Warped K-means (WKM) is a segmentation-based partitional clustering procedure that minimizes the Sum of Squared Error criterion, while imposing a hard sequentiality constraint in the classification step. The algorithm is tailored to simplify trajectories of n-dimensional objects, and it has interesting properties. In particular, it is much faster than conventional K-means algorithms and at the same time it provides better solutions for sequentially-distributed data.
This software is free for scientific use (MIT license). The software must not be distributed without prior permission of the authors. Please contact us if you are planning to use the software for commercial purposes. The authors are not responsible for any implication derived from the use of this software.
If you use the code (or a derivation thereof) in your work, please cite as
(cc) 2019 Luis A. Leiva, Enrique Vidal