Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2018/2019

Adaptive signal processing

The course is not on the list Without time-table
Code Completion Credits Range Language
BAM31ADA Z,ZK 6 2p+2c Czech
Corequisite:
Safety in Electrical Engineering for a master´s degree (BEZM)
Lecturer:
Tutor:
Supervisor:
Department of Circuit Theory
Synopsis:

This course provides a basic discourse on adaptive algorithms for filtering, decorrelation, separation and beamforming. The course explains adaptive algorithms for estimation and prediction, including analysis, implementation and practical applications. Next, it describes the algorithms for adaptive decorrelation and separation of multidimensional signals. Last, the course provides analysis of adaptive beamforming techniques.

Requirements:

The knowledge of basic digital signal processing techniques - primarily the spectral analysis and non-adaptive linear filtering. Ability to use Matlab.

Syllabus of lectures:

1. Block algorithms for estimation

2. Block algorithms for prediction

3. LMS and RLS algorithms and their use for estimation and prediction

4. Convergence of LMS and RLS algorithms

5. Structures for implementation of adaptive filters

6. Use of adaptive algorithms for signal compression

7. Use of adaptive algorithms for noise suppression

8. Kalman filters

9. Grid filters and particle filters

10. Adaptive algorithms for decorrelation of multidimensional signals

11. Adaptive algorithms for separation of multidimensional signals

12. Adaptive beamforming - LCMV and MVDR algorithms

13. Adaptive beamforming - MUSIC algorithm

14. Reserved

Syllabus of tutorials:

1. Implementation of block algorithms for estimation

2. Implementation of block algorithms for prediction

3. Implementation of LMS and RLS algorithms

4. Convergence of LMS and RLS algorithms

5. Comparisoin of structures for implementation of adaptive filters

6. Vocoder

7. Adaptive supression of narrowband interference.

8. Application of Kalman filters

9. Use of grid filters and particle filters

10. Implementation of algorithms for decorrelation of multidimensional signals

11. Implementation of algorithms for separation of multidimensional signals

12. Application of LCMV and MVDR algorithms

13. Application of MUSIC algorithm

14. Reserved

Study Objective:

This course aims to provides the basic knowledge in the area of algorithms for filtering, decorrelation, separation and beamforming.

Study materials:

Sayed, A.H., Adaptive Filters, Wiley-IEEE Press, 2008.

Bellanger, M.B., Adaptive Digital Filters, Marcel Dekker, NY 2001.

Hyvarinen, A, Karhunen, J, Oja, E. Independent Component Analysis, John Wiley & Sons, 2004.

Note:
Further information:
No time-table has been prepared for this course
The course is a part of the following study plans:
Data valid to 2019-04-19
For updated information see http://bilakniha.cvut.cz/en/predmet5435506.html