Department of Computer Science, University of Sherbook, Quebec, Canada 在期刊界中查找 在百度中查找 在本站中查找
作者单位:
作者简介:
通讯作者:
中图分类号:
基金项目:
Supported by the National Natural Science Foundation of China under Grant No.10771176 (国家自然科学基金); the National 985 Project of China under Grant No.0000-X07204 (国家"九八五"工程二期基金)
Pattern Matching Method Based on Point Distribution for Multivariate Time Series
Common methods for matching multivariate time series such as the Euclid method and PCA method have difficulties in taking advantage of the global shape of time series. The Euclid method is not robust, while the PCA method is not suitable to deal with the small-scale multivariate time series. This paper proposes a pattern matching method based on point distribution for multivariate time series, which is able to characterize the shape of series. Local important points of a multivariate time series and their distribution are used to construct the pattern vector. To match pattern of multivariate time series, the Euclid norm is used to measure the similarity between the pattern vectors. The global shape characteristic is used in the method to match patterns of series. The results of experiments show that it is easy to characterize the shape of multivariate time series with this method, with which various scales can be dealt with in series data.
[1] Zhou Y, Zhao Y, Xie LL, Zhou LM, Chen ZY. Computation and analysis of parameters in phase space reconstruction of epileptic EEG signal. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2007,46(3):5-9 (in Chinese with English abstract).
[2] Wang XY, Luo C, Qiu TS. Nonlinear dynamic research on EEG in HAI experiment. Chinese Journal of Biomedical Engineering, 2007,24(4):408-415 (in Chinese with English abstract).
[3] Singhal A, Seborg DE. Matching patterns from historical data using PCA and distance similarity factors. In: Krogh BH, ed. Proc. of the 2001 American Control Conf. Arlington, 2001,2:1759-1764.
[4] Liu B, Liu J. Multivariate time series prediction via temporal classification. In: Rakesh A, ed. Proc. of the 18th Int'l Conf. on Data Engineering. Washington: IEEE Computer Society, 2002. 268.
[5] Camarinha-Matos LM, Seabra Lopes L, Barata J. Integration and learning in supervision of flexible assembly systems. IEEE Trans. on Robotics and Automation, 1996,12(2):202-219.
[6] Liu HT, Ni ZW, Li JY. An effective algorithm to match similar time series pattern. Journal of Computer-Aided Design & Computer Graphics, 2007,19(16):725-729 (in Chinese with English abstract).
[7] Huang H, Huang K, Hang XS, Xiong FL. Algorithm for fast time-series pattern recovery in a long sequence. Computer Engineering and Applications, 2003,39(21):192-194 (in Chinese with English abstract).
[8] Ge XP, Padhraic S. Deformable Markov model templates for time-series pattern matching. In: Proc. of the 6th ACM SIGKDD Int'l Conf. on Knowledge Discovery and Data Mining. New York: ACM Press, 2000. 81-90.
[9] Pratt KB, Fink E. Search for patterns in compressed time series. Int'l Journal of Image and Graphics, 2002,2(1):89-106.
[10] Wang XH. Study on time series similarity and trend prediction [Ph.D. Thesis]. Tianjin: Tianjin University, 2003 (in Chinese with English abstract).
[11] Dong XL, Gu CK, Wang ZG. Research on shape-based time series similarity measure. Journal of Electronics & Information Technology, 2007,29(5):1228-1231 (in Chinese with English abstract).
[12] Wu SC, Wu GF, Wang W, Yu ZC. A time-sequence similarity matching algorithm for seismological relevant zones. Journal of Software, 2006,17(2):185-192 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/17/185.htm
[13] Kalpakis K, Gada D, Puttagunta V. Distance measures for effective clustering of ARIMA time-series. In: Nick C, ed. Proc. of the IEEE Int'l Conf. on Data Mining. Washington: IEEE Computer Society Press, 2001. 273-280.
[14] Zhang J, Wu SC, Wang W. Research of data mining method on multivariate time series. Computer Engineering and Design, 2006, 27(18):3364-2266 (in Chinese with English abstract).
[15] Singhal A, Seborg DE. Pattern matching in multivariate time series databases using a moving window approach. Ind. Eng. Chem. Res., 2002,41(16):3822-3838.
[16] Krzanowski WJ. Between-Groups comparison of principal components. Journal of the American Statistical Association, 1979, 74(367):703-707.
[17] Singhal A, Seborg DE. Pattern matching in historical batch data using PCA. IEEE Control Systems Magazine, 2002,22(5):53-63.
[18] Guan HS, Jiang QS, Wang SJ. A new similarity measure for clustering multivariate time series. Journal of Computational Information Systems, 2007,3(5):2031-2036.
[19] Huang H, Shi ZZ, Zheng Z. Similarity search based on shape k-d tree for multidimensional time sequences. 2006, 17(10):2048-2056 (in Chinese with English abstract).
[20] Raquel P, Francisco M, Gabriel H. Multivariate time series modeling and classification via hierarchical VAR mixtures. Computational Statistics & Data Analysis, 2006,51(3):1445-1462.
[21] Wang XZ, McGreavy C. Automatic classification for mining process operational data. Industrial & Engineering Chemistry Research, 1998,37(6):2215-2222.