期刊
SOFT COMPUTING
卷 22, 期 4, 页码 1361-1380出版社
SPRINGER
DOI: 10.1007/s00500-017-2938-3
关键词
General type-2 fuzzy logic systems; alpha-Planes; Type-reduction; Weighted enhanced Karnik-Mendel algorithms; Continuous enhanced Karnik-Mendel algorithms; Computer simulation
资金
- Natural Science Foundation of China [61374113]
- Fundamental Research Funds for Liaoning's Universities [JL201615410]
With the development of -planes representation of general type-2 fuzzy sets (GT2 FSs), general type-2 fuzzy logic systems (GT2 FLSs) based on GT2 FSs have become a hot topic in academic field. While type-reduction (TR) is most critical block for a T2 FLS, generally speaking, the most popular Karnik-Mendel (KM) or enhanced KM (EKM) algorithms are used to perform the TR. The paper connects the EKM and the continuous version of EKM algorithms together and expands the EKM algorithms to three different forms of weighted EKM (WEKM) algorithms resort to the Newton-Cotes quadrature formulas of numerical integration techniques, while the EKM algorithms just become a special case of the WEKM algorithms. Four computer simulation examples are used to illustrate the performances of the WEKM algorithms. Compared with the EKM algorithms, the WEKM algorithms have smaller absolute error and faster convergence speed to compute the centroid defuzzified value of GT2 FLSs in general, which make them potentially applicable for T2 FLSs designers and adopters.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据