Abstract

Most of the data mining algorithm focuses on frequent patterns, few algorithm emphases on rare items, but rare items [1] also have importance, for example, network intrusion detection, where among various normal connections we need to detect the rare malicious connections. Classification of such a non-uniform data set is a challenging issue. Most classifiers perform poorly in such a data set. Realizing the importance of rare class classification, in this paper we propose a classification algorithm (CBMR Algorithm) that is based on association rules mined by MSApriori approach [2] and is capable of classifying rare classes. The performance evaluation of the proposed algorithm has been done for different data sets [3] and in comparison with existing technique like [4], it is found that algorithm has efficient and superior performance for classifying rare cases.

References

• Weiss, G. M. "Mining With Rarity: A Unifying Framework. " SIGKDD Explorations, 2004, Vol. 6, Issue 1, pp. 7 – 19.
• Liu, B. , Hsu, W. , and Ma, Y. "Mining Association Rules with Multiple Minimum Supports. " SIGKDD Explorations, 1999wman, M. , Debray, S. K. , and Peterson, L. L. 1993. Reasoning about naming systems. .
• Coenen, F. (2003), The LUCS-KDD Discretized/normalised ARM and CARM data library http://www. csc. liv. ac. uk/~frans /KDD/Software /LUCS_KDD_DN/, Department of Computer Science, The University of Liverpool, UK.
• B. Liu, W. Hsu and Y. Ma, "Integrating classification and association rule mining", proceedings of the fourth international conference on knowledge discovery and data mining, 1998, pp. 80-86.
• M. S. Chen, J. Han, P. S. Yu, "Data mining: an overview from a database perspective", IEEE Transactions on Knowledge and Data Engineering, 1996, 8, pp. 866-883.
• Agrawal, R. , Imielinski, T. , and Swami, A. "Mining association rules between sets of items in large databases. " SIGMOD, 1993, pp. 207-216.
• Agrawal, R. , and Srikanth, R. "Fast algorithms for mining association rules. " VLDB, 1994.
• W. Li, J. Han and J. Pei, "CMAR: Accurate and efficient classification based on multiple class-association Rules", In ICDM'01, San Jose, CA, Nov. 2001, pp. 369-376.
• M. Kubat, R. C. Holte, and S. Matwin. Machine learning for the detection of oil spills in satellite radar images. Machine Learning, 30(2):195-215, 1998.
• P. K. Chan, and S. J. Stolfo. Toward scalable learning with non-uniform class and cost distributions: a case study in credit card fraud detection. In Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, pages 164-168, 2001.
• G. M. Weiss, and H. Hirsh. Learning to predict rare events in event sequences. In Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, pages 359-363, 1998.
• G. Medioni, I. Cohen, F. Brémond, S. Hongeng, and R. Nevatia. Event detection and analysis from video streams. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(8): 873-889, 2001.
• H. Zhong, J. Shi, and M. Visontai. Detecting unusual activity in video. Proc. CVPR'04, Washington, DC, 2004, Vol. 2, pp. 819-826.
• Mannila, H. "Methods and Problems in Data Mining. " ICDT, 1997.
• R. Kiran and P. Reddy "An Improved Multiple Minimum Support Based Approach to Mine Rare Association Rules" IEEE 2009.
• I. Kouris, C. Makris, A. Tsakalidis"An improved algorithm for mining association rules using multiple support values" FLAIRS 2003.
• Coenen, F. (2004). LUCS KDD implementation of CBA (Classification Based on associations). http://www. csc. liv. ac. uk/~frans/KDD/Software/CMAR/cba. html, Department of Computer Science, The University of Liverpool, UK.