Scribd
Upload
71 views

Lecture Overview AASP

This document provides an introduction to adaptive filtering and high-resolution parameter estimation techniques. It begins with an overview of adaptive filters, including single-channel temporal filtering and multi-channel spatial filtering. It then discusses the necessary mathematical background, including Wirtinger calculus, stochastic processes, and linear algebra. Next, it covers various adaptive filtering algorithms like the LMS, RLS, and linearly constrained algorithms. Finally, it describes high-resolution parameter estimation methods such as MUSIC, ESPRIT, and their multidimensional extensions.

Uploaded by

Henri Stema
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
71 views

Lecture Overview AASP

This document provides an introduction to adaptive filtering and high-resolution parameter estimation techniques. It begins with an overview of adaptive filters, including single-channel temporal filtering and multi-channel spatial filtering. It then discusses the necessary mathematical background, including Wirtinger calculus, stochastic processes, and linear algebra. Next, it covers various adaptive filtering algorithms like the LMS, RLS, and linearly constrained algorithms. Finally, it describes high-resolution parameter estimation methods such as MUSIC, ESPRIT, and their multidimensional extensions.

Uploaded by

Henri Stema
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

1 Introduction

1 Introduction

1.1 Adaptive Filters


- notation
- Schaltbild: programmable filter

1.2 Single channel adaptive equalization (temporal filter)


- FIR linear filter
- matrix notation, convolution matrix
- error signal (vector notation)
- goal for optimization problem
- observations for # of equations (N ), and # of degrees of freedom (M )
* underdetermined case
* unique solution
* overdetermined case
- squared error signal
- time averaged cross-correl. vector
- time averaged correlation matrix
- cost function

1.3 Multi channel adaptive beamforming (spatial filter)


- spatial filter, beamformer output
- matrix notation
- far field approximation
- contribution of the desired wavefront to the BF output
- array steering vector
- optimization task for spatial filtering problem

1
2 Mathematical Background

2 Mathematical Background

2.1 Wirtinger Calculus


- Gradients
- Differentiation with respect to a complex vector
- Quadratic optimization with linear constraints (method of Lagrangian multipliers)

2.2 Discrete-Time Stochastic Processes


- Stationary processes
- Time averages
- Ergodic processes
- Correlation matrices

2.3 Linear algebra


- Eigenvalue decomposition
- Eigenfilter
- Linear system of equations
- Four fundamental subspaces
- Singular value decomposition
- Generalized inverse of a matrix
- Projections
- Low rank modeling

2
3 Adaptive Filters

3 Adaptive Filters

3.1 Linear Optimum Filtering (Wiener Filters)


- Principle of Orthogonality
- Wiener-Hopf equations
- Error-performance surface
- MMSE (minimum mean-squared error)
- Canonical form of the error-performance surface
- MMSE filtering in case of linear models

3.2 Linearly Constrained Minimum Variance Filter


- LCMV beamformer
- Minimum Variance Distortionless Response (MVDR) spectrum: Capon’s method
- LCMV beamforming with multiple linear constraints

3.3 Generalized Sidelobe Canceler

3.4 Iterative Solution of the Normal Equations


- Steepest descent algorithm
- Stability of the algorithm
- Optimization of the step-size

3.5 Least Mean Square (LMS) Algorithm

3.6 Recursive Least Squares (RLS) Algorithm

3
4 High-Resolution Parameter Estimation

4 High-Resolution Parameter Estimation

- Data model (DOA estimation vs. harmonic retrieval)


- Eigendecomposition of the spatial correlation matrix at the receive array
- Subspace estimates
- Estimation of the model order

4.1 Spectral MUSIC


- DOA estimation
* Example: uniform linear array (ULA)
- Root-MUSIC for ULAs
- Periodogram
- MVDR spatial spectrum estimation (review)

4.2 StandardESPRIT
- Selection matrices
- Shift invariance property
- Shift invariance equations: LS, TLS, SLS

4.3 Spatial smoothing

4.4 Forward-backward averaging

4.5 Real-valued subspace estimation

4.6 1-D Unitary ESPRIT


- Transformed invariance equations
- Reliability test

4
4 High-Resolution Parameter Estimation

4.7 Signal Reconstruction


- LS solution
- MVDR / BLUE solution
- Wiener solution (MMSE solution)
- Antenna patterns

4.8 MultidimensionalExtensions
- 2-D MUSIC
- 2-D Unitary ESPRIT
- R-D Unitary ESPRIT

5
5 Tensor-Based Signal Processing

5 Tensor-Based Signal Processing

You might also like