Dinesh Devaraj

Improved genetic algorithm for optimal design of fuzzy classifier

One of the important issues in the design of fuzzy classifier is the formation of fuzzy if-then rules and the membership functions. This paper presents a Genetic Algorithm (GA) approach to obtain the optimal rule-set and the membership function. To develop the fuzzy system the membership functions and rule-set are encoded into the chromosome and evolved simultaneously using GA. Advanced genetic operators are applied to improve the performance of the GA in designing the fuzzy classifier. The performance of the proposed approach is demonstrated through development of fuzzy classifier for Iris, Wine and tcpdump data. From the simulation study, it is found that the improved GA produces a fuzzy classifier which has minimum number of rules and high classification accuracy. Statistical analysis of the test results shows the superiority of the proposed algorithm over the existing methods.

Type A woolly hair nevus

We present a 5-year-old girl with Type A woolly hair nevus. This is a rare non-hereditary focal condition characterized by unruly and tightly coiled hair. It may be associated with epidermal or melanocytic nevus. Children with woolly hair must be examined completely and monitored regularly to rule out cardiofaciocutaneous and Noonan syndrome.