State estimation with quantized measurements in Wireless Sensor Networks

Abstract

The problem of state estimation with quantized measurements is considered. Due to the nonlinearity of the quantizer, estimating the system state is a nonlinear and non-Gaussian estimation problem even if the system is linear and Gaussian. A novel algorithm for approximate minimum mean square error (MMSE) state estimation with quantized measurements is proposed. The algorithm is based on the information extraction from the quantized measurements. Through effective information extraction from the quantized measurements, the true measurement value is reestablished approximatively. Simulation and comparison of the proposed algorithm with the existing methods by simulation of a typical tracking scenario in Wireless Sensor Networks (WSNs) systems are presented. The numerical results show that the tracking algorithm is effective.