Method for Similar Pattern Discovery in Time SeriesBased on Neural Network
ZHANG Peng1,ZHANG Jian-Ye2,3,DU Jun1,LI Xue-Ren3
1.Institute of Engineering, Air Force Engineering University, Xi'an 7100382. School of Automation, Northwestern Polytechnical University, Xi'an 7100723. Department of Science Research, Air Force Engineering University, Xi'an 710051
Abstract According to the unsupervised neural network theory of clustering, a method is proposed for similar pattern discovery in time series database. Aiming at the poor capability of the neural network for handling the time change process sequence, the original data are mapped into the feature pattern space by means of fast discrete cosine transform (FDCT) for dimension reduction. The advantages of artificial neural network as similarity measurement model are analyzed and the range query algorithm is presented. The simulation results show that the proposed algorithm has the property of multi-scale, and compared with Euclidean distance and Slop distance, it can reflect similarities of time series under various resolutions.
[1] Agrawal R, Faloutsos C, Swami A. Efficient Similarity Search in Sequence Databases // Proc of the 4th International Conference on Foundations of Data Organization and Algorithms. Chicago, USA, 1993: 69-84 [2] Keogh E. Fast Similarity Search in the Presence of Longitudinal Scaling in Time Series Databases // Proc of the 9th International Conference on Tools with Artificial Intelligence. Newport Beach, USA, 1997: 578-584 [3] Chan K P, Fu A W. Efficient Time Series Matching by Wavelets // Proc of the 15th International Conference on Data Engineering. Sydney, Australia, 1999: 126-133 [4] Keogh E, Chu S, Hart D, et al. An Online Algorithm for Segmenting Time Series // Proc of the IEEE International Conference on Data Mining. San Jose, USA, 2001: 289-296 [5] Jiang Rong, Li Deyi. Similarity Search Based on Shape Representation in Time-Series Data Sets.Journal of Computer Research and Development, 2000, 37(5): 601-608 (in Chinese) (蒋 嵘,李德毅.基于形态表示的时间序列相似性搜索.计算机研究与发展, 2000, 37(5): 601-608) [6] Zheng Binxiang, Li Yugeng, Du Xiuhua. Research on Similarity Mining in Time Series Data Sets.Control and Decision, 2002, 17(5): 527-531 (in Chinese) (郑斌祥,席裕庚,杜秀华.利用反馈的时序模式挖掘算法研究.控制与决策, 2002, 17(5): 527-531) [7] Li Aiguo, Qin Zheng. Dimensionality Reduction and Similarity Search in Large Time Series Databases. Chinese Journal of Computers, 2005, 28(9): 1467-1475 (in Chinese) (李爱国,覃 征.大规模时间序列数据库降维及相似搜索.计算机学报, 2005, 28(9): 1467-1475) [8] Zhang Jianye, Pan Quan, Zhang Peng, et al. Similarity Measuring Method in Time Series Based on Slope.Pattern Recognition and Artificial Intelligence, 2007, 20(2): 271-274 (in Chinese) (张建业,潘 泉,张 鹏,等.基于斜率表示的时间序列相似性度量方法.模式识别与人工智能, 2007, 20(2): 271-274) [9] He Xingui, Liang Yongzhen. Some Theoretical Issues on Procedure Neural Networks. Engineering Science, 2000, 2(12): 40-44 (in Chinese) (何新贵,梁永祯.过程神经元网络的若干理论问题.中国工程科学, 2000, 2(12): 40-44) [10] Beckmann N, Kriegel H P, Schneider R, et al. The R*-Tree: An Efficient and Robust Access Method for Points and Rectangles // Proc of the ACM-SIGMOD International Conference on Management of Data. Atlantic City, USA, 1990: 322-331
2008, Vol. 21 
