Exact Dynamic Time Warping calculation for weak sparse time series

Abstract

The Dynamic Time Warping (DTW) technique is widely used in time series data mining. However, it should be pointed out that the calculation complexity of DTW is very high. In this paper, we propose an accurate and fast DTW calculation algorithm on weak sparse time series (WSTS). The algorithm takes the advantage of the weak sparse property, and it shows a remarkable time saving in DTW calculation. In addition, it should be emphasized that this algorithm for DTW calculation is an accurate one, which is one of the main contributions of this paper. The mathematical proof is also given to prove the accuracy of this algorithm. Several examples with different practical prospects are given to show the effectiveness of the proposed accurate and fast DTW calculation algorithm.