Association rules mining based on improved PSO algorithm
Shang Qianxiang, Wu Ping · 2017
One of the most classic algorithms for association rules mining is the Apriori algorithm. But it can't satisfy the requirement as the increasing scale of the data. It has some disadvantages such as scanning database too many times, setting support and confidence thresholds artificially. Particle swarm optimization is one of the classic heuristic algorithms and some researchers has used it to association rules mining. But the problem that it may fall into the local optimal solution prematurely affects the efficiency of the algorithm. A new improved particle swarm optimization algorithm is proposed to solve this problem by controlling the particle velocity. In order to improve the efficiency and reliability of the algorithm in the condition of guarantee the global searching capability, an adaptive acceleration coefficient control method based on distance is used.