Muutke küpsiste eelistusi

E-raamat: Digital Signal Processing with Kernel Methods [Wiley Online]

, , (University of Valencia, Spain),
  • Formaat: 672 pages
  • Sari: IEEE Press
  • Ilmumisaeg: 26-Jan-2018
  • Kirjastus: Wiley-IEEE Press
  • ISBN-10: 1118705815
  • ISBN-13: 9781118705810
Teised raamatud teemal:
  • Wiley Online
  • Hind: 132,16 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
Digital Signal Processing with Kernel MethodsSuurem pilt
  • Formaat: 672 pages
  • Sari: IEEE Press
  • Ilmumisaeg: 26-Jan-2018
  • Kirjastus: Wiley-IEEE Press
  • ISBN-10: 1118705815
  • ISBN-13: 9781118705810
Teised raamatud teemal:
Wiley Online e-raamatudRohkem infot Wiley Online kohta
Raamatu kodulehekülg: https://onlinelibrary.wiley.com/doi/book/10.1002/9781118705810

A realistic and comprehensive review of joint approaches to machine learning and signal processing algorithms, with application to communications, multimedia, and biomedical engineering systems

Digital Signal Processing with Kernel Methods reviews the milestones in the mixing of classical digital signal processing models and advanced kernel machines statistical learning tools. It explains the fundamental concepts from both fields of machine learning and signal processing so that readers can quickly get up to speed in order to begin developing the concepts and application software in their own research.

Digital Signal Processing with Kernel Methods provides a comprehensive overview of kernel methods in signal processing, without restriction to any application field. It also offers example applications and detailed benchmarking experiments with real and synthetic datasets throughout. Readers can find further worked examples with Matlab source code on a website developed by the authors. 

  • Presents the necessary basic ideas from both digital signal processing and machine learning concepts
  • Reviews the state-of-the-art in SVM algorithms for classification and detection problems in the context of signal processing
  • Surveys advances in kernel signal processing beyond SVM algorithms to present other highly relevant kernel methods for digital signal processing

An excellent book for signal processing researchers and practitioners, Digital Signal Processing with Kernel Methods will also appeal to those involved in machine learning and pattern recognition. 

