Research On The Representation And Mining Of Frequent Itemsets Based On Pruned Concept Lattice

Data Mining is a new intercrossed subject relevant to artificial intelligence and database. At today's digital ages, the explosive growth of many business, government, and scientific databases have far outpaced our ability to interpret and digest this data, creating a need for a new generation of tools and techniques for automated and intelligent database analysis, and that is the goal of data mining.As an important pattern in data mining, association rules mining attract many researchers. Discovering frequent itemsets is a crucial step in association rule mining. However, the most algorithms mining frequent itemsets scan databases several times, which decreases the efficiency. The complete concept lattice model is introduced to the study of frequent itemsets mining in the dissertation. Contributions of the dissertation are as follows:1. The itemsets representation and their solution methods based on the concept lattice model are proposed. The study shows that each itemset should be presented as the intents or sub-intents of one concept in the concept lattice, thus it is able to completely describe these itemsets, similarly, many itemsets are derived from one concept through the relations among concepts in the concept lattice, consequently, the number of concepts in the concept lattice is reduced more markedly than that of itemsets in transaction databases.2. The frequent itemsets representation and their solution methods based on the model of Pruned concept lattice are proposed. The scale of frequent itemsets is compressed efficiently. The algorithm for mining frequent itemsets based on PCL is proposed, which prune the infrequent concepts timely and dynamically during the PCL's construction according to Apriori property. The efficiency of the algorithm is shown in the experiments.