Towards more specific estimation of membership functions for data-driven fuzzy inference systems

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

5 Citaties (Scopus)

Uittreksel

Many fuzzy inference systems are built estimating their parameters from data. In particular, Takagi-Sugeno systems have been used a lot in data driven fuzzy modeling. In this paper, we investigate one step in data-driven identification of these models, namely the antecedent estimation when fuzzy clustering is used for estimating antecedent memberships and fuzzy rules. We propose removing noise coming from cluster membership values to obtain more specific antecedent sets, which is important for the interpretability of the models. The results obtained and presented in this paper show that this additional step leads to improved performance of the fuzzy model and higher specificity of the antecedents.
TaalEngels
Titel2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers (IEEE)
Aantal pagina's8
DOI's
StatusGepubliceerd - jul 2018
Evenement2018 IEEE International Conference on Fuzzy Systems (FUZZ 2018) - Rio de Janeiro, Brazilië
Duur: 8 jul 201813 jul 2018

Congres

Congres2018 IEEE International Conference on Fuzzy Systems (FUZZ 2018)
Verkorte titelFUZZ 2018
LandBrazilië
StadRio de Janeiro
Periode8/07/1813/07/18

Vingerafdruk

Fuzzy inference
Membership functions
Fuzzy clustering
Fuzzy rules
Identification (control systems)

Citeer dit

Fuchs, C. E. M., Wilbik, A. M., & Kaymak, U. (2018). Towards more specific estimation of membership functions for data-driven fuzzy inference systems. In 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) [8491524] Piscataway: Institute of Electrical and Electronics Engineers (IEEE). DOI: 10.1109/FUZZ-IEEE.2018.8491524
Fuchs, C.E.M. ; Wilbik, A.M. ; Kaymak, U./ Towards more specific estimation of membership functions for data-driven fuzzy inference systems. 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) . Piscataway : Institute of Electrical and Electronics Engineers (IEEE), 2018.
@inproceedings{8c5a191cf61d463c8949c120479726af,
title = "Towards more specific estimation of membership functions for data-driven fuzzy inference systems",
abstract = "Many fuzzy inference systems are built estimating their parameters from data. In particular, Takagi-Sugeno systems have been used a lot in data driven fuzzy modeling. In this paper, we investigate one step in data-driven identification of these models, namely the antecedent estimation when fuzzy clustering is used for estimating antecedent memberships and fuzzy rules. We propose removing noise coming from cluster membership values to obtain more specific antecedent sets, which is important for the interpretability of the models. The results obtained and presented in this paper show that this additional step leads to improved performance of the fuzzy model and higher specificity of the antecedents.",
author = "C.E.M. Fuchs and A.M. Wilbik and U. Kaymak",
year = "2018",
month = "7",
doi = "10.1109/FUZZ-IEEE.2018.8491524",
language = "English",
booktitle = "2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
address = "United States",

}

Fuchs, CEM, Wilbik, AM & Kaymak, U 2018, Towards more specific estimation of membership functions for data-driven fuzzy inference systems. in 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) ., 8491524, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, Rio de Janeiro, Brazilië, 8/07/18. DOI: 10.1109/FUZZ-IEEE.2018.8491524

Towards more specific estimation of membership functions for data-driven fuzzy inference systems. / Fuchs, C.E.M.; Wilbik, A.M.; Kaymak, U.

2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) . Piscataway : Institute of Electrical and Electronics Engineers (IEEE), 2018. 8491524.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

TY - GEN

T1 - Towards more specific estimation of membership functions for data-driven fuzzy inference systems

AU - Fuchs,C.E.M.

AU - Wilbik,A.M.

AU - Kaymak,U.

PY - 2018/7

Y1 - 2018/7

N2 - Many fuzzy inference systems are built estimating their parameters from data. In particular, Takagi-Sugeno systems have been used a lot in data driven fuzzy modeling. In this paper, we investigate one step in data-driven identification of these models, namely the antecedent estimation when fuzzy clustering is used for estimating antecedent memberships and fuzzy rules. We propose removing noise coming from cluster membership values to obtain more specific antecedent sets, which is important for the interpretability of the models. The results obtained and presented in this paper show that this additional step leads to improved performance of the fuzzy model and higher specificity of the antecedents.

AB - Many fuzzy inference systems are built estimating their parameters from data. In particular, Takagi-Sugeno systems have been used a lot in data driven fuzzy modeling. In this paper, we investigate one step in data-driven identification of these models, namely the antecedent estimation when fuzzy clustering is used for estimating antecedent memberships and fuzzy rules. We propose removing noise coming from cluster membership values to obtain more specific antecedent sets, which is important for the interpretability of the models. The results obtained and presented in this paper show that this additional step leads to improved performance of the fuzzy model and higher specificity of the antecedents.

U2 - 10.1109/FUZZ-IEEE.2018.8491524

DO - 10.1109/FUZZ-IEEE.2018.8491524

M3 - Conference contribution

BT - 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway

ER -

Fuchs CEM, Wilbik AM, Kaymak U. Towards more specific estimation of membership functions for data-driven fuzzy inference systems. In 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) . Piscataway: Institute of Electrical and Electronics Engineers (IEEE). 2018. 8491524. Beschikbaar vanaf, DOI: 10.1109/FUZZ-IEEE.2018.8491524