Liyi Zhang

Blind Equalization in Neural Networks

Theory, Algorithms and Applications
Mitarbeit:Tsinghua University Press

• Gebundenes Buch

Produktbeschreibung

The book begins with an introduction of blind equalization theory and its application in neural networks, then discusses the algorithms in recurrent networks, fuzzy networks and other frequently-studied neural networks. Each algorithm is accompanied by derivation, modeling and simulation, making the book an essential reference for electrical engineers, computer intelligence researchers and neural scientists.

Produktdetails

• Verlag: De Gruyter
• Seitenzahl: 268
• Erscheinungstermin: 18. Dezember 2017
• Englisch
• Abmessung: 246mm x 175mm x 21mm
• Gewicht: 640g
• ISBN-13: 9783110449624
• ISBN-10: 3110449625
• Artikelnr.: 48468245

Autorenporträt

Liyi Zhang, Tianjin University of Commerce, Tianjin, China.

Inhaltsangabe

Table of Content
Chapter 1 Introduction
1.1 Significance of Blind Equalization
1.2 Application of Blind Equalization
1.2.1 Application in Digital TV
1.2.2 Application in CATV System
1.2.3 Application in Smart Antenna
1.2.4 Application in Software Radio
1.2.5 Application in Blind Image Restoration
1.2.6 Application in RFID
1.3 Progress of Neural Network Blind Equalization Algorithm
1.3.1 Feedforward Neural Network Blind Equalization Algorithm
1.3.2 Feedback Neural Network Blind Equalization Algorithm5
1.3.3 Fuzzy Neural Network Blind Equalization Algorithm
1.3.4 Evolutionary Neural Network Blind Equalization Algorithm
1.3.5 Wavelet Neural Network Blind Equalization Algorithm
1.4 Research Background and Structural Arrangements
1.4.1 Background
1.4.2 Structural Arrangement of Book
Chapter 2 Principle of Neural Network Blind Equalization Algorithm
2.1 Basic Principles of Blind Equalization
2.1.1 Concept of Blind Equalization
2.1.2 Structure of Blind Equalizer
2.1.3 Basic Blind Equalization Algorithm
2.1.4 Equalization Criteria of Blind Equalization
2.2 Theory of Neural Networks
2.2.1 Concept of Artificial Neural Networks
2.2.2 Development of Artificial Neural Networks
2.2.3 Features of Artificial Neural Networks
2.2.4 Structure and Classification of Artificial Neural Networks
2.3 Basic Principles of Neural Network Blind Equalization Algorithm
2.3.1 Blind Equalization Algorithm Based on Neural Network Filter
2.3.2 Blind Equalization Algorithm Based on Neural Network Controller
2.3.3 Blind Equalization Algorithm Based on Neural Network Classifier
2.4 Learning Methods of Neural Network Blind Equalization Algorithm
2.4.1 BP Algorithm
2.4.2 Improved BP Algorithm
2.5 Evaluation of Neural Network Blind Equalization Algorithm
2.5.1 Convergence Rate
2.5.2 Computational Complexity
2.5.3 BER Performance
2.5.4 The Ability Tracking Time-varying Channel
2.5.5 Anti-jamming Capability
2.5.6 Convexity of Cost Function
2.5.7 State Residual Error
2.6 Summary
Chapter 3 Research of Feedforward Neural Network Blind Equalization Algorithm
3.1 Basic Principles of Feedforward Neural Networks
3.1.1 Concept of Feedforward Neural Networks
3.1.2 Structure of Feedforward Neural Networks
3.1.3 Features of Feedforward Neural Networks
3.2 Blind Equalization Algorithm Based on Three-layered Feedforward Neural Networks
3.2.1 Model of Three-layered Feedforward Neural Networks
3.2.2 Real Blind Equalization Algorithm Based on Three-layered Feedforward Neural Networks
3.2.3 Complex Blind Equalization Algorithm Based on Three-layered Feedforward Neural Networks
3.3 Blind Equalization Algorithm Based on Multi-layered Feedforward Neural Networks
3.3.1 Concept of Multi-layered Feedforward Neural Networks
3.3.2 Blind Equalization Algorithm Based on Four-layered Feedforward Neural Networks
3.3.3 Blind Equalization Algorithm Based on Five-layered Feedforward Neural Networks
3.4 Blind Equalization Algorithm Based on Momentum Feedforward Neural Networks
3.4.1 Basic Principles of Algorithm
3.4.2 Derivation of Algorithm
3.4.3 Computer Simulations
3.5 Blind Equalization Algorithm Based on Time-varying Momentum Feedforward Neural Networks
3.5.1 Basic Principles of Algorithm
3.5.2 Derivation of Algorithm
3.5.3 Computer Simulations
3.6 Blind Equalization Algorithm Based on Variable Step-size Feedforward Neural Networks
3.6.1 Basic Principles of Algorithm
3.6.2 Derivation of Algorithm
3.6.3 Computer Simulations
3.7 Summary
Appendix I: Hidden Layer Weight Iteration Formula Derivation of Complex Blind Equalization Algorithm Based on Three-layered Feedforward Neural Networks
Chapter 4 Research of Feedback Neural Network Blind Equalization Algorithm
4.1 Basic Principles of Feedback Neural Networks
4.1.1 Concept of Feedback Neural Networks
4.1.2 Structure of Feedback Neural Networks
