Effects of fuzzy membership function shapes on clustering performance in multisensor-multitarget data fusion systems

Fuzzy systems have been proven very successfully in many important applications and are rapidly growing to become a powerful technique for multisenosr-multitarget data fusion. The functional paradigm for fuzzy multisenosr-multitarget data fusion consists of fuzzification, fuzzy knowledge-base, fuzzy inference mechanism, and defuzzification. In fuzzy system design, users start with some fuzzy rules, which are chosen heuristically based on their experience, and membership functions, which in many cases are chosen subjectively based on understanding the problem, and they use the developed system to tune these rules and membership functions. Constructing membership function is the most important step in the fuzzy system design. This paper addresses the problem of constructing the optimal membership functions from input data in a multisenosr-multitarget environment. This analysis has been applied to clustering of multisensor information in a two-dimensional multisenosr-multitarget data fusion system. Clustering performance using optimal membership functions is compared to that of clustering using non-optimal membership functions. The results show that there is a significant performance improvement when using optimal membership functions.