文档介绍:Subject : Research of Classification Algorithm Based on Association
Rule Mining
Specialty : Computer Application Technology
Name : Xu Lisha (Signature)
Instructor : Yang Junrui (Signature)
ABSTRACT
With the rapid development of information society, the importance of data mining in all
fields is more and more prominent. In the area of data mining, classification is an important
analytical method, and association rule mining is an important research direction. As they are
two highly active research areas in data mining, they have similarities in mining item sets
with strong relevance. Therefore, bination of the two techniques that apply mining
association rules in the task of classification opens a new journey for data
classification-associative classification.
Associative classification is essential classification based on association rules, which not
only reflects the application characteristics of knowledge-classification and prediction, but
also embodies the inherent associated characteristics of knowledge. The differences between
the associative classification methods are mainly reflected in two aspects: the method used in
mining frequent item sets and analyzing the mined rules for classification.
On the base of analyzing paring both strengths and weaknesses of the existing
associative classification algorithm, this paper presents an associative classification algorithm
based on P-Trie tree, named CARPT. This algorithm uses a vertical data format press
and store the original database, which reduces the number of database scanning and makes the
support counting convenient and improves the efficiency of the algorithm. The algorithm
regards a frequent item set as a string and uses P-Trie tree to store the frequent information, to
mine class association rules. It removes the frequent item sets that cannot generate frequent
rules directly by adding support count for class labels of frequent items during the
cons