Improving the Speed of Center of Sets Type Reduction in Interval Type-2 Fuzzy Systems by Eliminating the Need for Sorting | IEEE Journals & Magazine | IEEE Xplore

Improving the Speed of Center of Sets Type Reduction in Interval Type-2 Fuzzy Systems by Eliminating the Need for Sorting


Abstract:

In the deployment of interval type-2 fuzzy systems, one of the most important steps is the type reduction. The commonly used center of sets type reducer requires the solu...Show More

Abstract:

In the deployment of interval type-2 fuzzy systems, one of the most important steps is the type reduction. The commonly used center of sets type reducer requires the solution of two nonlinear constrained optimization problems. Frequently used approaches to solve them are the Karnik-Mendel algorithms and their variants. However, these algorithms suffer from the need for sorting, which is known to be computationally very expensive. Using the reformulations proposed in this paper for center of sets type reducer, it is possible to eliminate the need for sorting. This makes interval type-2 fuzzy systems more appropriate for cost-sensitive real-time applications. Extensive simulations are presented to illustrate the faster convergence speed of the proposed method over six other enhanced variants of the Karnik-Mendel algorithm as applied to center of sets type reduction of interval type-2 fuzzy systems.
Published in: IEEE Transactions on Fuzzy Systems ( Volume: 25, Issue: 5, October 2017)
Page(s): 1193 - 1206
Date of Publication: 24 August 2016

ISSN Information:


Contact IEEE to Subscribe

References

References is not available for this document.