Abstract | ||
---|---|---|
The granularity and interpretability of a fuzzy model are influenced by the method used to construct the rule base. Models obtained by a heuristic assessment of the underlying system are generally highly granular with interpretable rules, while models algorithmically generated from an analysis of training data consist of a large number of rules with small granularity. This paper presents a method for increasing the granularity of rules while satisfying a prescribed precision bound on the training data. The model is generated by a two-stage process. The first step iteratively refines the partitions of the input domains until a rule base is generated that satisfies the precision bound. In this step, the antecedents of the rules are obtained from decomposable partitions of the input domains and the consequents are generated using proximity techniques. A greedy merging algorithm is then applied to increase the granularity of the rules while preserving the precision bound. To enhance the representational capabilities of a rule and reduce the number of rules required, the rules constructed by the merging procedure have multi-dimensional antecedents. A model defined with rules of this form incorporates advantageous features of both clustering and proximity methods for rule generation. Experimental results demonstrate the ability of the algorithm to reduce the number of rules in a fuzzy model with both precise and imprecise training information. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/TSMCB.2003.808186 | Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions |
Keywords | Field | DocType |
algorithm theory,fuzzy set theory,fuzzy systems,heuristic programming,learning (artificial intelligence),merging,algorithmic generation,antecedents,clustering methods,consequents,decomposable partitions,domain refinement,fuzzy model,granularity,greedy merging algorithm,heuristic assessment,imprecise training information,interpretability,interpretable rules,iteratively input domain partition refinement,model generation,precise training information,prescribed precision bound,proximity techniques,rule base,rule generation,rule reduction,training data | Data mining,Computer science,Fuzzy set,Artificial intelligence,Granularity,Fuzzy control system,Merge (version control),Cluster analysis,Interpretability,Heuristic,Mathematical optimization,Algorithm design,Machine learning | Journal |
Volume | Issue | ISSN |
33 | 1 | 1083-4419 |
Citations | PageRank | References |
11 | 0.57 | 20 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sudkamp, T. | 1 | 11 | 0.57 |
Knapp, A. | 2 | 11 | 0.57 |
Knapp, J. | 3 | 11 | 0.57 |