Time Series Segmentation Based on Series Importance Point

【Abstract】Time series data is characterized as large in data size, high dimensionality and updates continuously. It is hard to manipulate for data analysis and mining in its original structure. Defining a more effective and efficient time series segmentation algorithm is of fundamental importance. This paper proposes a time series segmentation algorithm based on Series Importance Point (SIP), which can approximately represent time series by linear composed of SIP. This method adopts SIP as segmentation point in time series reflecting mostly character of time series. The dimensionality of time series is reduced, and the error of the whole is least.

[1]  Korris Fu-Lai Chung,et al.  On multistage fuzzy neural network modeling , 2000, IEEE Trans. Fuzzy Syst..

[2]  Haixun Wang,et al.  Landmarks: a new model for similarity-based pattern querying in time series databases , 2000, Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073).

[3]  Eamonn J. Keogh,et al.  An Enhanced Representation of Time Series Which Allows Fast and Accurate Classification, Clustering and Relevance Feedback , 1998, KDD.

[4]  C. Su,et al.  Adaptive control of a class of nonlinear systems with a first-order parameterized Sugeno fuzzy approximator , 2001 .

[5]  Ching-Chang Wong,et al.  Generating fuzzy control rules by a clustering algorithm based on a grey relational measure , 1999, FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315).

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

[7]  W. Chu,et al.  Fast retrieval of similar subsequences in long sequence databases , 1999, Proceedings 1999 Workshop on Knowledge and Data Engineering Exchange (KDEX'99) (Cat. No.PR00453).

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

[9]  Changzhou Wang,et al.  Supporting fast search in time series for movement patterns in multiple scales , 1998, CIKM '98.

[10]  Tak-Chung Fu,et al.  Representing financial time series based on data point importance , 2008, Eng. Appl. Artif. Intell..