Title :
Risk-sensitive maximum likelihood sequence estimation
Author :
Elliott, R.J. ; Moore, J.B. ; Dey, S.
Author_Institution :
Dept. of Math., Alberta Univ., Edmonton, Alta., Canada
fDate :
9/1/1996 12:00:00 AM
Abstract :
In this brief, we consider risk-sensitive Maximum Likelihood sequence estimation for hidden Markov models with finite-discrete states. An algorithm is proposed which is essentially a risk-sensitive variation of the Viterbi algorithm. Simulation studies show that the risk-sensitive algorithm is more robust to uncertainties in the transition probability matrix of the Markov chain. Similar estimation results are also obtained for continuous-range state models
Keywords :
feedback; hidden Markov models; maximum likelihood estimation; optimal control; Markov chain; Viterbi algorithm; continuous-range state models; feedback; finite-discrete states; hidden Markov models; optimal control; risk-sensitive maximum likelihood sequence estimation; transition probability matrix; Cost function; Hidden Markov models; Maximum likelihood estimation; Modeling; Noise robustness; Nonlinear filters; Recursive estimation; State estimation; Uncertainty; Viterbi algorithm;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
