ECE 564: Detection and Estimation

Course ID: 366-680. Spring, 2004

Lecture: TR 10:10-11:25, PH 307

Website: courseinfo.cit.cornell.edu/courses/ECE564/

        Instructor:       Lang Tong                                     Graduate Assistant:    TBD
       Office:             384 Rhodes Hall                           Office:
       Tel/FAX:          (607) 255-3900/9072
       E-mail:              ltong@ece.cornell.edu
       Office Hours:   TBD

Course Description

In this course, we consider two fundamental problems in statistical signal processing---detection and estimation---and their applications in digital communications. The first part of the course introduces statistical decision theory, techniques in hypothesis testing, and their performance analysis. The second part of the course deals with parameter estimation theory. For both deterministic and random parameters, we present various optimal estimators and investigate their properties. The third part is an introduction of large deviation analysis for detection and estimation problems. Various applications of detection and estimation theory will be introduced and further explored as part of course projects. Examples include multiuser detection, channel estimation, iterative decoding, and distributed detection and estimation.

Prerequisites: Signal and Systems: ECE 301, ECE 302
Probability and Random Processes ECE 310, ECE411 (preferred).

Textbook

H. V. Poor, An Introduction to Signal Detection and Estimation, 2nd Ed., Springer-Verlag, 1994.

Course Outline

Background and Introduction

Statistical Model and Inference
Statistics and Sufficient Statistics.

Signal Detection

The Bayesian, Minimax and Neymann-Pearson Detectors.
Structures of Discrete-time Detectors.
Sequential detection.
Distributed detection and fusion.
Performance Bounds: Chernoff, Bhattacharyya, and Random Coding Bounds.

Parameter Estimation

MMSE and MAP Estimators. Kalman Filter.
Theory of Point Estimation. Minimum Variance Unbiased Estimation.
Maximum Likelihood Estimation and Least Squares.
Cramer-Rao lower bound and other performance bounds.

Large Deviation and Asymptotic Techniques

Cramer's Theorem.
Gartner-Ellis's Theorem.
Sarnov's Theorem.
Application in Detection and Parameter Estimations.

References on Reserve

S. Kay, Fundamentals of Statistical Signal Processing: Detection Theory, Prentice Hall, 1998.
S. Kay, Fundamentals of Statistical Signal Processing: Estimation Theory, Prentice Hall, 1993.
H.L. Van Trees, Detection, Estimation, and Modulation Theory, vol. I. Wiley, New York, 1968.
L. L. Scharf, Statistical Signal Processing: Detection, Estimation and Time Series Analysis, Addison-Wesley, 1991.
E.L. Lehmann, Theory of Point Estimation, Chapman & Hall, New York, 1991.
E.L. Lehmann, Testing Statistical Hypotheses, Wiley, 1986.
T. Ferguson, Mathematical Statistics: A Decision Theoretical Approach, Academic Press, 1967.
P.J. Bickel and K.A. Doksum, Mathematical Statistics: Basic Ideas and Selected Topics, Prentice Hall, Englewood Cliffs, NJ, 1977.
A. Dembo and O. Zeitouni, Large Deviations Techniques and Applications, 2nd Ed., Springer, 1998.
F. den Hollander, Large Deviations, Fields Institute Monographs, American Mathemathical Society, 2000.
S. Verdu, Multiuser Detection, Cambridge, 1998.
Wozencraft and Jacobs, Principles of Communication Engineering, Waveland Press, 1990.