An Improved Technique for Multi-Dimensional Constrained Gradient Mining

O. J. Elugbadebo, A. S. Sodiya, O Folorunso

Abstract


Multi-dimensional Constrained Gradient Mining, which is an aspect of data mining, is based on mining constrained frequent gradient pattern pairs with significant difference in their measures in transactional database. Top-k Fp-growth with Gradient Pruning and Top-k Fp-growth with No Gradient Pruning were the two algorithms used for Multi-dimensional Constrained Gradient Mining in previous studies. However, these algorithms have their shortcomings. The first requires construction of Fp-tree before searching through the database and the second algorithm requires searching of database twice in finding frequent pattern pairs. These cause the problems of using large amount of time and memory space, which retrogressively make mining of database cumbersome.  Based on this anomaly, a new algorithm that combines Top-k Fp-growth with Gradient pruning and Top-k Fp-growth with No Gradient pruning is designed to eliminate these drawbacks. The new algorithm called Top-K Fp-growth with support Gradient pruning (SUPGRAP) employs the method of scanning the database once, by searching for the node and all the descendant of the node of every task at each level. The idea is to form projected Multidimensional Database and then find the Multidimensional patterns within the projected databases. The evaluation of the new algorithm shows significant improvement in terms of time and space required over the existing algorithms.   


Keywords


Data mining, Association rules, Frequent itemsets, Multidimensional, Constraints, Gradient.

Full Text:

PDF

References


Agrawal, R., Ramakrishnan, S. 1994. Fast Algorithms for Mining Association Rules. In Proceedings of the 20th International Conference on Very Large Data bases (VLDB04), Santiago, de Chile, Chile.

Agrawal, R., Imielinski, T., Swami, A. 1993. Mining Association Rules between Sets of Items in Large Databases. In Proceedings of the ACM SIGMOD Conference on Management of Data (SIGMOD93), P. 207-216, Washington, D.C.

Guozhu Dong, Jiawei Han, Joyce M.W. Lam, Jian Pei, Ke Wang 2001. Mining Multidimensional Constrained Gradients in Data Cubes. To appear in Proceedings of 27th International Conference on Very Large Data Bases (VLDB01), September 11-14, 2001, Roma, Italy.

Guozhu Dong, Jiawei Han, Joyce M.W. Lam, Jian Pei, Ke Wang, Wei Zou 2004. "Mining Constrained Gradients in Large Databases," IEEE Transactions on Knowledge and Data Engineering, 16(8): 922-938.

Ibrahim, S.A. 2004. An Efficient pattern Growth Mining of Closed Frequent Itemsets: A thesis Submitted in Fulfilment of the requirement for the Degree of Master of science in the Department of Mathematical sciences, University of Agriculture, Abeokuta.

Jian Pei, Jiawei Han 2001. Can we push more Constraints into Frequent Pattern Mining?.In Proceedings of 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD00), p.350-354, August 20-23, 2000, Boston, MA, USA.

Jian Pei, Jiawei Han, Laks V.S. Lakshmanan 2001. Mining Frequent Itemsets with Convertible Constraints. In: Proceedings of the 17th International Conference on Data Engineering (ICDE01), April 2-6, 2001, Heidelberg, Germany.

Jiawei Han, Jian Pei, Yiwen Yin 2000. Mining Frequent Patterns without Candidate Generation. In Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data (SIGMOD00), May 16-18, 2000, Dallas, Texas, USA.

Joyce Man Wing Lam 2001: Multi-dimensional Constrained Gradient Mining. A Thesis Submitted in Partial Fulfillment the Requirement for the Degree Master of Science in the School of Computing Science: Simon Fraser University.

Neinbe, O.J. 2004. Mining Frequent MAX-Sequential patterns from Customer Portifolio Database: A thesis submitted in Fulfilment of the requirement for the Degree of Master of science in the Department of Mathematical sciences, University of Agriculture, Abeokuta.

Ansari, S., Sadreddini, M.H. 2009. An Efficient Approach to Mining Frequent Itemsets on Data Streams. In: Proceedings of World Academy of Science, Engineering and Technology, 37: ISBN 2070-3.

Tomasz Imielinski, L. Khachiyan, A. Abdulghani 2002. Cubegrades: Generalizing Association Rules, Data Mining and Knowledge Discovery, 6: 219-258.

Wang, J., Han, J., Pei, J. 2006. Closed Constrained Gradient Mining in Retail Databases, IEET Transactions on Knowledge and Data Engineering, 18(6): 764-769.


Refbacks

  • There are currently no refbacks.