Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김병훈 | - |
dc.date.accessioned | 2023-12-22T01:38:29Z | - |
dc.date.available | 2023-12-22T01:38:29Z | - |
dc.date.issued | 2023-08 | - |
dc.identifier.citation | 대한산업공학회지, v. 49, NO. 4, Page. 330.0-343.0 | - |
dc.identifier.issn | 1225-0988;2234-6457 | - |
dc.identifier.uri | https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11496977 | en_US |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/187796 | - |
dc.description.abstract | This study proposes a wafer defect pattern clustering model that can recognize defect patterns without the class label of the defect patterns. In the first step, noise defects are removed from each wafer bin map (WBM) image using the Depth-First Search (DFS) algorithm to clarify the defect pattern. Next, the defect patterns are clustered using the Dirichlet process, and the clustering results are adjusted by tuning the extracted features based on self-supervised learning. By employing a weighted cross-entropy loss that considers the cluster size, the model becomes robust to the imbalance of cluster sizes during the fine-tuning process. The proposed method can facilitate the identification and resolution of the causes of defects that occur during semiconductor processing. | - |
dc.description.sponsorship | 이 논문은 2023년도 산업통상자원부 및 한국산업기술진흥원의 재원으로 한국전자기술연구원의 지원을받아 수행된 인력양성사업임(P0008691). 이 논문은 2022년도 한국데이터마이닝학회 SAS 논문 경진대회에서 장려상을 수상한 논문을 확장하여 작성한 논문임. 이 논문은 한국연구재단의 연구비 지원을 받아 수행됨(No. NRF-2019R1F1A1042307). | - |
dc.language | ko | - |
dc.publisher | 대한산업공학회 | - |
dc.subject | Defect pattern clustering | - |
dc.subject | Self-supervised learning | - |
dc.subject | Semiconductor processing | - |
dc.subject | Wafer bin map | - |
dc.title | 패턴 불균형에 강건한 자가 지도학습을 활용한 웨이퍼 불량 패턴 클러스터링 방법 제안 | - |
dc.title.alternative | New Wafer Defect Pattern Clustering Method using a Self Supervised Learning Robust to Pattern Imbalance | - |
dc.type | Article | - |
dc.relation.no | 4 | - |
dc.relation.volume | 49 | - |
dc.identifier.doi | 10.7232/JKIIE.2023.49.4.330 | - |
dc.relation.page | 330.0-343.0 | - |
dc.relation.journal | 대한산업공학회지 | - |
dc.contributor.googleauthor | 최이수 | - |
dc.contributor.googleauthor | 윤주호 | - |
dc.contributor.googleauthor | 김병훈 | - |
dc.sector.campus | E | - |
dc.sector.daehak | 공학대학 | - |
dc.sector.department | 산업경영공학과 | - |
dc.identifier.pid | byungkim | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.