Generation of fuzzy classification rules directly from overlapping input partitioning

Ioannis Gadaras; Ludmil Mikhailov; Stavros Lekkas

doi:10.1109/FUZZY.2007.4295424

Generation of fuzzy classification rules directly from overlapping input partitioning

Ioannis Gadaras, Ludmil Mikhailov, Stavros Lekkas

MSM Decision Sciences

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

The aim of this paper is to present a new method for extraction of fuzzy classification rules directly from numerical input - output data. The key feature of the proposed algorithm lies on the fact that it allows an overlapping between different classes. Appropriate membership functions are produced by projecting the geometrical characteristics of the corresponding classes on each input feature. The classification conflict is intuitively resolved by treating the overlapping regions separately, introducing double-consequent fuzzy rules. Finally, a fuzzy rule-based classification system is formalized, assembled, tested on Fisher Iris dataset and benchmarks d against similar approaches. © 2007 IEEE.

Original language	English
Title of host publication	IEEE International Conference on Fuzzy Systems\|IEEE Int Conf Fuzzy Syst
DOIs	https://doi.org/10.1109/FUZZY.2007.4295424
Publication status	Published - 2007
Event	2007 IEEE International Conference on Fuzzy Systems, FUZZY - London Duration: 1 Jul 2007 → …

Conference

Conference	2007 IEEE International Conference on Fuzzy Systems, FUZZY
City	London
Period	1/07/07 → …

Access to Document

10.1109/FUZZY.2007.4295424

Cite this

@inproceedings{d25cc7b62f514c8ba2c3bd13f7b857b8,

title = "Generation of fuzzy classification rules directly from overlapping input partitioning",

abstract = "The aim of this paper is to present a new method for extraction of fuzzy classification rules directly from numerical input - output data. The key feature of the proposed algorithm lies on the fact that it allows an overlapping between different classes. Appropriate membership functions are produced by projecting the geometrical characteristics of the corresponding classes on each input feature. The classification conflict is intuitively resolved by treating the overlapping regions separately, introducing double-consequent fuzzy rules. Finally, a fuzzy rule-based classification system is formalized, assembled, tested on Fisher Iris dataset and benchmarks d against similar approaches. {\textcopyright} 2007 IEEE.",

author = "Ioannis Gadaras and Ludmil Mikhailov and Stavros Lekkas",

year = "2007",

doi = "10.1109/FUZZY.2007.4295424",

language = "English",

isbn = "1424412102",

booktitle = "IEEE International Conference on Fuzzy Systems|IEEE Int Conf Fuzzy Syst",

note = "2007 IEEE International Conference on Fuzzy Systems, FUZZY ; Conference date: 01-07-2007",

}

TY - GEN

T1 - Generation of fuzzy classification rules directly from overlapping input partitioning

AU - Gadaras, Ioannis

AU - Mikhailov, Ludmil

AU - Lekkas, Stavros

PY - 2007

Y1 - 2007

N2 - The aim of this paper is to present a new method for extraction of fuzzy classification rules directly from numerical input - output data. The key feature of the proposed algorithm lies on the fact that it allows an overlapping between different classes. Appropriate membership functions are produced by projecting the geometrical characteristics of the corresponding classes on each input feature. The classification conflict is intuitively resolved by treating the overlapping regions separately, introducing double-consequent fuzzy rules. Finally, a fuzzy rule-based classification system is formalized, assembled, tested on Fisher Iris dataset and benchmarks d against similar approaches. © 2007 IEEE.

AB - The aim of this paper is to present a new method for extraction of fuzzy classification rules directly from numerical input - output data. The key feature of the proposed algorithm lies on the fact that it allows an overlapping between different classes. Appropriate membership functions are produced by projecting the geometrical characteristics of the corresponding classes on each input feature. The classification conflict is intuitively resolved by treating the overlapping regions separately, introducing double-consequent fuzzy rules. Finally, a fuzzy rule-based classification system is formalized, assembled, tested on Fisher Iris dataset and benchmarks d against similar approaches. © 2007 IEEE.

U2 - 10.1109/FUZZY.2007.4295424

DO - 10.1109/FUZZY.2007.4295424

M3 - Conference contribution

SN - 1424412102

SN - 9781424412105

BT - IEEE International Conference on Fuzzy Systems|IEEE Int Conf Fuzzy Syst

T2 - 2007 IEEE International Conference on Fuzzy Systems, FUZZY

Y2 - 1 July 2007

ER -

Generation of fuzzy classification rules directly from overlapping input partitioning

Abstract

Conference

Access to Document

Fingerprint

Cite this