path":["10897"],"owner":"44499","recid":"217295","title":["複数の学習済みモデルを用いた業務ソフトウェアのバグ予測精度の比較"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-04"},"_buckets":{"deposit":"7cdf791f-d72c-478f-9b7c-eb547de964e0"},"_deposit":{"id":"217295","pid":{"type":"depid","value":"217295","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"複数の学習済みモデルを用いた業務ソフトウェアのバグ予測精度の比較","author_link":["562784","562782","562783","562781"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"複数の学習済みモデルを用いた業務ソフトウェアのバグ予測精度の比較"},{"subitem_title":"Comparison of bug prediction accuracy of business software using multiple trained models","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ソフトウェア工学における機械学習の利用(ML4SE)","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-04","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"茨城大学大学院"},{"subitem_text_value":"茨城大学大学院"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Ibaraki University Graduate School","subitem_text_language":"en"},{"subitem_text_value":"Ibaraki University Graduate School","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/217295/files/IPSJ-SE22210009.pdf","label":"IPSJ-SE22210009.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-04"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SE22210009.pdf","filesize":[{"value":"560.5 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"12"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"1f260fa9-acd9-46e4-91fa-b6b25a3a6d35","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"内藤, 大貴"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"上田, 賀一"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroki, Naitoh","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshikazu, Ueda","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112981","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":"2188-8825","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"バグ予測の精度向上はテストの効率化にとって重要であり，バグ予測の研究は盛んに行われる．多くの研究の対象はデータ収集しやすいオープンソースソフトウェア（OSS）を対象にしたものである．本研究は，VB.NET で開発された業務ソフトウェアに対し，実用的な学習モデルの構築を行いデバッグ作業の効率化を目的とする．本研究では，バグ予測の学習モデルに畳み込みニューラルネットワークを用い，メインシステムと複数のサブシステムから構成される医療業務用システムを対象とする．各システムのバグデータ数は少ないため，各システムで浅い学習を行った学習済みモデルを用意し，多数決を採ることで，過学習を抑え，精度の高い分類を行うことが可能か検討した．別々のシステムのデータを一括にまとめて学習を行った場合の精度と比較した．単体のシステムで突出して上手く学習できたモデルが無い場合は，多数決を採る方法が高精度であることが捉えられた．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Improving the accuracy of bug prediction is important for improving the efficiency of testing, and research on bug prediction is actively conducted. Most of the researches target open source software (OSS), which is easy to collect data. The purpose of this study is to construct a practical learning model for business software developed in VB.NET to improve the efficiency of debugging. In this study, we use convolutional neural networks as the learning model for bug prediction, and target a medical business system consisting of a main system and several subsystems. Since the number of bug data in each system is small, we prepared a trained model with shallow training in each system, and examined whether it is possible to suppress overtraining and classify with high accuracy by adopting majority voting. We compared the accuracy with that obtained by combining the data of different systems into a single training model. The results showed that the majority voting method was more accurate when there was no model that could be trained outstandingly well in a single system.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告ソフトウェア工学（SE）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"2022-SE-210"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217295,"links":{}}