The R Journal: article published in 2019, volume 11:1

Time-Series Clustering in R Using the dtwclust Package
Alexis Sardá-Espinosa , The R Journal (2019) 11:1, pages 22-43.

Abstract Most clustering strategies have not changed considerably since their initial definition. The common improvements are either related to the distance measure used to assess dissimilarity, or the function used to calculate prototypes. Time-series clustering is no exception, with the Dynamic Time Warping distance being particularly popular in that context. This distance is computationally expensive, so many related optimizations have been developed over the years. Since no single clustering algorithm can be said to perform best on all datasets, different strategies must be tested and compared, so a common infrastructure can be advantageous. In this manuscript, a general overview of shape-based time-series clustering is given, including many specifics related to Dynamic Time Warping and associated techniques. At the same time, a description of the dtwclust package for the R statistical software is provided, showcasing how it can be used to evaluate many different time-series clustering procedures.

Received: 2018-04-04; online 2019-08-16, supplementary material, (4.4 KiB)
CRAN packages: dtwclust, flexclust, cluster, TSdist, TSclust, pdc, dtw, proxy, clue, foreach, RcppParallel, doParallel
CRAN Task Views cited directly: TimeSeries
CRAN Task Views implied by cited CRAN packages: TimeSeries, Cluster, Multivariate, HighPerformanceComputing, Environmetrics, Optimization, Robust

This article and supplementary materials are licensed under a Creative Commons Attribution 4.0 International license.

@article{RJ-2019-023,
  author = {Alexis Sardá-Espinosa},
  title = {{Time-Series Clustering in R Using the dtwclust Package}},
  year = {2019},
  journal = {{The R Journal}},
  doi = {10.32614/RJ-2019-023},
  url = {https://doi.org/10.32614/RJ-2019-023},
  pages = {22--43},
  volume = {11},
  number = {1}
}