基于XML数据挖掘的Apriori算法的研究与改进

Research and Improvement of Apriori Algorithm for XML Data Mining[JZ)][HS)]

摘要:

XML以其诸多优点,迅速成为不同领域间信息表示与交换的标准;大量XML数据的出现给数据挖掘带来了新的挑战;挖掘XML数据关联规则的大部分工作都是基于Apriori算法的研究;对Apriori算法的基本方法与效率进行了分析,指出其不足,并提出了改进的XApriori算法,该算法基于新的数据结构,利用Hash表的存储技术以及对Apriori算法的优化来提高查找频繁项集的效率;对Apriori算法和XApriori算法进行了比较,实验结果表明改进的XApriori算法优于Apriori算法。

Abstract:

Due to its many advantages, XML has rapidly become as a standard for representing and exchanging information in different fields. A large number of XML data has brought new challenges to data mining. Most of the work for mining XML data association rules is based on Apriori algorithm.The basic methods and efficiency of Apriori are analyzed, pointing out its shortcomings and propose the improved XApriori algorithm. The algorithm is based on the new data structure, the use of Hash table and the optimization of Apriori to improve the efficiency of finding frequent item sets. The experimental results show that XApriori is superior to Apriori.