LPStimeSeries: Learned Pattern Similarity and Representation for Time Series

Learned Pattern Similarity (LPS) for time series, as described in Baydogan and Runger (2016) <doi:10.1007/s10618-015-0425-y>. Implements an approach to model the dependency structure in time series that generalizes the concept of autoregression to local auto-patterns. Generates a pattern-based representation of time series along with a similarity measure called Learned Pattern Similarity (LPS). Introduces a generalized autoregressive kernel. This package adapts C code from the 'randomForest' package by Andy Liaw and Matthew Wiener, itself based on original Fortran code by Leo Breiman and Adele Cutler.

Version:	1.1-0
Depends:	R (≥ 3.5.0)
Imports:	stats, graphics, grDevices, RColorBrewer
Published:	2026-04-21
DOI:	10.32614/CRAN.package.LPStimeSeries
Author:	Mustafa Gokce Baydogan [aut, cre], Leo Breiman [ctb] (author of original Fortran code adapted in src/regTree.c), Adele Cutler [ctb] (co-author of original Fortran code), Andy Liaw [ctb] (author of 'randomForest' R port adapted here), Matthew Wiener [ctb] (co-author of 'randomForest' R port), Merck & Co., Inc. [cph] (copyright holder of adapted 'randomForest' C code)
Maintainer:	Mustafa Gokce Baydogan <baydoganmustafa at gmail.com>
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation:	yes
Citation:	LPStimeSeries citation info
Materials:	NEWS
CRAN checks:	LPStimeSeries results

Documentation:

Reference manual:

LPStimeSeries.html , LPStimeSeries.pdf

Downloads:

Package source:	LPStimeSeries_1.1-0.tar.gz
Windows binaries:	r-release: LPStimeSeries_1.1-0.zip, r-oldrel: LPStimeSeries_1.1-0.zip
macOS binaries:	r-release (arm64): LPStimeSeries_1.1-0.tgz, r-oldrel (arm64): LPStimeSeries_1.1-0.tgz, r-release (x86_64): LPStimeSeries_1.1-0.tgz, r-oldrel (x86_64): LPStimeSeries_1.1-0.tgz
Old sources:	LPStimeSeries archive

Linking:

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