{"updated":"2025-01-19T17:26:13.887977+00:00","links":{},"created":"2025-01-19T01:13:34.393740+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00212637","sets":["6164:6165:7651:10646"]},"path":["10646"],"owner":"44499","recid":"212637","title":["リソグラフィホットスポット検出における特徴量評価用データセット生成手法の改良"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-08-25"},"_buckets":{"deposit":"482945a8-c202-4b8b-9af9-2510765aad04"},"_deposit":{"id":"212637","pid":{"type":"depid","value":"212637","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"リソグラフィホットスポット検出における特徴量評価用データセット生成手法の改良","author_link":["542851","542846","542848","542847","542849","542845","542844","542852","542853","542850"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"リソグラフィホットスポット検出における特徴量評価用データセット生成手法の改良"},{"subitem_title":"Improvement of Dataset Generation Method for Evaluating Features in Lithography Hotspot Detection","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"機械学習","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2021-08-25","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":"広島市立大学大学院情報科学研究科"},{"subitem_text_value":"広島市立大学大学院情報科学研究科"},{"subitem_text_value":"広島市立大学大学院情報科学研究科"},{"subitem_text_value":"広島市立大学大学院情報科学研究科"},{"subitem_text_value":"キオクシア株式会社"}]},"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/212637/files/IPSJ-DAS2021022.pdf","label":"IPSJ-DAS2021022.pdf"},"date":[{"dateType":"Available","dateValue":"2023-08-25"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DAS2021022.pdf","filesize":[{"value":"4.1 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":"10"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"268823f4-c2f5-4961-9a66-cfaf915dede8","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":"山本, 真大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"稲木, 雅人"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"永山, 忍"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"若林, 真一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"児玉, 親亮"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masahiro, Yamamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Masato, Inagi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shinobu, Nagayama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shin'ichi, Wakabayashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Chikaaki, Kodama","creatorNameLang":"en"}],"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":"リソグラフィプロセスにおいて，異常な短絡や開放を引き起こす確率の高い回路パターンであるホットスポットは，設計の段階で検出し除去することが望ましい．そこで近年，高速なホットスポット候補の検出手法として機械学習を用いた手法が複数提案されている．しかし，検出手法の高精度な比較評価ができる評価用データセットが，公開されたデータとして存在しない．そこで既存研究として，既存データセットに修正を加えて光学シミュレーションを適用することで訓練・テストデータの追加生成を行い，データセットを増強する手法が提案されている．本研究では，この光学シミュレーション後のラベル付け工程において，短絡や開放が生じているにもかかわらず非ホットスポットとラベル付けされる等の問題を発見し，このラベル付け工程を改良してデータセットの信頼性を向上させた．さらに，このデータセットを用い，検出手法の比較実験を行った．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In the lithography process, a hotspot refers to a circuit pattern that has a high probability of causing undesired open/short-circuits, which should be detected and removed at the design stage. In recent years, for fast hotspot detection, some machine learning-based methods have been proposed. However, there is no open benchmark dataset that can accurately evaluate and compare hotspot detection methods. Therefore, in a study, a method that enhances an existing open benchmark dataset was proposed. It modifies the dataset and applies optical simulation to generate additional training/test data. In this study, we found some problems in its simulation-based labeling process, such as labeling a pattern causing open/short-circuits as a non-hotspot. We improved the process and thus the reliability of the generated dataset. In addition, using the enhanced dataset, we conducted experiments to evaluate and compare some hotspot detection methods.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"126","bibliographic_titles":[{"bibliographic_title":"DAシンポジウム2021論文集"}],"bibliographicPageStart":"119","bibliographicIssueDates":{"bibliographicIssueDate":"2021-08-25","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2021"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":212637}