Abstract
In this paper, we present a genetic algorithm to perform global searching for generating interesting association rules from Spatial Gene Expression Data. The typical approach of association rule mining is to make strong simplifying assumptions about the form of the rules, and limit the measure of rule quality to simple properties such as minimum support or minimum confidence. Minimum-support or minimum confidence means that users must specify suitable thresholds for their mining tasks though they may have no knowledge concerning databases. The presented approach does not require users to specify thresholds. Instead of generating an unknown number of association rules, only the most interesting rules are generated according to interestingness measure as defined by the fitness function. Computational results show that applying this genetic algorithm to search for high quality association rules with their confidence and interestingness acceptably maximized leads to better results.