On estimation of discrete processes under multiplicative and additive noise conditions
Information Sciences: an International Journal
Automatica (Journal of IFAC)
Automatica (Journal of IFAC)
Simultaneous optimum detection and estimation of signals in noise
IEEE Transactions on Information Theory
Optimal recursive estimation with uncertain observation
IEEE Transactions on Information Theory
Recursive Bayesian estimation with uncertain observation (Corresp.)
IEEE Transactions on Information Theory
Discrete optimal linear smoothing for systems with uncertain observations
IEEE Transactions on Information Theory
Hi-index | 22.14 |
Abstract: This paper formulates and analyzes a generalized, finite-state version of the linear-quadratic-Gaussian control problem with interrupted observations. The mechanism that varies observation quality is allowed to be partially observed and subject to control. The new problem formulation is noted to be a special case of a vector version of a partially observed Markov optimization problem. Upper and lower bounds on optimal cost are determined for the case where the mechanism that varies observation quality is completely observed. Numerical approaches for the partially observed Markov optimization problem that are applicable to the newly formulated optimization problem are discussed.