Class MixtureHMM

All Implemented Interfaces:
RandomNumberGenerator, Seedable
Direct Known Subclasses:

public class MixtureHMM extends HiddenMarkovModel
This is the mixture hidden Markov model (HMM). The observations are continuous and follow a continuous distribution.
See Also:
    • W. Zucchini and I. L. MacDonald, "Hidden Markov Models for Time Series: An Introduction Using R," Boca Raton, Florida, CRC Press, 2009.
    • Wikipedia: Hidden Markov model
  • Constructor Details

    • MixtureHMM

      public MixtureHMM(Vector PI, Matrix A, MixtureDistribution dist)
      Constructs a mixture hidden Markov model.
      PI - the initial state probabilities
      A - the state transition probabilities of the homogeneous hidden Markov chain
      dist - the conditional distribution in the hidden Markov model
    • MixtureHMM

      public MixtureHMM(MixtureHMM model)
      Copy constructor.
      model - a HiddenMarkovModel
  • Method Details

    • getDistribution

      public MixtureDistribution getDistribution()
      Gets the distribution in the hidden Markov model.
      the distribution in the hidden Markov model
    • density

      public double density(int state, double observation)
      Description copied from class: HiddenMarkovModel
      Gets the (conditional) probability density/mass of making an observation in a particular state.
      Specified by:
      density in class HiddenMarkovModel
      state - the hidden state label, counting from 1
      observation - the observation value
      the probability density/mass