Automatic learning of general type-2 fuzzy logic systems using simulated annealing

ALMARAASHI, Majid, JOHN, Robert and HOPGOOD, Adrian (2014). Automatic learning of general type-2 fuzzy logic systems using simulated annealing. In: 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). Institute of Electrical and Electronics Engineers, 2384-2390.

Full text not available from this repository.
Official URL: http://dx.doi.org/10.1109/FUZZ-IEEE.2014.6891694
Link to published version:: https://doi.org/10.1109/FUZZ-IEEE.2014.6891694

Abstract

This paper reports on a new approach for automatic learning of general type-2 fuzzy logic systems (GT2FLSs) using simulated annealing (SA). The learning process in this work starts without an initial interval type-2 fuzzy system and has an objective to optimize all membership function parameters involved in the general type-2 fuzzy set in two stages. This is a novel methodology for learning GT2FLSs using the vertical-slices representation. The methodology used here is based on a proposed parameterization method presented in a previous work to ease the design of GT2FLSs. Two models of GT2FLSs have been applied using two different type-reduction techniques. The first technique is the sampling method, which is non-deterministic. The second technique is the vertical-slices centroid type-reduction (VSCTR), which is deterministic. Both models as well as an interval type-2 fuzzy logic system (IT2FLS) model have been applied to predict a Mackey-Glass time series. A comparison of the results of modeling these problems using the three models showed more accurate modeling for the GT2FLSs when using the VSCTR deterministic defuzzification method. It has also been shown that a GT2FLS with VSCTR defuzzification is more able to handle uncertainty than an IT2FLS, although the latter was faster.

Item Type: Book Section
Research Institute, Centre or Group - Does NOT include content added after October 2018: Materials and Engineering Research Institute > Modelling Research Centre > Microsystems and Machine Vision Laboratory
Identification Number: https://doi.org/10.1109/FUZZ-IEEE.2014.6891694
Page Range: 2384-2390
Depositing User: Hilary Ridgway
Date Deposited: 11 Dec 2014 10:16
Last Modified: 18 Mar 2021 09:15
URI: https://shura.shu.ac.uk/id/eprint/9018

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics