1
$\begingroup$

I am writing a thesis comparing some methods of time series classification, part of which is DTW combined with K-NN algorithm. I'd love to know (and write, backed by reliable references) something about the history of this algorithm, but I can't gather up information.

Searching through publications I wrote down first that (1) it was first introduced in 1975 and applied to speech recognition, then in 1994 someone proposed use in time series in general (unfortunately I don't remember where does this info come from, probably 1994 part is from here because this is 2004 paper and it says that A decade ago, DTW was introduced into Data Mining community as a utility for various tasks for time series problems including classification, clustering, and anomaly detection."). I think that somewhere I read also that (2) DTW is known since 1960's, but this paper about DTW states that (3) "In the year 1983, Joseph Kruskal and Mark Liberman introduced a new technique to compare two curves (calculate the distance between them)".

I can't make sense of information I have and don't know where to find more and make sure that everything is correct and consistent. I can't afford spending much time on research about history, because other thesis parts are far more important. What can I do? Does anyone know a good (and preferably just one) source of information about DTW history?

$\endgroup$

1 Answer 1

0
$\begingroup$

You may find this useful http://languagelog.ldc.upenn.edu/myl/KruskalLiberman1983.pdf

The paper that introduced DTW to data mining/AI/ML was [a]

You will also find this very useful https://csdl.ics.hawaii.edu/techreports/2008/08-04/08-04.pdf

eamonn

[a] Berndt, D. & Clifford, J. (1994) Using dynamic time warping to find patterns in time series. AAAI-94 Workshop on Knowledge Discovery in Databases (KDD-94), Seattle, Washington.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.