Time Series Pattern Representation Based on Skeleton Points
YE Wen-jun · Journal of Shanghai University of Electric Power · 2010
Time series data have the characteristics of being large in size,high dimensionality and prompt update.It is hard to manipulate for data analysis and mining in its original structure.Using the basic idea of piecewise linear time series for reference,a time series segmentation algorithm is proposed based on skeleton point,which can approximately represent time series by linear composed of skeleton point.This method adopts skeleton point 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 minimized.