Learning objectives
Introduce the basic principles of detection and estimation theory.
Course unit content
Discrete representation of deterministic and random signals.
Estimation theory--Statistic model for estimation. Estimation of deterministic parameters: ML criterion. Estimation of stochastic parameters: Bayes criterion. Cramer-Rao inequality. Minimum mean square linear estimation. Prediction and filtering. Wiener filter. Kalman filter.
Detection theory--Statistic model for detection. Bayes criterion, MAP criterion, Minimax criterion, Neyman-Pearson criterion. Detection in the presence of additive white Gaussian noise. Sufficient statistics. Matched filter. Detection in the presence of additive Gaussian colored noise: reversibility theorem. Detection in the presence of random parameters.
Bibliography
Textbooks:
[1] L. Verrazzani, "La teoria della decisione e della stima nelle applicazioni di telecomunicazione". Edizioni ETS, Pisa, 1996.
[2] G. Colavolpe, R. Raheli, Lezioni di Trasmissione numerica, Monte Università Parma editore, 2004.
Complementary Reading:
[1] S. M. Kay, "Fundamentals of statistical signal processing", Vol.I (estimation), Vol.II(detection), Prentice-Hall, 1998.
[2] F. Gini, "Esercizi di teoria dei segnali II". Edizioni ETZ, Pisa, 1996.
[3] J. Cioffi, "Ch. 1: Signal Processing and Detection", http://www.stanford.edu/~cioffi
Assessment methods and criteria
Exams:
The exam is oral, with on-line problem solving and theoretical questions.
Other information
For latest infos please consult:
http://www.tlc.unipr.it/bononi/didattica/TSD/informazioni.html