1.1 - 8.10 - DTW (ML Engine) - Teradata Vantage

Teradata Vantage™ - Machine Learning Engine Analytic Function Reference

Teradata Vantage
Release Number
October 2019
Content Type
Programming Reference
Publication ID
English (United States)
Last Update

The DTW function performs dynamic time warping (DTW), which measures the similarity (warp distance) between two time series that vary in time or speed. You can use DTW to analyze any data that can be represented linearly—for example, video, audio, and graphics.

For example:

  • In two videos, DTW can detect similarities in walking patterns, even if in one video the person is walking slowly and in another, the same person is walking fast.
  • In audio, DTW can detect similarities in speech speeds (useful in speech recognition applications).

Given an input table, a template table, and a mapping table, DTW compares each time series in the input table to the corresponding time series in the template table. The correspondence is defined by the mapping table.

How Machine Learning Engine function DTW works

For more information, see FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space. Stan Salvador and Philip Chan. KDD Workshop on Mining Temporal and Sequential Data, pp. 70-80, 2004 (http://cs.fit.edu/~pkc/papers/tdm04.pdf)