[R] fast time series similarity (iSAX, UCR DTW, UCR ED) implementations for R?

Anton Lebedevich mabrek at gmail.com
Wed May 15 08:14:16 CEST 2013


I'm looking for a fast way to group by similarity many (5-10k) long
(2-10k points) time series.
Using PAM on distance matrix obtained via as.dist(1-abs(cor(data)))
produces usable results but it's rather slow and doesn't catch slightly
shifted time series.
DTW implementation from package 'dtw' is orders of magnitude slower even
with global window constraints which renders it unusable for me.

Is there any fast and robust to noise and slight misalignment time
series comparison implementation for R?

There are fast algorithms that are able to deal with large time series

Is there any SAX, UCR DTW, UCR ED implementations for R?

Anton Lebedevich.

More information about the R-help mailing list