About the Authors xiii
Preface xvii
Acknowledgements xxi
List of Abbreviations xxiii
Part I Fundamentals and Basic Elements 1(208)
1 From Signal Processing to Machine Learning
3(10)
1.1 A New Science is Born: Signal Processing
3(2)
1.1.1 Signal Processing Before Being Coined
3(1)
1.1.2 1948: Birth of the Information Age
4(1)
1.1.3 1950s: Audio Engineering Catalyzes Signal Processing
4(1)
1.2 From Analog to Digital Signal Processing
5(2)
1.2.1 1960s: Digital Signal Processing Begins
5(1)
1.2.2 1970s: Digital Signal Processing Becomes Popular
6(1)
1.2.3 1980s: Silicon Meets Digital Signal Processing
6(1)
1.3 Digital Signal Processing Meets Machine Learning
7(1)
1.3.1 1990s: New Application Areas
7(1)
1.3.2 1990s: Neural Networks, Fuzzy Logic, and Genetic Optimization
7(1)
1.4 Recent Machine Learning in Digital Signal Processing
8(5)
1.4.1 Traditional Signal Assumptions Are No Longer Valid
8(1)
1.4.2 Encoding Prior Knowledge
8(1)
1.4.3 Learning and Knowledge from Data
9(1)
1.4.4 From Machine Learning to Digital Signal Processing
9(1)
1.4.5 From Digital Signal Processing to Machine Learning
10(3)
2 Introduction to Digital Signal Processing
13(84)
2.1 Outline of the Signal Processing Field
13(25)
2.1.1 Fundamentals on Signals and Systems
14(7)
2.1.2 Digital Filtering
21(3)
2.1.3 Spectral Analysis
24(4)
2.1.4 Deconvolution
28(2)
2.1.5 Interpolation
30(1)
2.1.6 System Identification
31(5)
2.1.7 Blind Source Separation
36(2)
2.2 From Time-Frequency to Compressed Sensing
38(10)
2.2.1 Time-Frequency Distributions
38(3)
2.2.2 Wavelet Transforms
41(3)
2.2.3 Sparsity, Compressed Sensing, and Dictionary Learning
44(4)
2.3 Multidimensional Signals and Systems
48(4)
2.3.1 Multidimensional Signals
49(2)
2.3.2 Multidimensional Systems
51(1)
2.4 Spectral Analysis on Manifolds
52(5)
2.4.1 Theoretical Fundamentals
52(2)
2.4.2 Laplacian Matrices
54(3)
2.5 Tutorials and Application Examples
57(37)
2.5.1 Real and Complex Signal Processing and Representations
57(6)
2.5.2 Convolution, Fourier Transform, and Spectrum
63(4)
2.5.3 Continuous-Time Signals and Systems
67(3)
2.5.4 Filtering Cardiac Signals
70(4)
2.5.5 Nonparametric Spectrum Estimation
74(3)
2.5.6 Parametric Spectrum Estimation
77(4)
2.5.7 Source Separation
81(3)
2.5.8 Time-Frequency Representations and Wavelets
84(3)
2.5.9 Examples for Spectral Analysis on Manifolds
87(7)
2.6 Questions and Problems
94(3)
3 Signal Processing Models
97(68)
3.1 Introduction
97(1)
3.2 Vector Spaces, Basis, and Signal Models
98(13)
3.2.1 Basic Operations for Vectors
98(2)
3.2.2 Vector Spaces
100(1)
3.2.3 Hilbert Spaces
101(1)
3.2.4 Signal Models
102(2)
3.2.5 Complex Signal Models
104(1)
3.2.6 Standard Noise Models in DSP
105(2)
3.2.7 The Role of the Cost Function
107(2)
3.2.8 The Role of the Regularizer
109(2)
3.3 Digital Signal Processing Models
111(11)
3.3.1 Sinusoidal Signal Models
112(1)
3.3.2 System Identification Signal Models
113(3)
3.3.3 Sinc Interpolation Models
116(4)
3.3.4 Sparse Deconvolution
120(1)
3.3.5 Array Processing
121(1)
3.4 Tutorials and Application Examples
122(38)
3.4.1 Examples of Noise Models
123(9)
3.4.2 Autoregressive Exogenous System Identification Models
132(6)
3.4.3 Nonlinear System Identification Using Volterra Models
138(2)
3.4.4 Sinusoidal Signal Models
140(4)
3.4.5 Sinc-based Interpolation
144(8)
3.4.6 Sparse Deconvolution
152(5)
3.4.7 Array Processing
157(3)
3.5 Questions and Problems
160(1)
3.A MATLAB simpleInterp Toolbox Structure
161(4)
4 Kernel Functions and Reproducing Kernel Hilbert Spaces
165(44)
4.1 Introduction
165(4)
4.2 Kernel Functions and Mappings
169(5)
4.2.1 Measuring Similarity with Kernels
169(1)
4.2.2 Positive-Definite Kernels
169(1)
4.2.3 Reproducing Kernel in Hilbert Space and Reproducing Property
170(3)
4.2.4 Mercer's Theorem
173(1)
4.3 Kernel Properties
174(5)
4.3.1 Tikhonov's Regularization
175(1)
