The single input rule modules connected fuzzy inference method (SIRMs method) by Yubazaki et al. can decrease the number of fuzzy rules drastically in comparison with the conventional fuzzy inference methods. Moreover, Seki et al. have proposed a functional-type SIRMs method which generalizes the consequent part of the SIRMs method to function. However, these SIRMs methods can not be applied to XOR (Exclusive OR). In this paper, we propose a "kernel-type SIRMs method" which uses the kernel trick to the SIRMs method, and show that this method can treat XOR. Further, a learning algorithm of the proposed SIRMs method is derived by using the steepest descent method, and compared with the one of conventional SIRMs method and kernel perceptron by applying to identification of nonlinear functions, medical diagnostic system and discriminant analysis of Iris data.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hirosato SEKI, Fuhito MIZUGUCHI, Satoshi WATANABE, Hiroaki ISHII, Masaharu MIZUMOTO, "An Extended Method of SIRMs Connected Fuzzy Inference Method Using Kernel Method" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 10, pp. 2514-2521, October 2009, doi: 10.1587/transfun.E92.A.2514.
Abstract: The single input rule modules connected fuzzy inference method (SIRMs method) by Yubazaki et al. can decrease the number of fuzzy rules drastically in comparison with the conventional fuzzy inference methods. Moreover, Seki et al. have proposed a functional-type SIRMs method which generalizes the consequent part of the SIRMs method to function. However, these SIRMs methods can not be applied to XOR (Exclusive OR). In this paper, we propose a "kernel-type SIRMs method" which uses the kernel trick to the SIRMs method, and show that this method can treat XOR. Further, a learning algorithm of the proposed SIRMs method is derived by using the steepest descent method, and compared with the one of conventional SIRMs method and kernel perceptron by applying to identification of nonlinear functions, medical diagnostic system and discriminant analysis of Iris data.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.2514/_p
Copy
@ARTICLE{e92-a_10_2514,
author={Hirosato SEKI, Fuhito MIZUGUCHI, Satoshi WATANABE, Hiroaki ISHII, Masaharu MIZUMOTO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Extended Method of SIRMs Connected Fuzzy Inference Method Using Kernel Method},
year={2009},
volume={E92-A},
number={10},
pages={2514-2521},
abstract={The single input rule modules connected fuzzy inference method (SIRMs method) by Yubazaki et al. can decrease the number of fuzzy rules drastically in comparison with the conventional fuzzy inference methods. Moreover, Seki et al. have proposed a functional-type SIRMs method which generalizes the consequent part of the SIRMs method to function. However, these SIRMs methods can not be applied to XOR (Exclusive OR). In this paper, we propose a "kernel-type SIRMs method" which uses the kernel trick to the SIRMs method, and show that this method can treat XOR. Further, a learning algorithm of the proposed SIRMs method is derived by using the steepest descent method, and compared with the one of conventional SIRMs method and kernel perceptron by applying to identification of nonlinear functions, medical diagnostic system and discriminant analysis of Iris data.},
keywords={},
doi={10.1587/transfun.E92.A.2514},
ISSN={1745-1337},
month={October},}
Copy
TY - JOUR
TI - An Extended Method of SIRMs Connected Fuzzy Inference Method Using Kernel Method
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2514
EP - 2521
AU - Hirosato SEKI
AU - Fuhito MIZUGUCHI
AU - Satoshi WATANABE
AU - Hiroaki ISHII
AU - Masaharu MIZUMOTO
PY - 2009
DO - 10.1587/transfun.E92.A.2514
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 2009
AB - The single input rule modules connected fuzzy inference method (SIRMs method) by Yubazaki et al. can decrease the number of fuzzy rules drastically in comparison with the conventional fuzzy inference methods. Moreover, Seki et al. have proposed a functional-type SIRMs method which generalizes the consequent part of the SIRMs method to function. However, these SIRMs methods can not be applied to XOR (Exclusive OR). In this paper, we propose a "kernel-type SIRMs method" which uses the kernel trick to the SIRMs method, and show that this method can treat XOR. Further, a learning algorithm of the proposed SIRMs method is derived by using the steepest descent method, and compared with the one of conventional SIRMs method and kernel perceptron by applying to identification of nonlinear functions, medical diagnostic system and discriminant analysis of Iris data.
ER -