自适应滤波器原理 第5版 英文版2025|PDF|Epub|mobi|kindle电子书版本百度云盘下载

自适应滤波器原理 第5版 英文版PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

Background and Preview19

1．The Filtering Problem19

2．Linear Optimum Filters22

3．Adaptive Filters22

4．Linear Filter Structures24

5．Approaches to the Development of Linear Adaptive Filters30

6．Adaptive Beamforming31

7．Four Classes of Applications35

8．Historical Notes38

Chapter 1 Stochastic Processes and Models48

1.1 Partial Characterization of a Discrete-Time Stochastic Process48

1.2 Mean Ergodic Theorem50

1.3 Correlation Matrix52

1.4 Correlation Matrix of Sine Wave Plus Noise57

1.5 Stochastic Models58

1.6 Wold Decomposition64

1.7 Asymptotic Stationarity of an Autoregressive Process67

1.8 Yule-Walker Equations69

1.9 Computer Experiment:Autoregressive Process of Order Two70

1.10 Selecting the Model Order78

1.11 Complex Gaussian Processes81

1.12 Power Spectral Density83

1.13 Properties of Power Spectral Density85

1.14 Transmission of a Stationary Process Through a Linear Filter87

1.15 Cramér Spectral Representation for a Stationary Process90

1.16 Power Spectrum Estimation92

1.17 Other Statistical Characteristics of a Stochastic Process95

1.18 Polyspectra96

1.19 Spectral-Correlation Density99

1.20 Summary and Discussion102

Problems103

Chapter 2 WienerFilters108

2.1 Linear Optimum Filtering:Statement of the Problem108

2.2 Principle of Orthogonality110

2.3 Minimum Mean-Square Error114

2.4 Wiener-Hopf Equations116

2.5 Error-Performance Surface118

2.6 Multiple Linear Regression Model122

2.7 Example124

2.8 Linearly Constrained Minimum-Variance Filter129

2.9 Generalized Sidelobe Cancellers134

2.10 Summary and Discussion140

Problems142

Chapter 3 Linear Prediction150

3.1 Forward Linear Prediction150

3.2 Backward Linear Prediction157

3.3 Levinson-Durbin Algorithm162

3.4 Properties of Prediction-Error Filters171

3.5 Schur-Cohn Test180

3.6 Autoregressive Modeling of a Stationary Stochastic Process182

3.7 Cholesky Factorization185

3.8 Lattice Predictors188

3.9 All-Pole,A11-Pass Lattice Filter193

3.10 Joint-Process Estimation195

3.11 Predictive Modeling of Speech199

3.12 Summary and Discussion206

Problems207

Chapter 4 Method of Steepest Descent217

4.1 Basic Idea of the Steepest-Descent Algorithm217

4.2 The Steepest-Descent Algorithm Applied to the Wiener Filter218

4.3 Stability of the Steepest-Descent Algorithm222

4.4 Example227

4.5 The Steepest-Descent Algorithm Viewed as a Deterministic Search Method239

4.6 Virtue and Limitation of the Steepest-Descent Algorithm240

4.7 Summary and Discussion241

Problems242

Chapter 5 Method of Stochastic Gradient Descent246

5.1 Principles of Stochastic Gradient Descent246

5.2 Application 1:Least-Mean-Square（LMS）Algorithm248

5.3 Application 2:Gradient-Adaptive Lattice Filtering Algorithm255

5.4 Other Applications of Stochastic Gradient Descent262

5.5 Summary and Discussion263

Problems264

Chapter 6 The Least-Mean-Square（LMS）Algorithm266

6.1 Signal-Flow Graph266

6.2 Optimality Considerations268

6.3 Applications270

6.4 Statistical Learning Theory290

6.5 Transient Behavior and Convergence Considerations301

6.6 Efficiency304

6.7 Computer Experiment on Adaptive Prediction306

6.8 Computer Experiment on Adaptive Equalization311

6.9 Computer Experiment on a Minimum-Variance Distortionless-Response Beamformer320

6.10 Summary and Discussion324

Problems326

Chapter 7 Normalized Least-Mean-Square（LMS）Algorithm and Its Generalization333

7.1 Normalized LMS Algorithm:The Solution to a Constrained Optimization Problem333

7.2 Stability of the Normalized LMS Algorithm337

7.3 Step-Size Control for Acoustic Echo Cancellation340

7. 4 Geometric Considerations Pertaining to the Convergence Process for Real-Valued Data345

