Applied Research Of Extension Approach In Data Mining Algorithm

Data mining is a multidisciplinary field,drawing work from areas including database technology,artificial intelligence,machine learning,neural networks,statistics,pattern recognition,knowledge-based systems,knowledge acquisition,information retrieval,high-performance computing,and data visualization. Discovering association rules is one of the most important task in data mining,that is to find interesting association or correlation relationships among a large set of data items.With massive amounts of data continuously being collected and stored,data patterns hidden in large data sets are more difficult to find. Thus to propose an efficient algorithm is very important and challenging,and is the main purpose of my dissertation.The method used in this paper is analyzing theory together with analyzing examples.The creation in this paper is we present an algorithm of association rules discovery based on Extension Transformation and Apriori Algorithm. The algorithm utilizes extension transformation to every matter-element in the matter-element set produced according to original database. The algorithm discusses not only itemsets but also tid-list,reducing database scans and saving a lot of time when finding frequent itemsets. We call the algorithm Association Rules Discovery Based on Extension Transformation (ARDBET). We experimentally compare the new algorithm against Apriori Algorithm obtaining satisfied improvements. Then we introduced a method of data classification based on extension sets,called extension classification. Finally we put forward an approach to reduce extension information space etc.data compression removing redundant data.In the end of the paper we get the conclusion,extension engineer theory and extension information analysis approach prepare basic theory for data mining and are good techniques of data mining.