viterbi_p {LaMa}

Viterbi algorithm for decoding states of periodically inhomogeneous HMMs

Description

Viterbi algorithm for decoding states of periodically inhomogeneous HMMs

Usage

viterbi_p(delta, Gamma, allprobs, tod)

Arguments

delta

Initial or periodically statioanary distribution of length N

Gamma

Array of transition probability matrices of dimension c(N,N,L), where L is the cycle length.

allprobs

Matrix of state-dependent probabilities/ density values of dimension c(n, N)

tod

Integer valued cyclic variable to index the transition probability matrix.

Value

Vector of decoded states of length n

Examples

delta = c(0.5, 0.5)
beta = matrix(c(-2, 1, -1,
                -2, -1, 1), nrow = 2, byrow = TRUE)
Gamma = tpm_p(1:24, 24, beta)

tod = rep(1:24, 10)
n = length(tod)

allprobs = matrix(runif(2*n), nrow = n, ncol = 2)
states = viterbi_p(delta, Gamma, allprobs, tod)