Coursepacks should be available at OSU bookstore in the near
future. For pricing, check OSU
This course will cover two fundamental problems: estimation and
detection. For both, Bayesian and non Bayesian estimation will be
discussed. Optimal estimation schemes, performance evaluation
metrics, and performance bounds such as the Cramer-Rao lower bound
will be presented. Filtering will be revisited in the context of
linear estimation. Optimal detection schemes for simple hypotheses,
uniformly most powerful test, Neyman-Pearson theorem, minimax,
likelihood ratio test (LRT) and the generalized LRT will be
discussed. Special focus on Gaussian models will be given in both
estimation and detection.
ECE 353 (Intro. to Probability and Random Processes) or equivalent.
You are expected to be familiar with concepts such as: random
variables, mean, variance, probability density function, or
cumulative distribution function.
Coursepack: EECS564 Detection, Estimation and Filtering by
Prof. Alfred Hero (feedback on the notes would be greatly
Fundamentals of Statistical Processing, Volume I: Estimation
Theory (Prentice Hall Signal Processing Series) ISBN-10:
Fundamentals of Statistical Signal Processing, Volume 2:
Detection Theory (Prentice Hall Signal Processing Series)
Detection, Estimation, and Modulation Theory, Part I
(Paperback) by Harry L. Van Trees ISBN-10: 0471095176
Estimation: linear and nonlinear minimum mean squared error
estimation, and other strategies.
Linear filtering: Wiener filtering, the orthogonality
Detection: simple, composite, binary and multiple hypotheses.
Neyman-Pearson and Bayesian approaches.