Research On Frequent-subtree Mining Algorithm Based On The Sequence Coding

Frequent patern mining is a basic problem of data mining,including mining transactions, sequences, trees and graphs. The algorithm for it has been prevalently used in many other data mining task, such as association analysis,period's analysis, maximal and closed paterns, query, classification and indextechnology etc.With the rapid development of internet, frequent pattern mining generalizes to more complex patterns like tree mining and graph mining. Methods for mining frequent trees are wdiely used in bioinformatics,web-mining,chemical data structure mining,and so on .In this paper, the frequent large-tree algorithm for mining, particularly those based on the growth patterns of tree-mining method conducted in-depth research and analysis, Based on the analysis of the main mode of growth strategy under various mining algorithm method with the skills, Mining against candidates process model and the generating support computational complexity characteristics, repeat operations and mining algorithm and the time consumption, We propose a simple and efficient algorithm for mining.This paper proposes the use of the tree coding sequence, in accordance with the mode of growth approach to mining frequent-tree algorithm. Algorithms based on the introduction of an array of sequence coding to indicate trees and forests; most left with the expansion path constructed integrity of the growth mode; According to the tree topology, in the tree-frequent pattern of various growth points structure corresponding expansion mode put candidates generating marvelously effective expansion into the search point. This approach not only ensures that the candidate generating completely non-redundant, but also support the calculation becomes more simple and feasible, On this basis, design and realization of the frequent mining sub-tree algorithm TreeMiner-G improved. Based on the algorithm and the TreeMiner Apriori algorithm, TreeMiner-G algorithm has found better performance. A broader scope, a simple transformation, we can for different types of trees to carry out excavations.