An efficient evolutionary algorithm for fuzzy inference systems
- Publication Type:
- Journal Article
- Citation:
- Evolving Systems, 2011, 2 (2), pp. 83 - 99
- Issue Date:
- 2011-06-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
10.1007_s12530-010-9024-8.pdf | Published Version | 931.62 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
In this paper, a novel self-constructing evolutionary algorithm (SCEA) for designing a TSK-type fuzzy model (TFM) is proposed. The proposed SCEA method is different from normal genetic algorithms (GAs). A chromosome of a population in traditional GAs represents a full solution and only one population presents all solutions in each generation. Our proposed method uses a population to evaluate a partial solution locally and applies several populations to construct a full solution. Thus, a chromosome represents only a partial solution. The proposed SCEA method uses the self-constructing learning algorithm to construct the TFM automatically that is based on the input training data to decide on the input partition. Fuzzy rules are created and begin to grow as the first training pattern arrives. Thus, the user need not give any a priori knowledge or even any initial information on the SCEA. We also adopted the sequence search-based dynamic evolution (SSDE) method to carry out parameter learning of the TFM. Simulation results have shown that the proposed SCEA method performs better than some existing methods. © 2010 Springer-Verlag.
Please use this identifier to cite or link to this item: