Course Details
Subject {L-T-P / C} : EC6612 : Bayesian Signal Processing { 3-0-0 / 3}
Subject Nature : Theory
Coordinator : Prof. Upendra Kumar Sahoo
Syllabus
Bayesian Estimation: Batch Bayesian Estimation, Batch Maximum Likelihood Estimation, Batch Minimum Variance Estimation, Sequential Bayesian Estimation Simulation Based Bayesian Methods: Probability Function Estimation, Sampling Theory, Monte Carlo Approach, Importance Sampling, Sequential Importance Sampling State-Space Models for Bayesian Processing: Continuous Time State-Space Models, Sampled Data Spate-Space Models, Discrete Time State-Space Models, Gauss-Markov State-Space model, Innovation Model, State-Space Model Structures Classical Bayesian State-Space Processor: Bayesian Approach to the State-Space, Linear Bayesian Processor, Linearized Bayesian Processor, Extended Bayesian Processor, Iterated-extended Bayesian processor, Practical aspects of classical Bayesian processor Modern Bayesian State-Space Processor: Sigma-point Transformations, Sigma Point Bayesian Processor, Quadrature Bayesian processor, Gaussian Sum Bayesian Processor Particle Based Bayesian State-Space Processors: Bayesian State-space Particle Filters, Importance Proposal Distributions, Resampling, State-Space Particle Filtering Technique, Practical Aspects of Particle Filter Design
Course Objectives
- To convey students about advanced statistical techniques.
Course Outcomes
This course will help one student to design modern signal processing algorithms where PDF of the noise is not known a priori.
Essential Reading
- James V. Candy, Bayesian Signal Processing: Classical, Modern and Particle Filtering Methods, John Wiley & Sons, 2009
- S. M. Kay, Fundamentals of Statistical Signal Processing: Estimation Theory", Vol-I, Prentice Hall PTR, 2009
Supplementary Reading
- T. Kailath, A.H. Sayed, B. Hassib, Linear Estimation, Prentice Hall,2000
- Ali H. Sayed, Fundamentals of Adaptive Filtering, Wiley-IEEE Press 1 edition (June 13, 2003)