Research on Improved Quality Measures for the Fuzzy Association Rules of One Airborne Radar Intelligence Database

To address the problems of the rule redundancy and the long algorithm execution time in the process of mining one airborne radar intelligence database by the fuzzy association rules algorithm, this paper define a new QL-implicator based fuzzy support measure in order to enhance the recognition probability of the positive association rules and introduce the fuzzy conditional entropy measure (CE-measure) based on information theory to find the negative association rules, and then pruning the generated rules to shorten the run time of the algorithm. The experimental results show that the proposed method is effective, and the accuracy and efficiency for generating rules have improved significantly by comparing with the traditional fuzzy association rules algorithm.