Multi-Variate Non-homogeneous Hidden Markov Model toolbox contains algorithms for modeling multivariate time series with hidden Markov models. The software has been developed on a Linux platform and has been used on Linux, UNIX (Solaris), and MacOS X. A quick-start manual provides basic information required to install and run the software.
Among the capabilities of the toolbox:
Estimation of the model parameters (EM) (both ML and MAP)
Computation of the most likely values of latent variables (Viterbi)
Computation of the log-likelihood
Simulation of the data given the parameters of the model
Model selection via cross-validation
Models implemented:
HMM
Non-homogeneous HMM
Mixture model
Non-homogeneous mixture model
Among the emission distribution types:
Conditionally independent variables or clusters of variables
Multinomial
Tree-dependent (Chow-Liu trees and conditional Chow-Liu forests)
Multivariate Gaussian
The software is distributed under BSD license.
Download (version dated 01/08/2007)
Please read and accept the licensing terms before downloading the software.
A short manual contains a brief description of the software along with a few examples. A full version of the manual will be available in the future. README file contains the complete functionality of the toolbox.
The software is provided as is. Unfortunately, at this time, I have no bandwidth to make modifications or to troubleshoot potential problems.