Preface |
|
xi | |
Contributors |
|
xv | |
|
Complex-Valued Adaptive Signal Processing |
|
|
1 | (86) |
|
|
1 | (5) |
|
Why Complex-Valued Signal Processing |
|
|
3 | (2) |
|
|
5 | (1) |
|
|
6 | (25) |
|
|
6 | (3) |
|
Efficient Computation of Derivatives in the Complex Domain |
|
|
9 | (8) |
|
Complex-to-Real and Complex-to-Complex Mappings |
|
|
17 | (3) |
|
|
20 | (4) |
|
Statistics of Complex-Valued Random Variables and Random Processes |
|
|
24 | (7) |
|
Optimization in the Complex Domain |
|
|
31 | (9) |
|
Basic Optimization Approaches in Rn |
|
|
31 | (3) |
|
Vector Optimization in Cn |
|
|
34 | (3) |
|
Matrix Optimization in Cn |
|
|
37 | (1) |
|
|
38 | (2) |
|
Widely Linear Adaptive Filtering |
|
|
40 | (7) |
|
Linear and Widely Linear Mean-Square Error Filter |
|
|
41 | (6) |
|
Nonlinear Adaptive Filtering with Multilayer Perceptrons |
|
|
47 | (11) |
|
Choice of Activation Function for the MLP Filter |
|
|
48 | (7) |
|
Derivation of Back-Propagation Updates |
|
|
55 | (3) |
|
Complex Independent Component Analysis |
|
|
58 | (16) |
|
Complex Maximum Likelihood |
|
|
59 | (5) |
|
Complex Maximization of Non-Gaussianity |
|
|
64 | (2) |
|
Mutual Information Minimization: Connections to ML and MN |
|
|
66 | (1) |
|
|
67 | (4) |
|
|
71 | (3) |
|
|
74 | (2) |
|
|
76 | (1) |
|
|
76 | (11) |
|
|
79 | (8) |
|
Robust Estimation Techniques for Complex-Valued Random Vectors |
|
|
87 | (56) |
|
|
87 | (4) |
|
|
88 | (2) |
|
|
90 | (1) |
|
Statistical Characterization of Complex Random Vectors |
|
|
91 | (4) |
|
|
91 | (2) |
|
|
93 | (2) |
|
Complex Elliptically Symmetric (CES) Distributions |
|
|
95 | (7) |
|
|
96 | (2) |
|
|
98 | (1) |
|
Testing the Circularity Assumption |
|
|
99 | (3) |
|
Tools to Compare Estimators |
|
|
102 | (5) |
|
Robustness and Influence Function |
|
|
102 | (4) |
|
Asymptotic Performance of an Estimator |
|
|
106 | (1) |
|
Scatter and Pseudo-Scatter Matrices |
|
|
107 | (7) |
|
Background and Motivation |
|
|
107 | (1) |
|
|
108 | (2) |
|
|
110 | (4) |
|
Array Processing Examples |
|
|
114 | (7) |
|
|
114 | (1) |
|
|
115 | (3) |
|
Estimating the Number of Sources |
|
|
118 | (2) |
|
Subspace DOA Estimation for Noncircular Sources |
|
|
120 | (1) |
|
MVDR Beamformers Based on M-Estimators |
|
|
121 | (7) |
|
The Influence Function Study |
|
|
123 | (5) |
|
|
128 | (9) |
|
The Class of DOGMA Estimators |
|
|
129 | (3) |
|
The Class of GUT Estimators |
|
|
132 | (2) |
|
|
134 | (3) |
|
|
137 | (1) |
|
|
137 | (6) |
|
|
138 | (5) |
|
|
143 | (68) |
|
|
143 | (1) |
|
|
144 | (1) |
|
|
145 | (2) |
|
|
147 | (5) |
|
Basic Properties of Iterative Decoding |
|
|
151 | (1) |
|
Forward-Backward Algorithm |
|
|
152 | (11) |
|
With Intersymbol Interference |
|
|
160 | (3) |
|
Simplified Algorithm: Interference Canceler |
|
|
163 | (5) |
|
|
168 | (5) |
|
|
173 | (9) |
|
|
179 | (3) |
|
|
182 | (13) |
|
|
187 | (3) |
|
|
190 | (2) |
|
EXIT Chart for Interference Canceler |
|
|
192 | (2) |
|
|
194 | (1) |
|
Multichannel and Multiuser Settings |
|
|
195 | (4) |
|
Forward-Backward Equalizer |
|
|
196 | (1) |
|
|
197 | (1) |
|
|
198 | (1) |
|
|
199 | (1) |
|
|
200 | (11) |
|
|
206 | (5) |
|
Subspace Tracking for Signal Processing |
|
|
211 | (60) |
|
|
211 | (2) |
|
|
213 | (6) |
|
Eigenvalue Value Decomposition |
|
|
213 | (1) |
|
|
214 | (1) |
|
Variational Characterization of Eigenvalues/Eigenvectors of Real Symmetric Matrices |
|
|
215 | (1) |
|
Standard Subspace Iterative Computational Techniques |
