Abstract
One important series mining problems is finding important patterns in larger time series sets. Two limitations of previous works were the poor scalability and the robustness to noise. Here we introduce a algorithm using symbolic mapping based on concept tree. The slope of subsequence is chosen to describe series data. Then, the numerical data is transformed into low dimension symbol by cloud models. Due to characteristic of the cloud models, the loss of data in the course of linear preprocessing is treated. Moreover, it is more flexible for the local noise. Second, cloud Boolean calculation is realized to automatically produce the basic concepts as the leaf nodes in pan-concept-tree which leads to hierarchal discovering of the knowledge .Last, the probabilistic project algorithm was adapted so that comparison among symbols may be carried out with less CPU computing time. Experiments show strong robustness and less time and space complexity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hegland, M., Clarke, W., Kahn, M.: Mining the MACHO dataset. Computer Physics Communications 142(1-3), 22–28 (2002)
Engelhardt, B., Chien, S., Mutz, D.: Hypothesis generation strategies for adaptive problem solving. In: Proceedings of the IEEE Aerospace Conference, Big Sky, MT (2000)
Tompa, M., Buhler, J.: Finding motifs using random projections. In: Proceedings of the 5th Int’l Conference on Computational Molecular Biology, Montreal, Canada, pp. 67–74 (2001)
Keogh, E., Chakrabarti, K., Pazzani, M., et al.: Dimensionality reduction for fast similarity search in large time series databases. Journal of Knowledge and Information Systems 3(3), 263–286 (2000)
Li, D.Y., Cheung, D., Shi, X.M., et al.: Uncertainty reasoning based on cloud models in controllers. Computer Math. Applic. 35(3), 99–123 (1998)
Weng, Y.J., Zhu, Z.Y.: Research on Time Series Data Mining Based on Linguistic Concept Tree Technique. In: Proceeding of the IEEE Int’l Conference on Systems, Man & Cybernetics, Washington, D.C., pp. 1429–1434 (2003)
Jiang, R., Li, D.Y.: Similarity search based on shape representation in time-series data sets. Journal of computer research & development 37(5), 601–608 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weng, Y., Zhu, Z. (2004). Pattern Mining for Time Series Based on Cloud Theory Pan-concept-tree. In: Tsumoto, S., Słowiński, R., Komorowski, J., Grzymała-Busse, J.W. (eds) Rough Sets and Current Trends in Computing. RSCTC 2004. Lecture Notes in Computer Science(), vol 3066. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25929-9_76
Download citation
DOI: https://doi.org/10.1007/978-3-540-25929-9_76
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22117-3
Online ISBN: 978-3-540-25929-9
eBook Packages: Springer Book Archive