Feature-Based Clustering of Longitudinal Trajectories

Identifies clusters of individual longitudinal trajectories. In the spirit of Leffondre et al. (2004), the procedure involves identifying each trajectory to a point in the space of measures. In this context, a measure is a quantity meant to capture a certain characteristic feature of the trajectory. The points in the space of measures are then clustered using a version of the Spectral Clustering algorithm.

traj

The goal of traj is to form clusters of longitudinal trajectories sharing certain distinctive characteristics. The procedure involves computing a set of numerical “measures”, each capturing a certain feature of the trajectory, and using a Spectral Clustering algorithm on those to identify the clusters.

Installation

You can install the development version of traj from GitHub with:

# install.packages("devtools")
devtools::install_github("IcatianTrout/traj")

Example

See the vignette.