M.E. Electronics & Comm. Engg:Statistical and Adaptive Signal Processing

First Semester

Advanced Digital signal Processing
Advanced Optical Communication Systems
Research Methodology
Digital VLSI Design
Microelectronics Technology

Second Semester

Advanced Solid State Devices
Advanced Communication Techniques
Hardware Description Languages


Third Semester

CDMA and GSM Systems
Seminar
Thesis (starts)


Fourth Semester

Thesis


Statistical and Adaptive Signal Processing

Signals and systems: System theory, stochastic processes Gauss Markov model, Representation of stochastic processes, likelihood and sufficiency, Hypothesis testing, decision criteria, multiple measurements

Estimation theory: Estimation of parameters, random parameters, Bayes Estimates, estimation of non random parameters, properties of estimators, Linear Estimation of signals ?V prediction, filtering, smoothing, correlation cancellation, Power Spectrum Estimation-Parametric and Maximum Entropy Methods

Estimation of waveforms: Linear, MMSE estimation of waveforms, estimation of stationary processes: Wiener filter, Estimation of non stationary processes: Kalman filter, Non linear estimation,

Prediction: Forward and backward linear prediction, Levinson-Durben algorithm, Schurr algorithm, properties of linear prediction error filters, AR- Lattice and ARMA Lattice Ladder filters, Wiener filters for prediction

System modeling and identification: System identification based on FIR (MA), All Pole (AR), Pole Zero (ARMA) system models, Least square linear prediction filter, FIR least squares inverse filter, predictive de convolution, Matrix formulation for least squares estimation: Cholesky decomposition, LDU decomposition, QRD decomposition, Grahm ?V Schmidt orthogonalization, Givens rotation, Householder reflection, SVD,

Adaptive filtering: Least square method for tapped ?V delay line structures. Least Mean Squares (LMS) and Recursive Least Squares (RLS) algorithms and their convergence performance, IIR adaptive filtering and Transform domain adaptive filtering.

Nonstationary Signal Analysis: Time frequency analysis, Cohen class distribution, Wigner-Ville Distribution, Wavelet Analysis.

Applications: Noise and echo cancellation, Parameters estimation in Radar systems , Dynamic target tracking, Application to pattern classification and system identification , channel identification and equalization.