Garibaldi and Ifeachor : Application of Simulated Annealing Fuzzy Model Tuning

| Fuzzy logic and fuzzy set theory provide an important framework for representing and managing impre-cision and uncertainty in medical expert systems, but the need remains to optimise such systems to enhance performance. This paper presents a general technique for optimizing fuzzy models in fuzzy expert systems by simulated annealing and N-dimensional hill climbing simplex method. The application of the technique to a fuzzy expert system for the interpretation of the acid-base balance of blood in the umbilical cord of new born infants is presented. The Spear-man Rank Order Correlation statistic was used to assess and to compare the performance of a commercially available crisp expert system, an initial fuzzy expert system and a tuned fuzzy expert system with experienced clinicians. Results showed that without tuning, the performance of the crisp system was signiicantly better (correlation of 0.80) than the fuzzy expert system (correlation of 0.67). The performance of the tuned fuzzy expert system was better than the crisp system and eeectively indistinguishable from the clinicians (correlation of 0.93) on training data, and was the best of the expert systems on validation data. Unlike most applications of fuzzy logic, where all fuzzy sets have normalised heights of unity, in this application it was found that a reduction in the height of some fuzzy sets was eeective in enhancing performance. This suggests that the height of fuzzy sets may be a generally useful parameter in tuning fuzzy expert systems.