Subject description - AE8B37SSP

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
AE8B37SSP Statistical Signal Processing Extent of teaching:4P+0C
Guarantors:  Roles:PO Language of
teaching:
EN
Teachers:  Completion:Z,ZK
Responsible Department:13137 Credits:6 Semester:L

Anotation:

The course provides fundamentals in three main domains of the statistical signal processing: 1) estimation theory, 2) detection theory, 3) optimal and adaptive filtering. The statistical signal processing is a core theory with many applications ranging from digital communications, audio and video processing, radar and radio navigation, measurement and experiment evaluation, etc.

Study targets:

The course provides theoretical foundations in the three main areas of stochatical signal processing and offers a unifying view of seemingly different approaches.

Content:

Parameter estimates, MVU estimator, Cramer-Rao bound, composite hypotheses, estimator properties. Sufficient statistics. Maximum plausible estimate, EM algorithm. Bayesian estimators (MMSE, MAP). Detection. Hypothesis testing Parametric methods, types and relations. Using the least squares method to design filters. Optimal filtration - Wiener and Kalman filter. Spectral analysis and adptive filtration.

Course outlines:

1. Estimation
1a. MVU estimator, Cramer-Rao lower bound, composite hypothesis, performance criteria 1b. Sufficient statistics 1c. Maximum Likelihood estimator, EM algorithm 1d. Bayesian estimators (MMSE, MAP)
2. Detection
2a. Hypothesis testing (binary, multiple, composite) 2b. Deterministic signals 2c. Random signals
3. Optimal and adaptive filtration
3a. Signal modeling (ARMA, Padé approximation, ...) 3b. Toeplitz equation, Levinson-Durbin recursion 3c. MMSE filters, Wiener filter 3d. Kalman filter 3e. Least Squares, RLS 3f. Steepest descent and stochastic gradient algorithms 3g. Spectrum analysis and estimation

Exercises outline:

The course has only lectures

Literature:

1. Steven Kay: Fundamentals of Statistical Signal Processing - Estimation theory
2. Steven Kay: Fundamentals of Statistical Signal Processing - Detection theory
3. Monson Hayes: Statistical digital signal processing and modeling
4. Ali Sayed: Fundamentals of Adaptive Filtering

Requirements:

None

Webpage:

https://moodle.fel.cvut.cz/course/view.php?id=3821

Keywords:

Estimator, Cramer-Rao bound, composite hypotheses, sufficient statistics,maximum likelihood estimation, EM algorithm. Bayesian estimators, detection, hypothesis testing Parametric methods, optimal filtration, Wiener and Kalman filter, spectral analysis and adptive filtration.

Subject is included into these academic programs:

Program Branch Role Recommended semester
BEOES Open Electronic Systems PO 6


Page updated 21.2.2020 17:51:44, semester: Z,L/2020-1, Z,L/2019-20, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)