Design of fuzzy expert system for microarray data classification using a novel Genetic Swarm Algorithm

Knowledge gained through classification of microarray gene expression data is increasingly important as they are useful for phenotype classification of diseases. Different from black box methods, fuzzy expert system can produce interpretable classifier with knowledge expressed in terms of if-then rules and membership function. This paper proposes a novel Genetic Swarm Algorithm (GSA) for obtaining near optimal rule set and membership function tuning. Advanced and problem specific genetic operators are proposed to improve the convergence of GSA and classification accuracy. The performance of the proposed approach is evaluated using six gene expression data sets. From the simulation study it is found that the proposed approach generated a compact fuzzy system with high classification accuracy for all the data sets when compared with other approaches.

► A hybrid GA and PSO approach is proposed for designing fuzzy expert system.
► GA is used to find the rules and PSO is used to tune the membership function.
► Advanced genetic operators are applied to improve the quality of solution.
► Microarray datasets for Diabetes, Cancer, and Rheumatoid Arthritis are examined.
► A compact fuzzy system with high classification accuracy is obtained for all cases.