A New Method for Piecewise Linear Representation of Time Series Data

Abstract In various methods of modeling of time series, the piecewise linear representation has the advantage of being simple, straightforward and supporting dynamic incremental update of time series. This paper proposed a new method of Piecewise Linear Representation of Time Series based on Slope Change Threshold (SCT). Detailed experiments on real datasets from various fields show that STC representation, compared with several other Piecewise Linear Representations, can be easily calculated and has a high degree of fitting.

[1]  Christos Faloutsos,et al.  Fast Time Sequence Indexing for Arbitrary Lp Norms , 2000, VLDB.

[2]  Eamonn J. Keogh,et al.  Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases , 2001, Knowledge and Information Systems.

[3]  Hui Xiao,et al.  A new segmented time warping distance for data mining in time series database , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[4]  Zhan Yan,et al.  Time Series Piecewise Linear Representation Based on Slope Extract Edge Point , 2006 .

[5]  Eugene Fink,et al.  Search for Patterns in Compressed Time Series , 2002, Int. J. Image Graph..