Detection and Estimation Theory. 3 credits

Catalog description

This course covers the fundamentals of linear estimation and provides an introduction to parameter estimation. We begin with deterministic least squares and proceed to the development of the Wiener and Kalman filters. The main theme is estimation from the innovation process (Gram-Schmidt) using the orthogonality principle. We also discuss more modern subspace-based estimation approaches such as the multistage Wiener filter. In parameter estimation we introduce the maximum-likelihood approach and its implementation through the expectation-maximization algorithm. We demonstrate the workings of the EM algorithm in state space parameter estimation. This course is recommended for students interested in communication theory, control theory, and signal processing. Offered by Electrical & Comp. Engineering . May not be repeated for credit.