7.5 Affine Projection Adaptive Filters348

7.6 Summary and Discussion352

Problems353

Chapter 8 Block-Adaptive Filters357

8.1 Block-Adaptive Filters:Basic Ideas358

8.2 Fast Block LMS Algorithm362

8.3 Unconstrained Frequency-Domain Adaptive Filters368

8.4 Self-Orthogonalizing Adaptive Filters369

8.5 Computer Experiment on Adaptive Equalization379

8.6 Subband Adaptive Filters385

8.7 Summary and Discussion393

Problems394

Chapter 9 Method of Least-Squares398

9.1 Statement of the Linear Least-Squares Estimation Problem398

9.2 Data Windowing401

9.3 Principle of Orthogonality Revisited402

9.4 Minimum Sum of Error Squares405

9.5 Normal Equations and Linear Least-Squares Filters406

9.6 Time-Average Correlation Matrix Ф409

9.7 Reformulation of the Normal Equations in Terms of Data Matrices411

9.8 Properties of Least-Squares Estimates415

9.9 Minimum-Variance Distortionless Response（MVDR）Spectrum Estimation419

9.10 Regularized MVDR Beamforming422

9.11 Singular-Value Decomposition427

9.12 Pseudoinverse434

9.13 Interpretation of Singular Values and Singular Vectors436

9.14 Minimum-Norm Solution to the Linear Least-Squares Problem437

9.15 Normalized LMS Algorithm Viewed as the Minimum-Norm Solution to an Underdetermined Least-Squares Estimation Problem440

