A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning

Ming-Feng Han; Chin-Teng Lin; Jyh Yeong Chang

doi:10.1109/ICSMC.2010.5642019

A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning

Ming-Feng Han, Chin-Teng Lin, Jyh Yeong Chang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

A compensatory neurofuzzy system (CNFS) with on-line learning ability is proposed in this paper. The proposed CNFS model uses a compensatory layer to raise the diversity of fuzzy rules by compensatory weights. The compensatory layer can automatically compare with each fuzzy rule and select higher resources for more important fuzzy rule. An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the fuzzy measure to determine the number of fuzzy rules. The parameter learning, based on the gradient descent method, can adjust the shape of the membership function and the weights of the compensatory layer. To demonstrate the capability of the proposed CNFS, it is applied to the Iris, and Wisconsin breast cancer classification datasets from the UCI Repository. Experimental results show that the proposed CNFS for pattern classification can achieve good classification performance.

Original language	American English
Title of host publication	2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010)
Publisher	IEEE
ISBN (Print)	978-1-4244-6588-0
DOIs	https://doi.org/10.1109/ICSMC.2010.5642019
State	Published - 2010
Event	2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010 - Istanbul, Turkey Duration: 10 Oct 2010 → 13 Oct 2010

Publication series

Name	IEEE International Conference on Systems Man and Cybernetics Conference Proceedings
Publisher	IEEE
ISSN (Print)	1062-922X

Conference

Conference	2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010
Country	Turkey
City	Istanbul
Period	10/10/10 → 13/10/10

Keywords

Compensatory NeuroFuzzy System (CNFS); NeuroFuzzy System; Compensation; Classification

Access to Document

10.1109/ICSMC.2010.5642019

Fingerprint Dive into the research topics of 'A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning'. Together they form a unique fingerprint.

Cite this

Han, M-F., Lin, C-T., & Chang, J. Y. (2010). A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning. In 2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010) ( IEEE International Conference on Systems Man and Cybernetics Conference Proceedings). IEEE. https://doi.org/10.1109/ICSMC.2010.5642019

@inproceedings{eefef811404744238c4d471a8ab8fa62,

title = "A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning",

abstract = "A compensatory neurofuzzy system (CNFS) with on-line learning ability is proposed in this paper. The proposed CNFS model uses a compensatory layer to raise the diversity of fuzzy rules by compensatory weights. The compensatory layer can automatically compare with each fuzzy rule and select higher resources for more important fuzzy rule. An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the fuzzy measure to determine the number of fuzzy rules. The parameter learning, based on the gradient descent method, can adjust the shape of the membership function and the weights of the compensatory layer. To demonstrate the capability of the proposed CNFS, it is applied to the Iris, and Wisconsin breast cancer classification datasets from the UCI Repository. Experimental results show that the proposed CNFS for pattern classification can achieve good classification performance.",

keywords = "Compensatory NeuroFuzzy System (CNFS); NeuroFuzzy System; Compensation; Classification",

author = "Ming-Feng Han and Chin-Teng Lin and Chang, {Jyh Yeong}",

year = "2010",

doi = "10.1109/ICSMC.2010.5642019",

language = "American English",

isbn = "978-1-4244-6588-0",

series = " IEEE International Conference on Systems Man and Cybernetics Conference Proceedings",

publisher = "IEEE",

booktitle = "2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010)",

note = "2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010 ; Conference date: 10-10-2010 Through 13-10-2010",

}

Han, M-F, Lin, C-T & Chang, JY 2010, A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning. in 2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010). IEEE International Conference on Systems Man and Cybernetics Conference Proceedings, IEEE, 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010, Istanbul, Turkey, 10/10/10. https://doi.org/10.1109/ICSMC.2010.5642019

A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning. / Han, Ming-Feng; Lin, Chin-Teng; Chang, Jyh Yeong.

2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010). IEEE, 2010. ( IEEE International Conference on Systems Man and Cybernetics Conference Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Compensatory NeuroFuzzy System with Online Constructing and Parameter Learning

AU - Han, Ming-Feng

AU - Lin, Chin-Teng

AU - Chang, Jyh Yeong

PY - 2010

Y1 - 2010

N2 - A compensatory neurofuzzy system (CNFS) with on-line learning ability is proposed in this paper. The proposed CNFS model uses a compensatory layer to raise the diversity of fuzzy rules by compensatory weights. The compensatory layer can automatically compare with each fuzzy rule and select higher resources for more important fuzzy rule. An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the fuzzy measure to determine the number of fuzzy rules. The parameter learning, based on the gradient descent method, can adjust the shape of the membership function and the weights of the compensatory layer. To demonstrate the capability of the proposed CNFS, it is applied to the Iris, and Wisconsin breast cancer classification datasets from the UCI Repository. Experimental results show that the proposed CNFS for pattern classification can achieve good classification performance.

AB - A compensatory neurofuzzy system (CNFS) with on-line learning ability is proposed in this paper. The proposed CNFS model uses a compensatory layer to raise the diversity of fuzzy rules by compensatory weights. The compensatory layer can automatically compare with each fuzzy rule and select higher resources for more important fuzzy rule. An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the fuzzy measure to determine the number of fuzzy rules. The parameter learning, based on the gradient descent method, can adjust the shape of the membership function and the weights of the compensatory layer. To demonstrate the capability of the proposed CNFS, it is applied to the Iris, and Wisconsin breast cancer classification datasets from the UCI Repository. Experimental results show that the proposed CNFS for pattern classification can achieve good classification performance.

KW - Compensatory NeuroFuzzy System (CNFS); NeuroFuzzy System; Compensation; Classification

U2 - 10.1109/ICSMC.2010.5642019

DO - 10.1109/ICSMC.2010.5642019

M3 - Conference contribution

SN - 978-1-4244-6588-0

T3 - IEEE International Conference on Systems Man and Cybernetics Conference Proceedings

BT - 2010 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010)

PB - IEEE

T2 - 2010 IEEE International Conference on Systems, Man and Cybernetics, SMC 2010

Y2 - 10 October 2010 through 13 October 2010

ER -