Induction of accurate and interpretable fuzzy rules from preliminary crisp representation

Tianhua Chen, Changjing Shang, Pan Su, Qiang Shen

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper proposes a novel approach for building transparent knowledge-based systems by generating accurate and interpretable fuzzy rules. The learning mechanism reported here induces fuzzy rules via making use of only predefined fuzzy labels that reflect prescribed notations and domain expertise, thereby ensuring transparency in the knowledge model adopted for problem solving. It works by mapping every coarsely learned crisp production rule in the knowledge base onto a set of potentially useful fuzzy rules, which serves as an initial step towards an intuitive technique for similarity-based rule generalisation. This is followed by a procedure that locally selects a compact subset of the emerging fuzzy rules, so that the resulting subset collectively generalises the underlying original crisp rule. The outcome of this local procedure forms the input to a global genetic search process, which seeks for a trade-off between accuracy and complexity of the eventually induced fuzzy rule base while maintaining transparency. Systematic experimental results are provided to demonstrate that the induced fuzzy knowledge base is of high performance and interpretability.
Original languageEnglish
Pages (from-to)152-166
Number of pages15
JournalKnowledge-Based Systems
Volume146
Early online date9 Feb 2018
DOIs
Publication statusPublished - 15 Apr 2018

Fingerprint

Fuzzy rules
Set theory
Transparency
Knowledge based systems
Labels
Induction

Cite this

Chen, Tianhua ; Shang, Changjing ; Su, Pan ; Shen, Qiang. / Induction of accurate and interpretable fuzzy rules from preliminary crisp representation. In: Knowledge-Based Systems. 2018 ; Vol. 146. pp. 152-166.
@article{125efda3d4d841bf9ee028b25fc0a908,
title = "Induction of accurate and interpretable fuzzy rules from preliminary crisp representation",
abstract = "This paper proposes a novel approach for building transparent knowledge-based systems by generating accurate and interpretable fuzzy rules. The learning mechanism reported here induces fuzzy rules via making use of only predefined fuzzy labels that reflect prescribed notations and domain expertise, thereby ensuring transparency in the knowledge model adopted for problem solving. It works by mapping every coarsely learned crisp production rule in the knowledge base onto a set of potentially useful fuzzy rules, which serves as an initial step towards an intuitive technique for similarity-based rule generalisation. This is followed by a procedure that locally selects a compact subset of the emerging fuzzy rules, so that the resulting subset collectively generalises the underlying original crisp rule. The outcome of this local procedure forms the input to a global genetic search process, which seeks for a trade-off between accuracy and complexity of the eventually induced fuzzy rule base while maintaining transparency. Systematic experimental results are provided to demonstrate that the induced fuzzy knowledge base is of high performance and interpretability.",
keywords = "Fuzzy rule-based systems, Interpretable fuzzy rules, Fuzzy rule learning, Crisp rules, Fuzzy rule-based classification",
author = "Tianhua Chen and Changjing Shang and Pan Su and Qiang Shen",
year = "2018",
month = "4",
day = "15",
doi = "10.1016/j.knosys.2018.02.003",
language = "English",
volume = "146",
pages = "152--166",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

Induction of accurate and interpretable fuzzy rules from preliminary crisp representation. / Chen, Tianhua; Shang, Changjing; Su, Pan ; Shen, Qiang.

In: Knowledge-Based Systems, Vol. 146, 15.04.2018, p. 152-166.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Induction of accurate and interpretable fuzzy rules from preliminary crisp representation

AU - Chen, Tianhua

AU - Shang, Changjing

AU - Su, Pan

AU - Shen, Qiang

PY - 2018/4/15

Y1 - 2018/4/15

N2 - This paper proposes a novel approach for building transparent knowledge-based systems by generating accurate and interpretable fuzzy rules. The learning mechanism reported here induces fuzzy rules via making use of only predefined fuzzy labels that reflect prescribed notations and domain expertise, thereby ensuring transparency in the knowledge model adopted for problem solving. It works by mapping every coarsely learned crisp production rule in the knowledge base onto a set of potentially useful fuzzy rules, which serves as an initial step towards an intuitive technique for similarity-based rule generalisation. This is followed by a procedure that locally selects a compact subset of the emerging fuzzy rules, so that the resulting subset collectively generalises the underlying original crisp rule. The outcome of this local procedure forms the input to a global genetic search process, which seeks for a trade-off between accuracy and complexity of the eventually induced fuzzy rule base while maintaining transparency. Systematic experimental results are provided to demonstrate that the induced fuzzy knowledge base is of high performance and interpretability.

AB - This paper proposes a novel approach for building transparent knowledge-based systems by generating accurate and interpretable fuzzy rules. The learning mechanism reported here induces fuzzy rules via making use of only predefined fuzzy labels that reflect prescribed notations and domain expertise, thereby ensuring transparency in the knowledge model adopted for problem solving. It works by mapping every coarsely learned crisp production rule in the knowledge base onto a set of potentially useful fuzzy rules, which serves as an initial step towards an intuitive technique for similarity-based rule generalisation. This is followed by a procedure that locally selects a compact subset of the emerging fuzzy rules, so that the resulting subset collectively generalises the underlying original crisp rule. The outcome of this local procedure forms the input to a global genetic search process, which seeks for a trade-off between accuracy and complexity of the eventually induced fuzzy rule base while maintaining transparency. Systematic experimental results are provided to demonstrate that the induced fuzzy knowledge base is of high performance and interpretability.

KW - Fuzzy rule-based systems

KW - Interpretable fuzzy rules

KW - Fuzzy rule learning

KW - Crisp rules

KW - Fuzzy rule-based classification

U2 - 10.1016/j.knosys.2018.02.003

DO - 10.1016/j.knosys.2018.02.003

M3 - Article

VL - 146

SP - 152

EP - 166

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -