| This dissertation consists of two main parts. One is about state estimation with two types of unconventional measurements and the other is about two types of network-induced state estimation problems.;The two types of unconventional measurements considered are noise-free measurements and set measurements. State estimation with them has numerous real supports. For state estimation with noisy and noise-free measurements, two sequential forms of the batch linear minimum mean-squared error (LMMSE) estimator are obtained to reduce the computational complexity. Inspired by the estimation with quantized measurements developed by Curry [28], under a Gaussian assumption, the minimum mean-squared error (MMSE) state estimator with point measurements and set measurements of any shape is proposed by discretizing continuous set measurements. State estimation under constraints, which are special cases of the more general framework, has some interesting properties. It is found that under certain conditions, although constraints are indispensable in the evolution of the state, update by treating them as measurements is redundant in filtering.;The two types of network-induced estimation problems considered are optimal state estimation in the presence of multiple packet dropouts and optimal distributed estimation fusion with transformed data. An alternative form of LMMSE estimation in the presence of multiple packet dropouts, which can overcome the shortcomings of two existing ones, is proposed first. Then under a Gaussian assumption, the MMSE estimation is also obtained based on a hard decision by comparing the measurements at two consecutive time instants. It is pointed out that if this comparison is legitimate, our simple MMSE solution largely nullifies existing work on this problem. By taking linear transformation of the raw measurements received by each sensor, two optimal distributed fusion algorithms are proposed. In terms of optimality, communication and computational requirements, three nice properties make them attractive. |
