基于邻接矩阵的FP-tree构造算法  

Construction algorithm of FP-tree based on adjacency matrix

作　　者：刘应东[1] 冷明伟[2] 陈晓云[3] 

机构地区：[1]兰州交通大学交通运输学院,兰州730070 [2]上饶师范学院数学与计算机系,江西上饶334000 [3]兰州大学信息科学与工程学院,兰州730000

出　　处：《计算机工程与应用》2011年第7期153-155,共3页Computer Engineering and Applications

基　　金：江西省教育厅青年科学基金资助(No.GJJ09616);江西省教育厅科技课题项目资助(No.GJJ09377)

摘　　要：提出了一种基于邻接矩阵的FP-tree构造方法。首先通过扫描数据库建立2-项集支持数的邻接矩阵,通过邻接矩阵对项进行过滤和新方式排序,然后再利用邻接矩阵构造FP-tree,使得FP-tree的分支、节点数和深度大幅度地减少,从而使存储空间减少、遍历时间缩短。最后使用标准数据集进行验证测试并和其他算法的比较,实验结果表明,该算法在保证结果的同时有效地提高频繁项集挖掘的效率。A construction algorithm of FP-tree based on adjacency matrix is proposed.An adjacency matrix about support count of 2-frequent item sets is constructed by scanning database.Using the adjacency matrix,FP-tree is established after item sets are filtered and restructured.For the numbers of branches,nodes and depths are reduced greatly,the storage space is far less and ergodic time is shorter much.The construction algorithm is tested and verified using standard datasets.The result shows the new construction strategy can improve efficiency of frequent item mining and ensure validity of the results compared with others algorithms.

关 键 词：数据挖掘 频繁项集 FP-TREE算法 邻接矩阵 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]