FS-FOIL: An inductive learning method for extracting interpretable fuzzy descriptions

Mario Drobics; Ulrich Bodenhofer; Erich Peter Klement

doi:10.1016/S0888-613X(02)00080-4

FS-FOIL: An inductive learning method for extracting interpretable fuzzy descriptions

Mario Drobics
, Ulrich Bodenhofer^*
, Erich Peter Klement

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

40 Citations (Scopus)

Abstract

This paper is concerned with FS-FOIL - an extension of Quinlan's First-Order Inductive Learning Method (FOIL). In contrast to the classical FOIL algorithm, FS-FOIL uses fuzzy predicates and, thereby, allows to deal not only with categorical variables, but also with numerical ones, without the need to draw sharp boundaries. This method is described in full detail along with discussions how it can be applied in different traditional application scenarios - classification, fuzzy modeling, and clustering. We provide examples of all three types of applications in order to illustrate the efficiency, robustness, and wide applicability of the FS-FOIL method.

Original language	English
Pages (from-to)	131-152
Number of pages	22
Journal	International Journal of Approximate Reasoning
Volume	32
Issue number	2-3
DOIs	https://doi.org/10.1016/S0888-613X(02)00080-4
Publication status	Published - Feb 2003
Externally published	Yes

Keywords

Clustering
Data mining
Fuzzy rules
Inductive learning
Interpretability
Machine learning

Access to Document

10.1016/S0888-613X(02)00080-4

Cite this

@article{2c61557e12f142e594d1e7e00536722e,

title = "FS-FOIL: An inductive learning method for extracting interpretable fuzzy descriptions",

abstract = "This paper is concerned with FS-FOIL - an extension of Quinlan's First-Order Inductive Learning Method (FOIL). In contrast to the classical FOIL algorithm, FS-FOIL uses fuzzy predicates and, thereby, allows to deal not only with categorical variables, but also with numerical ones, without the need to draw sharp boundaries. This method is described in full detail along with discussions how it can be applied in different traditional application scenarios - classification, fuzzy modeling, and clustering. We provide examples of all three types of applications in order to illustrate the efficiency, robustness, and wide applicability of the FS-FOIL method.",

keywords = "Clustering, Data mining, Fuzzy rules, Inductive learning, Interpretability, Machine learning",

author = "Mario Drobics and Ulrich Bodenhofer and Klement, \{Erich Peter\}",

note = "Funding Information: This work has been done in the framework of the Kplus Competence Center Program which is funded by the Austrian Government, the Province of Upper Austria, and the Chamber of Commerce of Upper Austria.",

year = "2003",

month = feb,

doi = "10.1016/S0888-613X(02)00080-4",

language = "English",

volume = "32",

pages = "131--152",

journal = "International Journal of Approximate Reasoning",

issn = "0888-613X",

publisher = "Elsevier",

number = "2-3",

}

TY - JOUR

T1 - FS-FOIL

T2 - An inductive learning method for extracting interpretable fuzzy descriptions

AU - Drobics, Mario

AU - Bodenhofer, Ulrich

AU - Klement, Erich Peter

N1 - Funding Information: This work has been done in the framework of the Kplus Competence Center Program which is funded by the Austrian Government, the Province of Upper Austria, and the Chamber of Commerce of Upper Austria.

PY - 2003/2

Y1 - 2003/2

N2 - This paper is concerned with FS-FOIL - an extension of Quinlan's First-Order Inductive Learning Method (FOIL). In contrast to the classical FOIL algorithm, FS-FOIL uses fuzzy predicates and, thereby, allows to deal not only with categorical variables, but also with numerical ones, without the need to draw sharp boundaries. This method is described in full detail along with discussions how it can be applied in different traditional application scenarios - classification, fuzzy modeling, and clustering. We provide examples of all three types of applications in order to illustrate the efficiency, robustness, and wide applicability of the FS-FOIL method.

AB - This paper is concerned with FS-FOIL - an extension of Quinlan's First-Order Inductive Learning Method (FOIL). In contrast to the classical FOIL algorithm, FS-FOIL uses fuzzy predicates and, thereby, allows to deal not only with categorical variables, but also with numerical ones, without the need to draw sharp boundaries. This method is described in full detail along with discussions how it can be applied in different traditional application scenarios - classification, fuzzy modeling, and clustering. We provide examples of all three types of applications in order to illustrate the efficiency, robustness, and wide applicability of the FS-FOIL method.

KW - Clustering

KW - Data mining

KW - Fuzzy rules

KW - Inductive learning

KW - Interpretability

KW - Machine learning

UR - https://www.scopus.com/pages/publications/0037311077

U2 - 10.1016/S0888-613X(02)00080-4

DO - 10.1016/S0888-613X(02)00080-4

M3 - Article

AN - SCOPUS:0037311077

SN - 0888-613X

VL - 32

SP - 131

EP - 152

JO - International Journal of Approximate Reasoning

JF - International Journal of Approximate Reasoning

IS - 2-3

ER -

FS-FOIL: An inductive learning method for extracting interpretable fuzzy descriptions

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this