Statistical Signal Processing: Modelling and Estimation

Modern information systems must handle huge amounts of data having varied natural or technological origins. Automated processing of these increasing signal loads requires the training of specialists capable of formalising the problems encountered. This book supplies a formalised, concise presentation of the basis of statistical signal processing. Equal emphasis is placed on approaches related to signal modelling and to signal estimation. In order to supply the reader with the desirable theoretical fundamentals and to allow him to make progress in the discipline, the results presented here are carefully justified. The representation of random signals in the Fourier domain and their filtering are considered. These tools enable linear prediction theory and related classical filtering techniques to be addressed in a simple way. The spectrum identification problem is presented as a first step toward spectrum estimation, which is studied in non-parametric and parametric frameworks. The later chapters introduce synthetically further advanced techniques that will enable the reader to solve signal processing problems of a general nature. Rather than supplying an exhaustive description of existing techniques, this book is designed for students, scientists and research engineers interested in statistical signal processing and who need to acquire the necessary grounding to address the specific problems with which they may be faced. It also supplies a well-organized introduction to the literature.

Table of Contents:
1. Introduction.- 2. Random Processes.- 3. Power Spectrum of WSS Processes.- 4. Spectral Representation of WSS Processes.- 5. Filtering of WSS Processes.- 6. Important Particular Processes.- 7. Non-linear Transforms of Processes.- 8. Linear Prediction of WSS Processes.- 9. Particular Filtering Techniques.- 10. Rational Spectral Densities.- 11. Spectral Identification of WSS Processes.- 12. Non-parametric Spectral Estimation.- 13. Parametric Spectral Estimation.- 14. Higher Order Statistics.- 15. Bayesian Methods and Simulation Techniques.- 16. Adaptive Estimation.- A. Elements of Measure Theory.- C. Extension of a Linear Operator.- D. Kolmogorov’s Isomorphism and Spectral Representation...- E. Wold’s Decomposition.- F. Dirichlet’s Criterion.- G. Viterbi Algorithm.- H. Minimum-phase Spectral Factorisation of Rational.- I. Compatibility of a Given Data Set with an Autocovariance Set.- 1.1 Elements of Convex Analysis.- 1.2 A Necessary and Sufficient Condition.- J. Levinson’s Algorithm.- K. Maximum Principle.- L. One Step Extension of an Autocovariance Sequence.- N. General Solution to the Trigonometric Moment Problem ..- O. A Central Limit Theorem for the Empirical Mean.- P. Covariance of the Empirical Autocovariance Coefficients ...- Q. A Central Limit Theorem for Empirical Autocovariances ..- R. Distribution of the Periodogram for a White Noise.- S. Periodogram of a Linear Process.- T. Variance of the Periodogram.- U. A Strong Law of Large Numbers (I).- V. A Strong Law of Large Numbers (II).- W. Phase-amplitude Relationship for Minimum-phase Causal Filters.- X. Convergence of the Metropolis-Hastings Algorithm.- Y. Convergence of the Gibbs Algorithm.- Z. Asymptotic Variance of the LMS Algorithm.- References.