4.3.2 Representer Theorem and Regularization Properties
176(2)
4.3.3 Basic Operations with Kernels
178(1)
4.4 Constructing Kernel Functions
179(5)
4.4.1 Standard Kernels
179(1)
4.4.2 Properties of Kernels
180(1)
4.4.3 Engineering Signal Processing Kernels
181(3)
4.5 Complex Reproducing Kernel in Hilbert Spaces
184(2)
4.6 Support Vector Machine Elements for Regression and Estimation
186(5)
4.6.1 Support Vector Regression Signal Model and Cost Function
186(1)
4.6.2 Minimizing Functional
187(4)
4.7 Tutorials and Application Examples
191(14)
4.7.1 Kernel Calculations and Kernel Matrices
191(3)
4.7.2 Basic Operations with Kernels
194(3)
4.7.3 Constructing Kernels
197(2)
4.7.4 Complex Kernels
199(3)
4.7.5 Application Example for Support Vector Regression Elements
202(3)
4.8 Concluding Remarks
205(1)
4.9 Questions and Problems
205(4)
Part II Function Approximation and Adaptive Filtering 209(224)
5 A Support Vector Machine Signal Estimation Framework
211(30)
5.1 Introduction
211(2)
5.2 A Framework for Support Vector Machine Signal Estimation
213(3)
5.3 Primal Signal Models for Support Vector Machine Signal Processing
216(11)
5.3.1 Nonparametric Spectrum and System Identification
218(2)
5.3.2 Orthogonal Frequency Division Multiplexing Digital Communications
220(2)
5.3.3 Convolutional Signal Models
222(3)
5.3.4 Array Processing
225(2)
5.4 Tutorials and Application Examples
227(11)
5.4.1 Nonparametric Spectral Analysis with Primal Signal Models
227(1)
5.4.2 System Identification with Primal Signal Model gamma-filter
228(2)
5.4.3 Parametric Spectral Density Estimation with Primal Signal Models
230(1)
5.4.4 Temporal Reference Array Processing with Primal Signal Models
231(2)
5.4.5 Sinc Interpolation with Primal Signal Models
233(1)
5.4.6 Orthogonal Frequency Division Multiplexing with Primal Signal Models
233(5)
5.5 Questions and Problems
238(3)
6 Reproducing Kernel Hilbert Space Models for Signal Processing
241(40)
6.1 Introduction
241(1)
6.2 Reproducing Kernel Hilbert Space Signal Models
242(16)
6.2.1 Kernel Autoregressive Exogenous Identification
244(3)
6.2.2 Kernel Finite Impulse Response and the gamma-filter
247(1)
6.2.3 Kernel Array Processing with Spatial Reference
248(1)
6.2.4 Kernel Semiparametric Regression
249(9)
6.3 Tutorials and Application Examples
258(21)
6.3.1 Nonlinear System Identification with Support Vector Machine-Autoregressive and Moving Average
258(2)
6.3.2 Nonlinear System Identification with the gamma-filter
260(4)
6.3.3 Electric Network Modeling with Semiparametric Regression
264(8)
6.3.4 Promotional Data
272(3)
6.3.5 Spatial and Temporal Antenna Array Kernel Processing
275(4)
6.4 Questions and Problems
279(2)
7 Dual Signal Models for Signal Processing
281(52)
7.1 Introduction
281(1)
7.2 Dual Signal Model Elements
281(2)
7.3 Dual Signal Model Instantiations
283(6)
7.3.1 Dual Signal Model for Nonuniform Signal Interpolation
283(1)
7.3.2 Dual Signal Model for Sparse Signal Deconvolution
284(1)
7.3.3 Spectrally Adapted Mercer Kernels
285(4)
7.4 Tutorials and Application Examples
289(42)
7.4.1 Nonuniform Interpolation with the Dual Signal Model
290(2)
7.4.2 Sparse Deconvolution with the Dual Signal Model
292(2)
7.4.3 Doppler Ultrasound Processing for Fault Detection
294(2)
7.4.4 Spectrally Adapted Mercer Kernels
296(8)
7.4.5 Interpolation of Heart Rate Variability Signals
304(5)
7.4.6 Denoising in Cardiac Motion-Mode Doppler Ultrasound Images
309(7)
7.4.7 Indoor Location from Mobile Devices Measurements
316(6)
7.4.8 Electroanatomical Maps in Cardiac Navigation Systems
322(9)
7.5 Questions and Problems
331(2)
8 Advances in Kernel Regression and Function Approximation
333(54)
8.1 Introduction
333(1)
8.2 Kernel-Based Regression Methods
333(15)
8.2.1 Advances in Support Vector Regression
334(4)
8.2.2 Multi-output Support Vector Regression
338(1)
8.2.3 Kernel Ridge Regression
339(2)
