基于改进蚁群算法的频繁项集数据挖掘模型

Data mining model of frequent itemsets based the improved ant colony algorithms

针对传统Apriori算法在关联规则中频繁项集挖掘中效率不高的问题,文章提出了将频繁项集挖掘问题转化为TSP问题中最短路径的求解,利用改进后的蚁群算法进行挖掘,通过设计新的信息素计算方法使算法的执行效率得到提升。实验表明,与经典的Apriori算法进行比较,改进的蚁群算法能够在较短的时间里挖掘出大部分的频繁项集,是一种简洁有效的频繁项集挖掘模型。

Against the low efficiency of mining frequent itemsets in association rules with Apriori algorithm, the improved ant colony algorithm is proposed to mine the frequent itemsets with designing the new method to compute pheromone for improve the efficiency after converting mining frequent itemsets to finding the shortest path of TSP. Compared with classical Apriori algorithm, the experiments show that the improved ant colony algorithm can mine most frequent itemsets and it is an efficient mining model of frequent itemsets.