Abstract

Time Series information are ordinarily utilized in information mining. Bunching is the most often utilized technique for exploratory information investigation. In this paper, a model is proposed for comparability search in ongoing one-sided time-arrangement information bases dependent on various grouping strategies. In the ongoing one-sided examination, information are significantly more fascinating and valuable for foreseeing future information than old ones. So in our technique, we attempt to lessen information dimensionality by keeping more detail on late information than more seasoned information. Because of "Dimensionality Curse" the first information is planned into a component space utilizing Vari–portioned Discrete Wavelet Transform1 and afterward closeness estimation is performed by applying distinctive grouping strategies such as Self Organizing Map (SOM), Hierarchical and K-means Clustering. This model is tried utilizing Control Chart Data and the bunching result watched demonstrates that the proposed model is better in gathering comparative arrangement under different goals.

References

1. Radha Devi DM, Thambidurai P. Clustering based similarity measurement model for recent biased time series databases. International Journal of Computer Science Engineering and Information Technology Research (IJCSEITR). 2013 Aug; 3(2):355–62.
2. Morchen F. Time series feature extraction for data mining using DWT and DFT. Philipps–University Marburg; 2003. Technical Report No. 33
3. Rokach L, Maimon O. Data Mining and Knowledge Discovery Handbook. Part III. US: Springer; 2005. Chapter 15, Clustering Methods; p. 321–352.
4. Fu TC. A review on time series data mining. Eng Appl Artif Intel. 2010; 24(1):164–81.
5. Gavrilov M, Anguelov D, Indyk P, Motwani R. Mining the stock market: which measure is best? Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2000; 487–96.
6. Agrawal R, Faloutsos C, Swami A. Efficient similarity search in sequence databases. In: Lomet DB, editor. Proceedings of the 4th International Conference on Foundations of Data organization and Algorithms; 1993 Oct 13–15; Chicago, Illinios, USA: Springer Verlag; 1993. p. 69–84.
7. Keogh E, Chakrabti K, Pazzani M, Mehrota S. Dimensionality reduction for fast similarity search in large time series databases. Knowl Inform Syst. 2001 Aug; 3(3):263–86.
8. Keogh E, Chakraborti K, Pazzani M, Mehrotra S. Locally adaptive dimensionality reduction for indexing large time series databases. ACM Transactions on Database Systems. 2002 Jun; 27(2):188–228.
9. Han J, Kamber M. Data mining concepts and techniques. 2nd ed. Morgan Kaufmann Publishers. 2009.
10. Xu R, Wunsch DT. Survey of clustering algorithms. IEEE Trans Neural Netw. 2005 May; 16(3):645–78.
11. Abbas OA. Comparison between data clustering algorithms. The Int Arab J Inform Tech. 2008 Jul; 5(3):320–25.
12. Kohonen T. Self–organizing maps. 2nd ed. Berlin, Heilderberg, Germany: Springer; 1995.
13. Zhang P, Li X, Zhang Z. Similarity search in time series databases based on SOFM neural network. Third International Conference on Natural Computation, ICNC 2007. 2007 Aug 24–27; Haikou, China; 2007. p. 715–18.
14. Vesanto J, Alhoniemi E. Clustering of SOM. IEEE Trans Neural Netw. 2000 May; 11(3):586–600.
15. Vesanto J. SOM based visualization methods. Intell Data Anal. 1999; 3(2):111–26.
16. UCI KDD Archive. Available from: http://kdd.ics.uci.edu/

Download PDF
Back