Scribd
Upload
772 views

Syllabus Adaptive Filter Theory

This document provides an outline for an adaptive signal processing course. The course will cover two main classes of adaptive filter algorithms: the LMS and RLS algorithms. It will develop the necessary mathematical tools like random variables, stochastic processes, and linear algebra. For the LMS algorithm, it will analyze convergence and stability. It will also cover variants like normalized LMS. The course will develop the lattice filter and its adaptive version. For the RLS algorithm, it will formulate the optimal filtering problem and develop the RLS lattice filter through time and order updating of an orthogonal projection operator. The course will present applications of adaptive filters like channel equalization and noise cancellation.

Uploaded by

Rajarshi Bhattacharya
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
772 views

Syllabus Adaptive Filter Theory

This document provides an outline for an adaptive signal processing course. The course will cover two main classes of adaptive filter algorithms: the LMS and RLS algorithms. It will develop the necessary mathematical tools like random variables, stochastic processes, and linear algebra. For the LMS algorithm, it will analyze convergence and stability. It will also cover variants like normalized LMS. The course will develop the lattice filter and its adaptive version. For the RLS algorithm, it will formulate the optimal filtering problem and develop the RLS lattice filter through time and order updating of an orthogonal projection operator. The course will present applications of adaptive filters like channel equalization and noise cancellation.

Uploaded by

Rajarshi Bhattacharya
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

NPTEL Syllabus

Adaptive Signal Processing - Web course


COURSE OUTLINE Adaptive signal processing concerns with processing of signals where the processing parameters are adjusted continuously to suit time varying signal environmental conditions. Central to adaptive signal processing is the concept of adaptive linear combiner, often called adaptive filter where the combiner (filter) coefficients are trained continuously so that the filter can estimate and track an unknown, target signal. The study of adaptive signal processing involves development of various adaptation algorithms and assessing them in terms of convergence rate, computational complexity, robustness against noisy data, hardware complexity, numerical stability etc. This course will develop two main classes of adaptive filter algorithms, namely the LMS and the RLS algorithms. Towards this, it will develop all necessary mathematical tools, in particular, random variables, stochastic processes and correlation structure. The filtering problem is developed in the form of computing orthogonal projection on a signal subspace. To make this treatment self-contained, a rigorous treatment to linear algebra and vector spaces will be presented. For the LMS algorithm, convergence analysis for filter weights (in mean) as well stability analysis for the steady state mean square error will be taken up. Various versions of the LMS transversal forms like the normalized LMS, sign LMS, block LMS etc will be considered. As a counterpart to the transversal filter, the lattice filter/predictor will be developed next, where relation of the lattice filter with autoregressive time series modeling and human speech production process will be highlighted. Adaptive version of the lattice like the so-called gradient adaptive lattice will also be developed. In the case of the RLS algorithm, the optimal filtering problem will be formulated in terms of the pseudo-inverse of a data matrix. The RLS lattice filter will be developed by using time and order updating of an orthogonal projection operator, for which exact time and order update relations of the lattice coefficients will be derived. The course will present several examples of adaptive filter applications like channel equalization, echo cancellation, noise cancellation, interference suppression etc.

NPTEL
http://nptel.iitm.ac.in

Electronics & Communication Engineering


Pre-requisites: 1. First course in Signals and Systems as well as DSP is a prerequisite. 2. Familiarity with linear algebra and random process theory will be helpful. Coordinators: Prof. Mrityunjoy Chakraborty Department of Electronics & Electrical Communication EngineeringIIT Kharagpur

COURSE DETAIL

Module No.

Topic/s

No.of Lectures

Introduction to Adaptive Filters. 1. Adaptive filter structures, issues and examples. 2. Applications of adaptive filters. a. Channel equalization, active noise control. b. Echo cancellation, beamforming.

Discrete time stochastic processes. 1. Re-visiting probability and random variables. 2. Discrete time random processes. 3. Power spectral density - properties. 4. Autocorrelation and covariance structures of discrete time random processes. 5. Eigen-analysis of autocorrelation matrices.

Wiener filter, search methods and the LMS algorithm. 1. Wiener FIR filter (real case). 2. Steepest descent search and the LMS algorithm. 3. Extension of optimal filtering to complex valued input. 4. The Complex LMS algorithm.

Convergence and Stability Analyses. 1. Convergence analysis of the LMS algorithm. 2. Learning curve and mean square error behavior. 3. Weight error correlation matrix. 4. Dynamics of the steady state mean square error (mse). 5. Misadjustment and stability of excess mse.

Variants of the LMS Algorithm. 1. The sign-LMS and the normalized LMS algorithm. 2. Block LMS. 3. Review of circular convolution. 4. Overlap and save method, circular correlation. 5. FFT based implementation of the block LMS Algorithm.

Vector space framework for optimal filtering. 1. Axioms of a vector space, examples, subspace. 2. Linear independence, basis, dimension, direct sum of subspaces. 3. Linear transformation, examples. 4. Range space and null space, rank and nullity of a linear operator. 5. Inner product space, orthogonality, Gram-Schmidt orthogonalization. 6. Orthogonal projection, orthogonal decomposition of subspaces. 7. Vector space of random variables, optimal filtering

as an orthogonal projection computation problem.

The lattice filter and estimator. 1. Forward and backward linear prediction, signal subspace decomposition using forward and backward predictions. 2. Order updating the prediction errors and prediction error variances, basic lattice section. 3. Reflection coefficients, properties, updating predictor coefficients. 4. Lattice filter as a joint process estimator. 5. AR modeling and lattice filters. 6. Gradient adaptive lattice.

RLS lattice filter. 1. Least square (LS) estimation, pseudo-inverse of a data matrix, optimality of LS estimation. 2. Vector space framework for LS estimation. 3. Time and order updating of an orthogonal projection operator. 4. Order updating prediction errors and prediction error power. 5. Time updating PARCOR coefficients.

Total References:

40

1. "Adaptive Filter Theory" by S. Haykin, Prentice Hall, Englewood Cliffs, NJ, 1991 (end Ed.). 2. "Adaptive Filters Theory and Applications", by B. Farhang-Boroujeny, John Wiley and Sons, 1999.
A joint venture by IISc and IITs, funded by MHRD, Govt of India http://nptel.iitm.ac.in

You might also like