Optimal fuzzy rule bases-the cat and mouse problem

Approximate fuzzy rule-based models are more precise if their size is bigger. A larger model, however, requires more time for its evaluation and hence the problem arises of finding a compromise between size and accuracy for the task at hand. This trade-off between computation time and precision is mapped into the problem of tracking a moving target: higher accuracy results in a tighter precision of the target location, but at the cost of longer computation time, during which the target can move further away, thus ultimately requiring a longer search time for target localization. This paper examines the problem of determining the optimal rule-base size that will yield a minimum total time required to repeatedly re-acquire a moving target. The general problem has no known solution: here solutions of specific cases are presented.