fsMTS: Feature Selection for Multivariate Time Series

Implements feature selection routines for multivariate time series (MTS). The list of implemented algorithms includes: own lags (independent MTS components), distance-based (using external structure, e.g. Pfeifer and Deutsch (1980) <doi:10.2307/1268381>), cross-correlation (see Schelter et al. (2006, ISBN:9783527406234)), graphical LASSO (see Haworth and Cheng (2014) <https://www.gla.ac.uk/media/Media_401739_smxx.pdf>), random forest (see Pavlyuk (2020) "Random Forest Variable Selection for Sparse Vector Autoregressive Models" in Contributions to Statistics, in production), least angle regression (see Gelper and Croux (2008) <https://lirias.kuleuven.be/retrieve/16024>), mutual information (see Schelter et al. (2006, ISBN:9783527406234), Liu et al. (2016) <doi:10.1109/ChiCC.2016.7554480>), and partial spectral coherence (see Davis et al.(2016) <doi:10.1080/10618600.2015.1092978>). In addition, the package implements functions for ensemble feature selection (using feature ranking and majority voting). The package is implemented within Dmitry Pavlyuk's research project No. 1.1.1.2/VIAA/1/16/112 "Spatiotemporal urban traffic modelling using big data".

Version: 0.1.5
Depends: R (≥ 3.6)
Imports: glasso, lars, mpmi, freqdom, randomForestSRC
Suggests: knitr, rmarkdown, sparsevar, plot.matrix, svMisc, MTS
Published: 2020-04-06
Author: Dmitry Pavlyuk ORCID iD [aut, cre]
Maintainer: Dmitry Pavlyuk <Dmitry.Pavlyuk at tsi.lv>
License: GPL-3
NeedsCompilation: no
Materials: NEWS
CRAN checks: fsMTS results

Downloads:

Reference manual: fsMTS.pdf
Vignettes: Feature selection for a simulated data set
Feature selection for a real traffic data set
Package source: fsMTS_0.1.5.tar.gz
Windows binaries: r-devel: fsMTS_0.1.5.zip, r-release: fsMTS_0.1.5.zip, r-oldrel: fsMTS_0.1.5.zip
macOS binaries: r-release: fsMTS_0.1.5.tgz, r-oldrel: fsMTS_0.1.5.tgz
Old sources: fsMTS archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=fsMTS to link to this page.