Click or drag to resize
Accord.NET (logo)

IHiddenMarkovModelDecode Method

Calculates the most likely sequence of hidden states that produced the given observation sequence.

Namespace:  Accord.Statistics.Models.Markov
Assembly:  Accord.Statistics (in Accord.Statistics.dll) Version: 3.8.0
Syntax
int[] Decode(
	Array observations,
	out double logLikelihood
)
Request Example View Source

Parameters

observations
Type: SystemArray
A sequence of observations.
logLikelihood
Type: SystemDouble
The state optimized probability.

Return Value

Type: Int32
The sequence of states that most likely produced the sequence.
Remarks
Decoding problem. Given the HMM M = (A, B, pi) and the observation sequence O = {o1,o2, ..., oK}, calculate the most likely sequence of hidden states Si that produced this observation sequence O. This can be computed efficiently using the Viterbi algorithm.
See Also