A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection

This paper develops a hybrid approach integrating an adaptive artificial neural network (ANN) and a fuzzy logic system for tackling class-imbalance problems. In particular, a supervised learning ANN based on Adaptive Resonance Theory (ART) is combined with a Tagaki�Sugeno�Kang-based fuzzy infere...

Full description

Main Authors: Tan, S.C., Wang, S., Watada, J.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.21815 /
Published: Elsevier Inc. 2018
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032186655&doi=10.1016%2fj.ins.2017.10.040&partnerID=40&md5=fefe70c2341a3f89d2d12059cf151c29
http://eprints.utp.edu.my/21815/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.21815
recordtype eprints
spelling utp-eprints.218152019-02-20T01:53:24Z A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection Tan, S.C. Wang, S. Watada, J. This paper develops a hybrid approach integrating an adaptive artificial neural network (ANN) and a fuzzy logic system for tackling class-imbalance problems. In particular, a supervised learning ANN based on Adaptive Resonance Theory (ART) is combined with a Tagaki�Sugeno�Kang-based fuzzy inference mechanism to learn and detect defects of a real large highly imbalanced dataset collected from a semiconductor company. A benchmark study is also conducted to compare the classification performance of the proposed method with other published methods in the literature. The real dataset collected from the semiconductor company intrinsically demonstrates class overlap and data shift in a highly imbalanced data environment. The generalization ability of the proposed method in detecting semiconductor defects is evaluated and compared with other existing methods, and the results are analyzed using statistical methods. The outcomes from the empirical studies positively indicate high potentials of the proposed approach in classifying the highly imbalanced dataset posing overlap class and data shift. © 2017 Elsevier Inc. 2018 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032186655&doi=10.1016%2fj.ins.2017.10.040&partnerID=40&md5=fefe70c2341a3f89d2d12059cf151c29 Tan, S.C. and Wang, S. and Watada, J. (2018) A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection. Information Sciences, 427 . pp. 1-17. http://eprints.utp.edu.my/21815/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description This paper develops a hybrid approach integrating an adaptive artificial neural network (ANN) and a fuzzy logic system for tackling class-imbalance problems. In particular, a supervised learning ANN based on Adaptive Resonance Theory (ART) is combined with a Tagaki�Sugeno�Kang-based fuzzy inference mechanism to learn and detect defects of a real large highly imbalanced dataset collected from a semiconductor company. A benchmark study is also conducted to compare the classification performance of the proposed method with other published methods in the literature. The real dataset collected from the semiconductor company intrinsically demonstrates class overlap and data shift in a highly imbalanced data environment. The generalization ability of the proposed method in detecting semiconductor defects is evaluated and compared with other existing methods, and the results are analyzed using statistical methods. The outcomes from the empirical studies positively indicate high potentials of the proposed approach in classifying the highly imbalanced dataset posing overlap class and data shift. © 2017
format Article
author Tan, S.C.
Wang, S.
Watada, J.
spellingShingle Tan, S.C.
Wang, S.
Watada, J.
A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
author_sort Tan, S.C.
title A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
title_short A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
title_full A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
title_fullStr A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
title_full_unstemmed A self-adaptive class-imbalance TSK neural network with applications to semiconductor defects detection
title_sort self-adaptive class-imbalance tsk neural network with applications to semiconductor defects detection
publisher Elsevier Inc.
publishDate 2018
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032186655&doi=10.1016%2fj.ins.2017.10.040&partnerID=40&md5=fefe70c2341a3f89d2d12059cf151c29
http://eprints.utp.edu.my/21815/
_version_ 1741196525297467392
score 11.62408

Similar Items