Improved genetic algorithm based on simulated annealing and quantum computing strategy for mining association rules

Association rules mining is an important content in data mining. It can discover the relations of different attributes by analyzing and disposing data which is in database. This paper proposes a novel data mining algorithm to enhance the capability of exploring valuable information from databases with continuous values. The algorithm combines with quantum-inspired genetic algorithm and simulated annealing to find interesting association rules. The final best sets of membership functions in all the populations are then gathered together to be used for mining association rules. The experiment result demonstrates that the proposed approach could generate more association rules than other algorithms. © 2010 ACADEMY PUBLISHER.