Early Abandon to Accelerate Exact Dynamic Time Warping
Junkui Li, Yuanzhen Wang · 2009
Abstract: Dynamic time warping is one of the important distance measures in similarity search of time series; however, the exact calculation of dynamic time warping has become a bottleneck. We propose an approach, named early abandon dynamic time warping, to accelerate the calculation. The method checks if values of the neighbouring cells in the cumulative distance matrix exceed the tolerance, and if so, it will terminate the calculation of the related cell. We demonstrate the idea of early abandon on dynamic time warping by theoretical analysis, and show the utilities of early abandon dynamic time warping by thorough empirical experiments performed both on synthetic datasets and real datasets. The results show, early abandon dynamic time warping outperforms the dynamic time warping calculation in the light of processing time, and is much better when the tolerance is below the real dynamic time warping distance.