9.16 Summary and Discussion442

Problems443

Chapter 10 The Recursive Least-Squares（RLS）Algorithm449

10.1 Some Preliminaries449

10.2 The Matrix Inversion Lemma453

10.3 The Exponentially Weighted RLS Algorithm454

10.4 Selection of the Regularization Parameter457

10.5 Updated Recursion for the Sum of Weighted Error Squares459

10.6 Example:Single-Weight Adaptive Noise Canceller461

10.7 Statistical Learning Theory462

10.8 Efficiency467

10.9 Computer Experiment on Adaptive Equalization468

10.10 Summary and Discussion471

Problems472

Chapter 11 Robustness474

11.1 Robustness,Adaptation.and Disturbances474

11.2 Robustness:Preliminary Considerations Rooted in H∞ Optimization475

11.3 Robustness of the LMS Algorithm478

11.4 Robustness of the RLS Algorithm483

11.5 Comparative Evaluations of the LMS and RLS Algorithms from the Perspective of Robustness488

11.6 Risk-Sensitive Optimality488

11.7 Trade-Offs Between Robustness and Efficiency490

11.8 Summary and Discussion492

Problems492

Chapter 12 Finite-Precision Effects497

12.1 Quantization Errors498

12.2 Least-Mean-Square（LMS）Algorithm500

12.3 Recursive Least-Squares（RLS）Algorithm509

12.4 Summary and Discussion515

Problems516

Chapter 13 Adaptation in Nonstationary Environments518

13.1 Causes and Consequences of Nonstationarity518

13.2 The System Identification Problem519

13.3 Degree of Nonstationarity522

13.4 Criteria for Tracking Assessment523

13.5 Tracking Performance of the LMS Algorithm525

13.6 Tracking Performance of the RLS Algorithm528

13.7 Comparison of the Tracking Performance of LMS and RLS Algorithms532

13.8 Tuning of Adaptation Parameters536

13.9 Incremental Delta-Bar-Delta（IDBD）Algorithm538

13.10 Autostep Method544

13.11 Computer Experiment:Mixture of Stationary and Nonstationary Environmental Data548

13.12 Summary and Discussion552

Problems553

Chapter 14 Kalman Filters558

14.1 Recursive Minimum Mean-Square Estimation for Scalar Random Variables559

14.2 Statement of the Kalman Filtering Problem562

14.3 The Innovations Process565

14.4 Estimation of the State Using the Innovations Process567

14.5 Filtering573

14.6 Initial Conditions575

14.7 Summary of the Kalman Filter576

14.8 Optimality Criteria for Kalman Filtering577

14.9 KalmanFilter as the Unifying Basis for RLS Algorithms579

14.10 Covariance Filtering Algorithm584

14.11 Information Filtering Algorithm586

14.12 Summary and Discussion589

Problems590

Chapter 15 Square-Root Adaptive Filtering Algorithms594

15.1 Square-Root Kalman Filters594

15.2 Building Square-Root Adaptive Filters on the Two Kalman Filter Variants600

15.3 QRD-RLS Algorithm601

15.4 Adaptive Beamforming609

15.5 Inverse QRD-RLS Algorithm616

15.6 Finite-Precision Effects619

15.7 Summary and Discussion620

Problems621

Chapter 16 Order-Recursive Adaptive Filtering Algorithm625

16.1 Order-Recursive Adaptive Filters Using Least-Squares Estimation:An Overview626

16.2 Adaptive Forward Linear Prediction627

16.3 Adaptive Backward Linear Prediction630

16.4 Conversion Factor633

16.5 Least-Squares Lattice（LSL） Predictor636

16.6 Angle-Normalized Estimation Errors646

16.7 First-Order State-Space Models for Lattice Filtering650

16.8 QR-Decomposition-Based Least-Squares Lattice（QRD-LSL）Filters655

16.9 Fundamental Properties of the QRD-LSL Filter662

16.10 Computer Experiment on Adaptive Equalization667

16.11 Recursive（LSL）Filters Using A Posteriori Estimation Errors672

16.12 Recursive LSL Filters Using A Priori Estimation Errors with Error Feedback675

16.13 Relation Between Recursive LSL and RLS Algorithms680

16.14 Finite-Precision Effects683

16.15 Summary and Discussion685

Problems687

Chapter 17 Blind Deconvolution694

17.1 Overview of Blind Deconvolution694

17.2 Channel Identifiability Using Cyclostationary Statistics699

17.3 Subspace Decomposition for Fractionally Spaced Blind Identification700

17.4 Bussgang Algorithm for Blind Equalization714

17.5 Extension of the Bussgang Algorithm to Complex Baseband Channels731

17.6 Special Cases of the Bussgang Algorithm732

17.7 Fractionally Spaced Bussgang Equalizers736

17.8 Estimation of Unknown Probability Distribution Function of Signal Source741

17.9 Summary and Discussion745

Problems746

Epilogue750

1. Robustness,Efficiency,and Complexity750

2. Kernel-Based Nonlinear Adaptive Filtering753

Appendix A Theory of Complex Variables770

A.1 Cauchy-Riemann Equations770

A.2 Cauchy's Integral Formula772

A.3 Laurent's Series774

A.4 Singularities and Residues776

A.5 Cauchy's Residue Theorem777

A.6 Principle of the Argument778

A.7 Inversion Integral for the z-Transform781

A.8 Parseval's Theorem783

Appendix B Wirtinger Calculus for Computing Complex Gradients785

B.1 Wirtinger Calculus:Scalar Gradients785

B.2 Generalized Wirtinger Calculus:Gradient Vectors788

B.3 Another Approach to Compute Gradient Vectors790

B.4 Expressions for the Partial Derivatives ？f/？z and ？f/？z＊791

Appendix C Method of Lagrange Multipliers792

C.1 Optimization Involving a Single Equality Constraint792

C.2 Optimization Involving Multiple Equality Constraints793

C.3 Optimum Beamformer794

Appendix D Estimation Theory795

D.1 Likelihood Function795

D.2 Cramér-Rao Inequality796

D.3 Properties of Maximum-Likelihood Estimators797

D.4 Conditional Mean Estimator798

Appendix E Eigenanalysis800

E.1 The Eigenvalue Problem800

E.2 Properties of Eigenvalues and Eigenvectors802

E.3 Low-Rank Modeling816

E.4 Eigenfilters820

E.5 Eigenvalue Computations822

Appendix F Langevin Equation of Nonequilibrium Thermodynamics825

F.1 Brownian Motion825

F.2 Langevin Equation825

Appendix G Rotations and Reflections827

G.1 Plane Rotations827

G.2 Two-Sided Jacobi Algorithm829

G.3 Cyclic Jacobi Algorithm835

G.4 Householder Transformation838

G.5 The QR Algorithm841

Appendix H Complex Wishart Distribution848

H.1 Definition848

H.2 The Chi-Square Distribution as a Special Case849

H.3 Properties of the Complex Wishart Distribution850

H.4 Expectation of the Inverse Correlation Matrix Ф-1（n）851

Glossary852

Text Conventions852

Abbreviations855

Principal Symbols858

Bibliography864

Suggested Reading879

Index897