Abstract
Emerging Patterns are itemsets whose supports change significantly from one dataset to another. They are useful as a means of discovering distinctions inherently present amongst a collection of datasets and have been shown to be a powerful method for constructing accurate classifiers. In this paper, we present two techniques for significantly improving emerging pattern classifying power. The first strategy involves mining patterns which have a more targeted description of their relative supports in each dataset. The second technique is to employ a pairwise classification strategy for situations where more than two classes are present. Novel mining algorithms are also presented which emphasise dataset partitioning as a crucial mechanism in reducing the complexity of the task. We provide experimental results demonstrating the value of these techniques and show that in general, the resulting classifier performs demonstrably better than other preeminent methods, while mining time is considerably improved on earlier methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bailey, J., Manoukian, T., Ramamohanarao, K.: Fast Algorithms For Mining Emerging Patterns. In: Proceedings of the Sixth European Conference on Principles of Data Mining and Knowledge Discovery, pp. 39–50 (2002)
Blake, C.L., Murphy, P.M.: UCI Repository of Machine Learning Databases, http://www.ics.uci.edu/~mlearn/MLRepository.html
Dong, G., Li, J.: Efficient Mining of Emerging Patterns: Discovering Trends and Differences. In: Proceedings of the Fifth International Conference on Knowledge Discovery and Data Mining, pp. 43–52 (1999)
Dong, G., Zhang, X., Wong, L., Li, J.: CAEP: Classification by Aggregating Emerging Patterns. In: Arikawa, S., Furukawa, K. (eds.) DS 1999. LNCS (LNAI), vol. 1721, pp. 30–42. Springer, Heidelberg (1999)
Fan, H., Ramamohanarao, K.: An Efficient Single-Scan Algorithm for Mining Essential Jumping Emerging Patterns. In: Proceedings of the Sixth Pacific Asia Conference on Knowledge Discovery in Databases, pp. 456–462 (2002)
Fayyad, U.M., Irani, K.B.: Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning. In: Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, pp. 1022–1027 (1993)
Furnkranz, J.: Pairwise Classification as an Ensemble Technique. In: Proceedings of the Thirteenth European Conference on Machine Learning, pp. 97–110 (2002)
Gouda, K., Zaki, M.J.: Efficiently Mining Maximal Frequent Itemsets. In: Proceedings of the First International Conference on Data Mining, pp. 163–170 (2001)
Han, J., Pei, J., Yin, Y.: Mining Frequent Patterns Without Candidate Generation. In: Proceedings of the International Conference on Management of Data, pp. 1–12 (2000)
Li, J.: Mining Emerging Patterns to Construct Accurate and Efficient Classifiers. PhD thesis, University of Melbourne (2001)
Li, J., Dong, G., Ramamohanarao, K.: Making use of the most Expressive Jumping Emerging Patterns for Classification. In: Proceedings of the Fourth Pacific Asia Conference on Knowledge Discovery in Databases, pp. 220–232 (2000)
Li, J., Dong, G., Ramamohanarao, K.: DeEPs: Instance-Based Classification by Emerging Patterns. In: Proceedings of the Fourth European Conference on Principles of Data Mining and Knowledge Discovery, pp. 191–200 (2000)
Li, J., Wong, L.: Emerging Patterns and Gene Expression Data. In: Proceedings of the Twelfth Workshop on Genome Informatics, pp. 3–13 (2001)
Liu, B., Hsu, W., Ma, Y.: Integrating Classification and Association Rule Mining. In: Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, pp. 80–86 (1998)
Mitchell, T.M.: Generalization as Search. Artificial Intelligence 18(2), 203–226 (1982)
Quinlan, J.R.: C4.5 Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)
Zhang, X., Dong, G., Ramamohanarao, K.: Eploring Constraints to Efficiently Mine Emerging Patterns from Large High-Dimensional Datasets. In: Proceedings of the Sixth International Conference on Knowledge Discovery and Data Mining, pp. 310–314 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bailey, J., Manoukian, T., Ramamohanarao, K. (2003). Classification Using Constrained Emerging Patterns. In: Dong, G., Tang, C., Wang, W. (eds) Advances in Web-Age Information Management. WAIM 2003. Lecture Notes in Computer Science, vol 2762. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45160-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-540-45160-0_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40715-7
Online ISBN: 978-3-540-45160-0
eBook Packages: Springer Book Archive