8.2.4 Kernel Signal-to-Noise Regression
341(2)
8.2.5 Semi-supervised Support Vector Regression
343(2)
8.2.6 Model Selection in Kernel Regression Methods
345(3)
8.3 Bayesian Nonparametric Kernel Regression Models
348(12)
8.3.1 Gaussian Process Regression
349(10)
8.3.2 Relevance Vector Machines
359(1)
8.4 Tutorials and Application Examples
360(22)
8.4.1 Comparing Support Vector Regression, Relevance Vector Machines, and Gaussian Process Regression
360(2)
8.4.2 Profile-Dependent Support Vector Regression
362(2)
8.4.3 Multi-output Support Vector Regression
364(2)
8.4.4 Kernel Signal-to-Noise Ratio Regression
366(2)
8.4.5 Semi-supervised Support Vector Regression
368(1)
8.4.6 Bayesian Nonparametric Model
369(1)
8.4.7 Gaussian Process Regression
370(9)
8.4.8 Relevance Vector Machines
379(3)
8.5 Concluding Remarks
382(1)
8.6 Questions and Problems
383(4)
9 Adaptive Kernel Learning for Signal Processing
387(46)
9.1 Introduction
387(1)
9.2 Linear Adaptive Filtering
387(5)
9.2.1 Least Mean Squares Algorithm
388(1)
9.2.2 Recursive Least-Squares Algorithm
389(3)
9.3 Kernel Adaptive Filtering
392(1)
9.4 Kernel Least Mean Squares
392(6)
9.4.1 Derivation of Kernel Least Mean Squares
393(1)
9.4.2 Implementation Challenges and Dual Formulation
394(1)
9.4.3 Example on Prediction of the Mackey-Glass Time Series
395(1)
9.4.4 Practical Kernel Least Mean Squares Algorithms
396(2)
9.5 Kernel Recursive Least Squares
398(8)
9.5.1 Kernel Ridge Regression
398(1)
9.5.2 Derivation of Kernel Recursive Least Squares
399(2)
9.5.3 Prediction of the Mackey-Glass Time Series with Kernel Recursive Least Squares
401(1)
9.5.4 Beyond the Stationary Model
402(3)
9.5.5 Example on Nonlinear Channel Identification and Reconvergence
405(1)
9.6 Explicit Recursivity for Adaptive Kernel Models
406(5)
9.6.1 Recursivity in Hilbert Spaces
406(2)
9.6.2 Recursive Filters in Reproducing Kernel Hilbert Spaces
408(3)
9.7 Online Sparsification with Kernels
411(3)
9.7.1 Sparsity by Construction
411(2)
9.7.2 Sparsity by Pruning
413(1)
9.8 Probabilistic Approaches to Kernel Adaptive Filtering
414(4)
9.8.1 Gaussian Processes and Kernel Ridge Regression
415(1)
9.8.2 Online Recursive Solution for Gaussian Processes Regression
416(1)
9.8.3 Kernel Recursive Least Squares Tracker
417(1)
9.8.4 Probabilistic Kernel Least Mean Squares
418(1)
9.9 Further Reading
418(1)
9.9.1 Selection of Kernel Parameters
418(1)
9.9.2 Multi-Kernel Adaptive Filtering
419(1)
9.9.3 Recursive Filtering in Kernel Hilbert Spaces
419(1)
9.10 Tutorials and Application Examples
419(11)
9.10.1 Kernel Adaptive Filtering Toolbox
420(1)
9.10.2 Prediction of a Respiratory Motion Time Series
421(2)
9.10.3 Online Regression on the KIN4OK Dataset
423(2)
9.10.4 The Mackey-Glass Time Series
425(2)
9.10.5 Explicit Recursivity on Reproducing Kernel in Hilbert Space and Electroencephalogram Prediction
427(1)
9.10.6 Adaptive Antenna Array Processing
428(2)
9.11 Questions and Problems
430(3)
Part III Classification, Detection, and Feature Extraction 433(156)
10 Support Vector Machine and Kernel Classification Algorithms
435(68)
10.1 Introduction
435(1)
10.2 Support Vector Machine and Kernel Classifiers
435(17)
10.2.1 Support Vector Machines
435(6)
10.2.2 Multiclass and Multilabel Support Vector Machines
441(6)
10.2.3 Least-Squares Support Vector Machine
447(1)
10.2.4 Kernel Fisher's Discriminant Analysis
448(4)
10.3 Advances in Kernel-Based Classification
452(25)
10.3.1 Large Margin Filtering
452(2)
10.3.2 Semi-supervised Learning
454(6)
10.3.3 Multiple Kernel Learning
460(2)
10.3.4 Structured-Output Learning
462(6)
10.3.5 Active Learning
468(9)
10.4 Large-Scale Support Vector Machines
477(8)
10.4.1 Large-Scale Support Vector Machine Implementations
477(1)
10.4.2 Random Fourier Features
478(2)
10.4.3 Parallel Support Vector Machine
480(3)
10.4.4 Outlook
483(2)
10.5 Tutorials and Application Examples
