Flexible Dynamic Time Warping for Time Series Classification

Measuring the similarity or distance between two time series sequences is critical for the classification of a set of time series sequences. Given two time series sequences, X and Y, the dynamic time warping (DTW) algorithm can calculate the distance between X and Y. But the DTW algorithm may align some neighboring points in X to the corresponding points which are far apart in Y. It may get the alignment with higher score, but with less representative information. This paper proposes the flexible dynamic time wrapping (FDTW) method for measuring the similarity of two time series sequences. The FDTW algorithm adds an additional score as the reward for the contiguously long one-to-one fragment. As the experimental results show, the DTW and DDTW and FDTW methods outperforms each other in some testing sets. By combining the FDTW, DTW and DDTW methods to form a classifier ensemble with the voting scheme, it has less average error rate than that of each individual method.