Abstract The similarity search in time series attracts much attention recently, and the similarity measuring method is one of the most important problems in this area. Aiming at the time series data with high dimension, multiproperty, noise and default, a similarity measuring method based on slope is proposed in this paper. Based on PLR, the method distributes the power among their slope differences so that its physical concept is more clear. The slope distance completely satisfies the basic rules of similarity measuring, and the example shows its validity.
[1] Pavlidis T, Horowitzs S L. Segmentation of Plane Curves. IEEE Trans on Computation, 1974, 23(8): 860870 [2] Lee S, Kwon D, Lee S. Minimum Distance Queries for Time Series Data. Journal of Systems and Software, 2004, 69(1/2): 105113 [3] Goldina D Q, Millsteinb T D, Kutlua A. Bounded Similarity Querying for TimeSeries Data. Information and Computation, 2004, 194(2): 203241 [4] Keogh E J. Efficiently Finding Arbitrarily Scaled Patterns in Massive Time Series Databases // Proc of the 7th European Conference on Principles and Practice of Knowledge Discovery in Databases. CavtatDubrovnik, Croatia, 2003: 253265 [5] Vlachos M, Kollios G, Gunopulos D. Discovering Similar Multidimensional Trajectories // Proc of the 18th International Conference on Data Engineering. San Jose, USA, 2002: 673684 [6] Yi B K, Faloutsos C. Fast Time Sequence Indexing for Arbitrary Lp Norms // Proc of the 26th International Conference on Very Large Databases. Cairo, Egypt, 2000: 385394 [7] Wang Da, Rong Gang. Pattern Distance of Time Series. Journal of Zhejiang University: Engineering Science, 2004, 38(7): 795798 (in Chinese) (王 达,荣 冈.时间序列的模式距离.浙江大学学报:工学版, 2004, 38(7): 795798)
2007, Vol. 20 