4.1.3 Features of Feedback Neural Networks
4.2 Blind Equalization Algorithm Based on Bilinear Feedback Neural Networks
4.2.1 Model of Bilinear Feedback Neural Networks
4.2.2 Real Blind Equalization Algorithm Based on Bilinear Feedback Neural Networks
4.2.3 Complex Blind Equalization Algorithm Based on Bilinear Feedback Neural Networks
4.3 Blind Equalization Algorithm Based on Diagonal Recurrent Neural Networks
4.3.1 Model of Diagonal Recurrent Neural Networks
4.3.2 Derivation of Algorithm
4.3.3 Computer Simulations
4.4 Blind Equalization Algorithm Based on Quasi-diagonal Recurrent Neural Networks
4.4.1 Model of Quasi-diagonal Recurrent Neural Networks
4.4.2 Derivation of Algorithm
4.4.3 Computer Simulations
4.5 Blind Equalization Algorithm Based on Variable Step-size Diagonal Recurrent Neural Networks
4.5.1 Basic Principles of Algorithm
4.5.2 Derivation of Algorithm
4.5.3 Computer Simulations
4.6 Blind Equalization Algorithm Based on Variable Step-size Quasi-diagonal Recurrent Neural Networks
4.6.1 Basic Principles of Algorithm
4.6.2 Derivation of Algorithm
4.6.3 Computer Simulations
4.7 Summary
Appendix I: Iteration Formula Derivation of Complex Blind Equalization Algorithm Based on Bilinear Feedback Neural Networks
Chapter 5 Research of Fuzzy Neural Network Blind Equalization Algorithm
5.1 Basic Principles of Fuzzy Neural Networks
5.1.1 Concept of Fuzzy Neural Networks
5.1.2 Structure of Fuzzy Neural Networks
5.1.3 Choosing Fuzzy Membership Functions
5.1.4 Learning Algorithms of Fuzzy Neural Networks
5.1.5 Features of Fuzzy Neural Networks
5.2 Blind Equalization Algorithm Based on Fuzzy Neural Network Filter
5.2.1 Basic Principles of Algorithm
5.2.2 Derivation of Algorithm
5.2.3 Computer Simulations
5.3 Blind Equalization Algorithm Based on Fuzzy Neural Network Controller
5.3.1 Basic Principles of Algorithm
5.3.2 Derivation of Algorithm
5.3.3 Computer Simulations
5.4 Blind Equalization Algorithm Based on Fuzzy Neural Network Classifier
5.4.1 Basic Principles of Algorithm
5.4.2 Derivation of Algorithm
5.4.3 Computer Simulations
5.5 Summary
Appendix I: Types of Fuzzy Membership Functions
Appendix II: Iteration Formula Derivation of Blind Equalization Algorithm Based on Dynamic Recurrent Fuzzy Neural Networks
Chapter 6 Research of Evolutionary Neural Network Blind Equalization Algorithm
6.1 Basic Principles of Evolutionary Neural Networks
6.1.1 Concept of Genetic Algorithm
6.1.2 Development of Genetic Algorithm
6.1.3 Parameters of Genetic Algorithm
6.1.4 Basic Process of Genetic Algorithm
6.1.5 Features of Genetic Algorithm
6.1.6 Combination of Genetic Algorithm and Neural Networks
6.2 Neural Network Weight Optimization Blind Equalization Algorithm Using GA
6.2.1 Basic Principles of Algorithm
6.2.2 Neural Network Weight Optimization Blind Equalization Algorithm Using Binary Coding GA
6.2.3 Neural Network Weight Optimization Blind Equalization Algorithm Using Real Coding GA
6.3 Neural Network Structure Optimization Blind Equalization Algorithm Using GA
6.3.1 Basic Principles of Algorithm
6.3.2 Derivation of Algorithm
6.3.3 Computer Simulations
6.4 Summary
Chapter 7 Research of Wavelet Neural Network Blind Equalization Algorithm
7.1 Basic Principles of Wavelet Neural Networks
7.1.1 Concept of Wavelet Neural Networks
7.1.2 Structure of Wavelet Neural Networks
7.1.3 Features of Wavelet Neural Networks4
7.2 Blind Equalization Algorithm Based on Feedforward Wavelet Neural Networks
7.2.1 Basic Principles of Algorithm
7.2.2 Real Blind Equalization Algorithm Based on Feedforward Wavelet Neural Networks
7.2.3 Complex Blind Equalization Algorithm Based on Feedforward Wavelet Neural Networks
7.3 Blind Equalization Algorithm Based on Feedback Wavelet Neural Networks
7.3.1 Basic Principles of Algorithm3
7.3.2 Real Blind Equalization Algorithm Based on Feedback Neural Networks
7.3.3 Complex Blind Equalization Algorithm Based on Feedback Neural
Networks
7.4 Summary
Chapter 8 Application of Neural Network Blind Equalization Algorithm in Medical Image Processing
8.1 Concept of Image Blind Equalization
8.1.1 Imaging Mechanism and Degradation Process of Medical CT Image
8.1.2 Basic Principles of Medical CT Image Blind Equalization
8.1.3 Quantitative Measurement of Medical Image Blind Equalization
8.2 Medical CT Image Neural Network Blind Equalization Algorithm Based on Zigzag Coding
8.2.1 Basic Principles of Algorithm
8.2.2 teration Formula Derivation of Algorithm
8.2.3 Convergence Analysis of Algorithm
8.2.4 Computer Simulations
8.3 Medical CT Image Neural Network Blind Equalization Algorithm Based on Double Zigzag Coding
8.3.1 Basic Principles of Algorithm
8.3.2 Iteration Formula Derivation of Algorithm
8.3.3 Computer Simulations
8.4 Summary
References