Identification of Type-2 Fuzzy Models for Time-Series Forecasting Using Particle Swarm Optimization

Author

Khosla, Mamta ; Sarin, Rakesh Kumar ; Uddin, Moin

Author_Institution

Dept. of Electron. & Commun. Eng., Dr. B.R. Ambekdar Nat. Inst. of Technol., Jalandhar, India

fYear

2012

fDate

11-13 May 2012

Firstpage

259

Lastpage

264

Abstract

This paper presents the fuzzy model identification framework, where Particle Swarm Optimization (PSO) algorithm has been used as an optimization engine for building Type-2 fuzzy models from the available chaotic Mackeyâ-Glass time-series data. The presented framework is capable of evolving the Membership Functions parameters, Footprint of Uncertainty (FOU) and the rule set to obtain an optimized Type-2 fuzzy model. Four experiments are reported for differently corrupted chaotic time-series data sets. Root Mean square error (RMSE), between the outputs of the designed T2 FLS and the target is used as the performance criterion to rate the quality of solutions and hence demonstrate the performance of the proposed framework.

Keywords

fuzzy set theory; mean square error methods; particle swarm optimisation; time series; FOU; PSO algorithm; RMSE; T2 FLS; chaotic Mackeyâ-Glass time-series data; footprint of uncertainty; membership functions parameters; optimization engine; particle swarm optimization; performance criterion; root mean square error; time-series forecasting; type-2 fuzzy model identification; Computational modeling; Data models; Forecasting; Frequency selective surfaces; Mathematical model; Predictive models; Uncertainty; Footprint of Uncertainty; Mackey-Glass time-series data; Particle Swarm Optimization; Type-2 Fuzzy Logic System;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication Systems and Network Technologies (CSNT), 2012 International Conference on

Conference_Location

Rajkot

Print_ISBN

978-1-4673-1538-8

Type

conf

DOI

10.1109/CSNT.2012.64

Filename

6200646