485(16)
10.5.1 Examples of Support Vector Machine Classification
485(7)
10.5.2 Example of Least-Squares Support Vector Machine
492(1)
10.5.3 Kernel-Filtering Support Vector Machine for Brain-Computer Interface Signal Classification
493(1)
10.5.4 Example of Laplacian Support Vector Machine
494(4)
10.5.5 Example of Graph-Based Label Propagation
498(1)
10.5.6 Examples of Multiple Kernel Learning
498(3)
10.6 Concluding Remarks
501(1)
10.7 Questions and Problems
502(1)
11 Clustering and Anomaly Detection with Kernels
503(40)
11.1 Introduction
503(3)
11.2 Kernel Clustering
506(8)
11.2.1 Kernelization of the Metric
506(2)
11.2.2 Clustering in Feature Spaces
508(6)
11.3 Domain Description Via Support Vectors
514(4)
11.3.1 Support Vector Domain Description
514(1)
11.3.2 One-Class Support Vector Machine
515(1)
11.3.3 Relationship Between Support Vector Domain Description and Density Estimation
516(1)
11.3.4 Semi-supervised One-Class Classification
517(1)
11.4 Kernel Matched Subspace Detectors
518(4)
11.4.1 Kernel Orthogonal Subspace Projection
518(2)
11.4.2 Kernel Spectral Angle Mapper
520(2)
11.5 Kernel Anomaly Change Detection
522(3)
11.5.1 Linear Anomaly Change Detection Algorithms
522(1)
11.5.2 Kernel Anomaly Change Detection Algorithms
523(2)
11.6 Hypothesis Testing with Kernels
525(4)
11.6.1 Distribution Embeddings
526(1)
11.6.2 Maximum Mean Discrepancy
527(1)
11.6.3 One-Class Support Measure Machine
528(1)
11.7 Tutorials and Application Examples
529(12)
11.7.1 Example on Kernelization of the Metric
529(1)
11.7.2 Example on Kernel k-Means
530(1)
11.7.3 Domain Description Examples
531(3)
11.7.4 Kernel Spectral Angle Mapper and Kernel Orthogonal Subspace Projection Examples
534(2)
11.7.5 Example of Kernel Anomaly Change Detection Algorithms
536(4)
11.7.6 Example on Distribution Embeddings and Maximum Mean Discrepancy
540(1)
11.8 Concluding Remarks
541(1)
11.9 Questions and Problems
542(1)
12 Kernel Feature Extraction in Signal Processing
543(46)
12.1 Introduction
543(2)
12.2 Multivariate Analysis in Reproducing Kernel Hilbert Spaces
545(10)
12.2.1 Problem Statement and Notation
545(1)
12.2.2 Linear Multivariate Analysis
546(3)
12.2.3 Kernel Multivariate Analysis
549(2)
12.2.4 Multivariate Analysis Experiments
551(4)
12.3 Feature Extraction with Kernel Dependence Estimates
555(15)
12.3.1 Feature Extraction Using Hilbert-Schmidt Independence Criterion
556(7)
12.3.2 Blind Source Separation Using Kernels
563(7)
12.4 Extensions for Large-Scale and Semi-supervised Problems
570(5)
12.4.1 Efficiency with the Incomplete Cholesky Decomposition
570(1)
12.4.2 Efficiency with Random Fourier Features
570(1)
12.4.3 Sparse Kernel Feature Extraction
571(2)
12.4.4 Semi-supervised Kernel Feature Extraction
573(2)
12.5 Domain Adaptation with Kernels
575(12)
12.5.1 Kernel Mean Matching
578(1)
12.5.2 Transfer Component Analysis
579(2)
12.5.3 Kernel Manifold Alignment
581(4)
12.5.4 Relations between Domain Adaptation Methods
585(1)
12.5.5 Experimental Comparison between Domain Adaptation Methods
585(2)
12.6 Concluding Remarks
587(1)
12.7 Questions and Problems
588(1)
References 589(42)
Index 631
JOSÉ LUIS ROJO-ÁLVAREZ, PhD, is a Professor in the Department of Signal Theory and Communications at the University Rey Juan Carlos, Fuenlabrada (Madrid) and Center for Computational Simulation, Universidad Politécnica de Madrid, Spain.

MANEL MARTÍNEZ-RAMÓN, PhD, is a Professor in the Department of Electrical and Computer Engineering at the University of New Mexico, Albuquerque, USA.



JORDI MUÑOZ-MARÍ, PhD, is an Associate Professor in the Department of Electronics Engineering at the Universitat de València, Spain.

GUSTAU CAMPS-VALLS, PhD, is an Associate Professor in the Department of Electronics Engineering at the Universitat de València, Spain.
Püsilink: https://www.kriso.ee/db/9781118705810_pe.html
Märksõnad: