Trend-based symbolic aggregate approximation for time series representation

Due to high dimensionality and large volume of big time series data, the existing analysis technologies are poor for processing the raw data. The symbolic aggregate approximation (SAX) is one of the most powerful tools to deal with big time series data via reducing dimensionality. However, the SAX is a mean value-based approach that cannot analyze significant trend features of time series. In this paper, trend-based symbolic aggregate approximation (TSAX) is proposed to handle this problem by adding trend indicators to each segment. The proposed method can depict the trend characteristics precisely without losing the merits such as symbolic nature of the SAX. Moreover, it has a more reasonable distance measure for the data processing task. The utility of the proposed approach is demonstrated by experiment of predefined pattern detection on different data sets.