Browsing by Author "Hemalatha, R"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Mining Frequent Item Sets More Efficiently Using ITL Mining
    (INFLIBNET Centre, 2005-02-02) Hemalatha, R; Krishnan, A; Hemamathi, R
    Correlated The discovery of association rules is an important problem in data mining. It is a two-step process consisting of finding the frequent itemsets and generating association rules from them. Most of the research attention is focused on efficient methods of finding frequent itemsets because it is computationally the most expensive step. This paper presents a new data structure and a more efficient algorithm for mining frequent itemsets from typical data sets. The improvement is achieved by scanning the database just once and by reducing item traversals within transactions. The performance comparisons of the algorithm against the fastest Apriori implementation and the recently developed H-Mine algorithm are given here. These results show that the algorithm outperforms both Apriori and H-mine on several widely used test data sets.
  • Thumbnail Image
    Item
    Mining of Confidence-Closed Correlated Patterns Efficiently
    (INFLIBNET Centre, 2005-02-02) Hemalatha, R; Krishnan, A; Senthamarai, C; Hemamalini, R
    Correlated pattern mining has become increasingly important recently as an alternative or an augmentation of association rule mining. Though correlated pattern mining discloses the correlation relationships among data objects and reduces significantly the number of patterns produced by the association mining, it still generates quite a large number of patterns. This paper proposes closed correlated pattern mining to reduce the number of the correlated patterns produced without information loss. A new notion of the confidenceclosed correlated patterns is proposed first, and then an efficient algorithm is present, called CCMine, for mining those patterns. Confidence closed pattern mining reduces the number of patterns by at least an order of magnitude. It also shows that CCMine outperforms a simple method making use of the traditional closed pattern miner. Confidence-closed pattern mining is a valuable approach to condensing correlated patterns.