A Piecewise Linear Representation Method of Time Series Based on Feature Points

摘要

In recent years, there has been an explosion of interest in mining time series databases. Representation of the data is the key to efficient and effective solutions. One of the most commonly used representation is piecewise linear approximation, which has been used to support clustering, classification, indexing and association rule mining of time series data. In this paper, we propose a method of piecewise linear representation (PLR) based on feature points. Experiment shows that the method has less fit error to the original time series and has a better ability of adaptation, which can be applied to diverse data environments.