MSAFIS: an evolving fuzzy inference system

José de Jesús Rubio, Abdelhamid Bouchachia

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

© 2015, Springer-Verlag Berlin Heidelberg. In this paper, the problem of learning in big data is considered. To solve this problem, a new algorithm is proposed as the combination of two important evolving and stable intelligent algorithms: the sequential adaptive fuzzy inference system (SAFIS), and stable gradient descent algorithm (SGD). The modified sequential adaptive fuzzy inference system (MSAFIS) is the SAFIS with the difference that the SGD is used instead of the Kalman filter for the updating of parameters. The SGD improves the Kalman filter, because it first obtains a better learning in big data. The effectiveness of the introduced method is verified by two experiments.
Original languageAmerican English
Pages (from-to)2357-2366
Number of pages10
JournalSoft Computing
DOIs
StatePublished - 1 May 2017

Fingerprint

Fuzzy Inference System
Fuzzy inference
Descent Algorithm
Gradient Algorithm
Gradient Descent
Kalman Filter
Kalman filters
Updating
Experiment
Experiments
Learning
Big data

Cite this

de Jesús Rubio, José ; Bouchachia, Abdelhamid. / MSAFIS: an evolving fuzzy inference system. In: Soft Computing. 2017 ; pp. 2357-2366.
@article{2ff8f109a5624f27aa21796fe45310ae,
title = "MSAFIS: an evolving fuzzy inference system",
abstract = "{\circledC} 2015, Springer-Verlag Berlin Heidelberg. In this paper, the problem of learning in big data is considered. To solve this problem, a new algorithm is proposed as the combination of two important evolving and stable intelligent algorithms: the sequential adaptive fuzzy inference system (SAFIS), and stable gradient descent algorithm (SGD). The modified sequential adaptive fuzzy inference system (MSAFIS) is the SAFIS with the difference that the SGD is used instead of the Kalman filter for the updating of parameters. The SGD improves the Kalman filter, because it first obtains a better learning in big data. The effectiveness of the introduced method is verified by two experiments.",
author = "{de Jes{\'u}s Rubio}, Jos{\'e} and Abdelhamid Bouchachia",
year = "2017",
month = "5",
day = "1",
doi = "10.1007/s00500-015-1946-4",
language = "American English",
pages = "2357--2366",
journal = "Soft Computing",
issn = "1432-7643",
publisher = "Springer Verlag",

}

MSAFIS: an evolving fuzzy inference system. / de Jesús Rubio, José; Bouchachia, Abdelhamid.

In: Soft Computing, 01.05.2017, p. 2357-2366.

Research output: Contribution to journalArticle

TY - JOUR

T1 - MSAFIS: an evolving fuzzy inference system

AU - de Jesús Rubio, José

AU - Bouchachia, Abdelhamid

PY - 2017/5/1

Y1 - 2017/5/1

N2 - © 2015, Springer-Verlag Berlin Heidelberg. In this paper, the problem of learning in big data is considered. To solve this problem, a new algorithm is proposed as the combination of two important evolving and stable intelligent algorithms: the sequential adaptive fuzzy inference system (SAFIS), and stable gradient descent algorithm (SGD). The modified sequential adaptive fuzzy inference system (MSAFIS) is the SAFIS with the difference that the SGD is used instead of the Kalman filter for the updating of parameters. The SGD improves the Kalman filter, because it first obtains a better learning in big data. The effectiveness of the introduced method is verified by two experiments.

AB - © 2015, Springer-Verlag Berlin Heidelberg. In this paper, the problem of learning in big data is considered. To solve this problem, a new algorithm is proposed as the combination of two important evolving and stable intelligent algorithms: the sequential adaptive fuzzy inference system (SAFIS), and stable gradient descent algorithm (SGD). The modified sequential adaptive fuzzy inference system (MSAFIS) is the SAFIS with the difference that the SGD is used instead of the Kalman filter for the updating of parameters. The SGD improves the Kalman filter, because it first obtains a better learning in big data. The effectiveness of the introduced method is verified by two experiments.

U2 - 10.1007/s00500-015-1946-4

DO - 10.1007/s00500-015-1946-4

M3 - Article

SP - 2357

EP - 2366

JO - Soft Computing

JF - Soft Computing

SN - 1432-7643

ER -