|
|
216 | (2) |
|
Characterization of the Principal Subspace of a Covariance Matrix from the Minimization of a Mean Square Error |
|
|
218 | (1) |
|
Observation Model and Problem Statement |
|
|
219 | (2) |
|
|
219 | (1) |
|
|
220 | (1) |
|
Preliminary Example: Oja's Neuron |
|
|
221 | (2) |
|
|
223 | (10) |
|
Subspace Power-Based Methods |
|
|
224 | (6) |
|
Projection Approximation-Based Methods |
|
|
230 | (2) |
|
|
232 | (1) |
|
|
233 | (10) |
|
Rayleigh Quotient-Based Methods |
|
|
234 | (1) |
|
Eigenvector Power-Based Methods |
|
|
235 | (5) |
|
Projection Approximation-Based Methods |
|
|
240 | (1) |
|
|
240 | (2) |
|
Particular Case of Second-Order Stationary Data |
|
|
242 | (1) |
|
Convergence and Performance Analysis Issues |
|
|
243 | (13) |
|
A Short Review of the ODE Method |
|
|
244 | (2) |
|
A Short Review of a General Gaussian Approximation Result |
|
|
246 | (2) |
|
Examples of Convergence and Performance Analysis |
|
|
248 | (8) |
|
|
256 | (4) |
|
Direction of Arrival Tracking |
|
|
257 | (1) |
|
Blind Channel Estimation and Equalization |
|
|
258 | (2) |
|
|
260 | (1) |
|
|
260 | (11) |
|
|
266 | (5) |
|
|
271 | (62) |
|
|
272 | (2) |
|
Motivation for Use of Particle Filtering |
|
|
274 | (4) |
|
|
278 | (11) |
|
The Choice of Proposal Distribution and Resampling |
|
|
289 | (6) |
|
Choice of Proposal Distribution |
|
|
290 | (1) |
|
|
291 | (4) |
|
Some Particle Filtering Methods |
|
|
295 | (10) |
|
|
295 | (2) |
|
Auxiliary Particle Filtering |
|
|
297 | (4) |
|
Gaussian Particle Filtering |
|
|
301 | (1) |
|
Comparison of the Methods |
|
|
302 | (3) |
|
Handling Constant Parameters |
|
|
305 | (5) |
|
Kernel-Based Auxiliary Particle Filter |
|
|
306 | (2) |
|
Density-Assisted Particle Filter |
|
|
308 | (2) |
|
|
310 | (4) |
|
|
314 | (2) |
|
|
316 | (4) |
|
|
320 | (3) |
|
Computational Issues and Hardware Implementation |
|
|
323 | (1) |
|
|
324 | (1) |
|
|
325 | (8) |
|
|
327 | (6) |
|
Nonlinear Sequential State Estimation for Solving Pattern-Classification Problems |
|
|
333 | (16) |
|
|
333 | (1) |
|
Back-Propagation and Support Vector Machine-Learing Algorithms: Review |
|
|
334 | (6) |
|
Back-Propagation Learning |
|
|
334 | (3) |
|
|
337 | (3) |
|
Supervised Training Framework of MLPs Using Nonlinear Sequential State Estimation |
|
|
340 | (1) |
|
The Extended Kalman Filter |
|
|
341 | (3) |
|
|
344 | (1) |
|
Experimental Comparison of the Extended Kalman Filtering Algorithm with the Back-Propagation and Support Vector Machine Learning Algorithms |
|
|
344 | (3) |
|
|
347 | (1) |
|
|
348 | (1) |
|
|
348 | (1) |
|
Bandwidth Extension of Telephony Speech |
|
|
349 | (44) |
|
|
349 | (3) |
|
Organization of the Chapter |
|
|
352 | (1) |
|
Nonmodel-Based Algorithms for Bandwidth Extension |
|
|
352 | (2) |
|
Oversampling with Imaging |
|
|
353 | (1) |
|
Application of Nonlinear Characteristics |
|
|
353 | (1) |
|
|
354 | (10) |
|
|
355 | (3) |
|
Parametric Representations of the Spectral Envelope |
|
|
358 | (4) |
|
|
362 | (2) |
|
Model-Based Algorithms for Bandwidth Extension |
|
|
364 | (19) |
|
Generation of the Excitation Signal |
|
|
365 | (4) |
|
Vocal Tract Transfer Function Estimation |
|
|
369 | (14) |
|
Evaluation of Bandwidth Extension Algorithms |
|
|
383 | (5) |
|
Objective Distance Measures |
|
|
383 | (2) |
|
Subjective Distance Measures |
|
|
385 | (3) |
|
|
388 | (1) |
|
|
388 | (5) |
|
|
390 | (3) |
Index |
|
393 | |