On equivalence of FIS and ELM for interpretable rule-based knowledge representation

Shen Yuong Wong, Keem Siah Yap, Hwa Jen Yap, Shing Chiang Tan, Siow Wee Chang

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

This paper presents a fuzzy extreme learning machine (F-ELM) that embeds fuzzy membership functions and rules into the hidden layer of extreme learning machine (ELM). Similar to the concept of ELM that employed the random initialization technique, three parameters of F-ELM are randomly assigned. They are the standard deviation of the membership functions, matrix-C (rule-combination matrix), and matrix-D [don't care (DC) matrix]. Fuzzy if-then rules are formulated by the rule-combination Matrix of F-ELM, and a DC approach is adopted to minimize the number of input attributes in the rules. Furthermore, F-ELM utilizes the output weights of the ELM to form the target class and confidence factor for each of the rules. This is to indicate that the corresponding consequent parameters are determined analytically. The operations of F-ELM are equivalent to a fuzzy inference system. Several benchmark data sets and a real world fault detection and diagnosis problem have been used to empirically evaluate the efficacy of the proposed F-ELM in handling pattern classification tasks. The results show that the accuracy rates of F-ELM are comparable (if not superior) to ELM with distinctive ability of providing explicit knowledge in the form of interpretable rule base.

Original languageEnglish
Article number6877713
Pages (from-to)1417-1430
Number of pages14
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume26
Issue number7
DOIs
Publication statusPublished - 01 Jul 2015

Fingerprint

Knowledge representation
Learning systems
Membership functions
Fuzzy inference
Fault detection
Pattern recognition
Failure analysis

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Wong, Shen Yuong ; Yap, Keem Siah ; Yap, Hwa Jen ; Tan, Shing Chiang ; Chang, Siow Wee. / On equivalence of FIS and ELM for interpretable rule-based knowledge representation. In: IEEE Transactions on Neural Networks and Learning Systems. 2015 ; Vol. 26, No. 7. pp. 1417-1430.
@article{0a484ef05bae42c6885b818f0be16842,
title = "On equivalence of FIS and ELM for interpretable rule-based knowledge representation",
abstract = "This paper presents a fuzzy extreme learning machine (F-ELM) that embeds fuzzy membership functions and rules into the hidden layer of extreme learning machine (ELM). Similar to the concept of ELM that employed the random initialization technique, three parameters of F-ELM are randomly assigned. They are the standard deviation of the membership functions, matrix-C (rule-combination matrix), and matrix-D [don't care (DC) matrix]. Fuzzy if-then rules are formulated by the rule-combination Matrix of F-ELM, and a DC approach is adopted to minimize the number of input attributes in the rules. Furthermore, F-ELM utilizes the output weights of the ELM to form the target class and confidence factor for each of the rules. This is to indicate that the corresponding consequent parameters are determined analytically. The operations of F-ELM are equivalent to a fuzzy inference system. Several benchmark data sets and a real world fault detection and diagnosis problem have been used to empirically evaluate the efficacy of the proposed F-ELM in handling pattern classification tasks. The results show that the accuracy rates of F-ELM are comparable (if not superior) to ELM with distinctive ability of providing explicit knowledge in the form of interpretable rule base.",
author = "Wong, {Shen Yuong} and Yap, {Keem Siah} and Yap, {Hwa Jen} and Tan, {Shing Chiang} and Chang, {Siow Wee}",
year = "2015",
month = "7",
day = "1",
doi = "10.1109/TNNLS.2014.2341655",
language = "English",
volume = "26",
pages = "1417--1430",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "7",

}

On equivalence of FIS and ELM for interpretable rule-based knowledge representation. / Wong, Shen Yuong; Yap, Keem Siah; Yap, Hwa Jen; Tan, Shing Chiang; Chang, Siow Wee.

In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 26, No. 7, 6877713, 01.07.2015, p. 1417-1430.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On equivalence of FIS and ELM for interpretable rule-based knowledge representation

AU - Wong, Shen Yuong

AU - Yap, Keem Siah

AU - Yap, Hwa Jen

AU - Tan, Shing Chiang

AU - Chang, Siow Wee

PY - 2015/7/1

Y1 - 2015/7/1

N2 - This paper presents a fuzzy extreme learning machine (F-ELM) that embeds fuzzy membership functions and rules into the hidden layer of extreme learning machine (ELM). Similar to the concept of ELM that employed the random initialization technique, three parameters of F-ELM are randomly assigned. They are the standard deviation of the membership functions, matrix-C (rule-combination matrix), and matrix-D [don't care (DC) matrix]. Fuzzy if-then rules are formulated by the rule-combination Matrix of F-ELM, and a DC approach is adopted to minimize the number of input attributes in the rules. Furthermore, F-ELM utilizes the output weights of the ELM to form the target class and confidence factor for each of the rules. This is to indicate that the corresponding consequent parameters are determined analytically. The operations of F-ELM are equivalent to a fuzzy inference system. Several benchmark data sets and a real world fault detection and diagnosis problem have been used to empirically evaluate the efficacy of the proposed F-ELM in handling pattern classification tasks. The results show that the accuracy rates of F-ELM are comparable (if not superior) to ELM with distinctive ability of providing explicit knowledge in the form of interpretable rule base.

AB - This paper presents a fuzzy extreme learning machine (F-ELM) that embeds fuzzy membership functions and rules into the hidden layer of extreme learning machine (ELM). Similar to the concept of ELM that employed the random initialization technique, three parameters of F-ELM are randomly assigned. They are the standard deviation of the membership functions, matrix-C (rule-combination matrix), and matrix-D [don't care (DC) matrix]. Fuzzy if-then rules are formulated by the rule-combination Matrix of F-ELM, and a DC approach is adopted to minimize the number of input attributes in the rules. Furthermore, F-ELM utilizes the output weights of the ELM to form the target class and confidence factor for each of the rules. This is to indicate that the corresponding consequent parameters are determined analytically. The operations of F-ELM are equivalent to a fuzzy inference system. Several benchmark data sets and a real world fault detection and diagnosis problem have been used to empirically evaluate the efficacy of the proposed F-ELM in handling pattern classification tasks. The results show that the accuracy rates of F-ELM are comparable (if not superior) to ELM with distinctive ability of providing explicit knowledge in the form of interpretable rule base.

UR - http://www.scopus.com/inward/record.url?scp=84933037890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933037890&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2014.2341655

DO - 10.1109/TNNLS.2014.2341655

M3 - Article

VL - 26

SP - 1417

EP - 1430

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 7

M1 - 6877713

ER -