Description
This book was written in response to the growing demand for a text that provides a unified treatment of linear and nonlinear complex valued adaptive filters, and methods for the processing of general complex signals (circular and noncircular). It brings together adaptive filtering algorithms for feedforward (transversal) and feedback architectures and the recent developments in the statistics of complex variable, under the powerful frameworks of CR (Wirtinger) calculus and augmented complex statistics. This offers a number of theoretical performance gains, which is illustrated on both stochastic gradient algorithms, such as the augmented complex least mean square (ACLMS), and those based on Kalman filters. This work is supported by a number of simulations using synthetic and real world data, including the noncircular and intermittent radar and wind signals.
Chapter
2 Why Signal Processing in the Complex Domain?
pp.:
34 – 54
3 Adaptive Filtering Architectures
pp.:
54 – 64
4 Complex Nonlinear Activation Functions
pp.:
64 – 76
5 Elements of CR Calculus
pp.:
76 – 90
6 Complex Valued Adaptive Filters
pp.:
90 – 112
7 Adaptive Filters with Feedback
pp.:
112 – 128
8 Filters with an Adaptive Stepsize
pp.:
128 – 140
9 Filters with an Adaptive Amplitude of Nonlinearity
pp.:
140 – 150
10 Data-reusing Algorithms for Complex Valued Adaptive Filters
pp.:
150 – 158
11 Complex Mappings and Möbius Transformations
pp.:
158 – 172
12 Augmented Complex Statistics
pp.:
172 – 190
13 Widely Linear Estimation and Augmented CLMS (ACLMS)
pp.:
190 – 204
14 Duality Between Complex Valued and Real Valued Filters
pp.:
204 – 212
15 Widely Linear Filters with Feedback
pp.:
212 – 228
16 Collaborative Adaptive Filtering
pp.:
228 – 242
17 Adaptive Filtering Based on EMD
pp.:
242 – 254
18 Validation of Complex Representations – Is This Worthwhile?
pp.:
254 – 266
Appendix A: Some Distinctive Properties of Calculus in C
pp.:
266 – 272
Appendix B: Liouville’s Theorem
pp.:
272 – 274
Appendix C: Hypercomplex and Clifford Algebras
pp.:
274 – 278
Appendix D: Real Valued Activation Functions
pp.:
278 – 280
Appendix E: Elementary Transcendental Functions (ETF)
pp.:
280 – 284
Appendix F: The O Notation and Standard Vector and Matrix Differentiation
pp.:
284 – 286
Appendix G: Notions From Learning Theory
pp.:
286 – 290
Appendix H: Notions from Approximation Theory
pp.:
290 – 294
Appendix I: Terminology Used in the Field of Neural Networks
pp.:
294 – 296
Appendix J: Complex Valued Pipelined Recurrent Neural Network (CPRNN)
pp.:
296 – 300
Appendix K: Gradient Adaptive Step Size (GASS) Algorithms in R
pp.:
300 – 304
Appendix L: Derivation of Partial Derivatives from Chapter 8
pp.:
304 – 308
Appendix M: A Posteriori Learning
pp.:
308 – 312
Appendix N: Notions from Stability Theory
pp.:
312 – 314
Appendix O: Linear Relaxation
pp.:
314 – 320
Appendix P: Contraction Mappings, Fixed Point Iteration and Fractals
pp.:
320 – 330
References
pp.:
330 – 342