segclust2d: bivariate segmentation with optional clustering for R

Introduction

segclust2d provides R code for a segmentation method that can be used on all bivariate time-series. The segmentation method can additionally be associated with a clustering algorithm. It was originally intended for ecological segmentation (home-range and behavioural modes) but can be easily applied on other type of time-series. The package also provides tools for analysing outputs from R packages moveHMM and marcher.

Website

Full documentation for segclust2d is available on this website: https://rpatin.github.io/segclust2d/

Three topics are discussed there, and are also available as vignettes in the R package:

• First, preparation of data to be analyzed with segmentation/clustering algorithm, including covariate calculations, subsampling and guidelines to prepare movement data.
• Second, a guide to run the segmentation and segmentation/clustering method, including advise on setting parameters.
• Finally, an overview of the possible outputs that can be generated with the package.

Installation

For the version :

install.packages("segclust2d")

If you want the newest , you can install segclust2d from github with:

# devtools::install_github("rpatin/segclust2d")
install.packages("segclust2d", repos = c('https://rpatin.r-universe.dev', 'https://cloud.r-project.org'))