MCDMTime-series distance
Dynamic Time Warping
Dynamic Time Warping is a distance metric for comparing time series or sequential data that may vary in length or speed. Introduced by Hideki Sakoe and Seibi Chiba in 1978 for speech recognition, DTW measures the minimal cumulative distance needed to align two sequences using dynamic programming. Unlike fixed-distance metrics, DTW allows flexible time warping, making it ideal for sequences that are similar in shape but offset or scaled differently in time.
Apply with DecisionMindSoonVideoSoon
Read the full method
Members only
Sign inSign in with a free account to read this section.
Sources
- Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26(1), 43-49. DOI: 10.1109/TASSP.1978.1163055 ↗
- Salvador, S., & Chan, P. (2007). FastDTW: Toward accurate dynamic time warping in linear time and space. KDD Explorations, 5(1), 70-86. link ↗