dtw(method=’multiscale’)

pyts.metrics.dtw(x=None, y=None, dist='square', method='multiscale', options={'resolution': 2, 'radius': 0}, return_cost=False, return_accumulated=False, return_path=False)

Multiscale Dynamic Time Warping (DTW) distance.

This version of DTW builds an adaptive constraint region. First both time series are downsampled, with the sizes of the original times series being divided by resolution. Then the optimal path between the two downsampled time series is computed. Finally this optimal path is projected on the orginal scale and used as the constraint region.

See also

For documentation for the rest of the parameters, see dtw().

Options:

resolution : int (default = 2)

The resolution level.

radius : int (default = 0)

The radius used to expand the constraint region. The optimal path computed at the resolution level is expanded with radius cells to the top, bottom, left and right of every cell belonging to the optimal path. It is computed at the resolution level.

References

[1]	M. Müller, H. Mattes and F. Kurth, “An efficient multiscale approach to audio synchronization”. International Conference on Music Information Retrieval, 6(1), 192-197 (2006).