Performance Analysis of MixMatch-Based Semi-Supervised Learning for Defect Detection in Manufacturing Processes
* 본 문서는 배포용으로 복사 및 편집이 불가합니다.
서지정보
ㆍ발행기관 : 한국산업경영시스템학회
ㆍ수록지정보 : 산업경영시스템학회지 / 46권 / 4호
ㆍ저자명 : 김예준, 정예은, 김용수
ㆍ저자명 : 김예준, 정예은, 김용수
목차
1. 연구 목표 및 배경1.1 연구 배경 및 필요성
1.2 연구절차 및 구성
2. 관련 문헌 연구
3. 방법론
3.1 일관성 정규화(Consistency Regularization)
3.2 엔트로피 최소화(Entropy Minimization)
3.3 MixUp
3.4 MixMatch Algorithm [2]
4. 실험 및 결과
4.1 데이터 소개
4.2 실험 내용
4.3 평가 지표
4.4 실험 결과
5. 결론 및 추후연구
Acknowledgement
References
영어 초록
Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.참고 자료
없음"산업경영시스템학회지"의 다른 논문
An Analysis on the Effect of PBL(Performance Based Logi..8페이지
A Study on the Loss Cost of Delayed Weaponization of We..10페이지
A Study on the Organization and Procedures for Acquirin..8페이지
A War-time Engineering Equipment’s Assignment and Opera..10페이지
Optimal Hierarchical Design Methodology for AESA Radar ..13페이지
Net Assessment-Based Study to Determine the Optimal Siz..9페이지
Reallocation of Force in the Lanchester (3,3) Combat Mo..9페이지
Exploring trends in U.N. Peacekeeping Activities in Kor..17페이지
Location-Routing Problem for Reconnaissance Surveillanc..8페이지
Test and Evaluation Procedures of Defense AI System lin..9페이지