Neuro-Fuzzy Equalizers for Mobile Cellular Channels

Book Description

Equalizers are present in all forms of communication systems. Neuro-Fuzzy Equalizers for Mobile Cellular Channels details the modeling of a mobile broadband communication channel and designing of a neuro-fuzzy adaptive equalizer for it. This book focuses on the concept of the simulation of wireless channel equalizers using the adaptive-network-based fuzzy inference system (ANFIS). The book highlights a study of currently existing equalizers for wireless channels. It discusses several techniques for channel equalization, including the type-2 fuzzy adaptive filter (type-2 FAF), compensatory neuro-fuzzy filter (CNFF), and radial basis function (RBF) neural network.

Neuro-Fuzzy Equalizers for Mobile Cellular Channels

starts with a brief introduction to channel equalizers, and the nature of mobile cellular channels with regard to the frequency reuse and the resulting CCI. It considers the many channel models available for mobile cellular channels, establishes the mobile indoor channel as a Rayleigh fading channel, presents the channel equalization problem, and focuses on various equalizers for mobile cellular channels. The book discusses conventional equalizers like LE and DFE using a simple LMS algorithm and transversal equalizers. It also covers channel equalization with neural networks and fuzzy logic, and classifies various equalizers.

This being a fairly new branch of study, the book considers in detail the concept of fuzzy logic controllers in noise cancellation problems and provides the fundamental concepts of neuro-fuzzy. The final chapter offers a recap and explores venues for further research. This book also establishes a common mathematical framework of the equalizers using the RBF model and develops a mathematical model for ultra-wide band (UWB) channels using the channel co-variance matrix (CCM).

  • Introduces the novel concept of the application of adaptive-network-based fuzzy inference system (ANFIS) in the design of wireless channel equalizers

  • Provides model ultra-wide band (UWB) channels using channel co-variance matrix
  • Offers a formulation of a unified radial basis function (RBF) framework for ANFIS-based and fuzzy adaptive filter (FAF) Type II, as well as compensatory neuro-fuzzy equalizers
  • Includes extensive use of MATLAB® as the simulation tool in all the above cases

Table of Contents

  1. Cover Page
  2. Half title
  3. Title Page
  4. Copyright Page
  5. Dedication
  6. List of Figures
  7. List of Tables
  8. Preface
  9. Acknowledgments
  10. List of Abbreviations
  11. 1 Introduction
    1. 1.1 Introduction
    2. 1.2 Need for Equalizers
    3. 1.3 Review of Contemporary Literature
    4. 1.4 Major Contributions of the Book
    5. Further Reading
  12. 2 Overview of Mobile Channels and Equalizers
    1. 2.1 Introduction
    2. 2.2 Mobile Cellular Communication System
      1. 2.2.0.1 Call Initiation
      2. 2.2.0.2 Frequency Reuse
      3. 2.2.1 Co-Channel Interference and System Capacity
      4. 2.2.2 Adjacent Channel Interference
      5. 2.2.3 Digital Modulation Types and Relative Efficiencies
    3. 2.3 Fading Characteristics of Mobile Channels
      1. 2.3.0.1 Tapped Delay Line (TDL) Channel Model
      2. 2.3.0.2 Rayleigh and Ricean Fading Models
    4. 2.4 Channel Models
      1. 2.4.1 Suburban Path Loss Model
      2. 2.4.2 Urban (Alternative Flat Suburban) Path Loss Model
        1. 2.4.2.1 Multipath Delay Profile
        2. 2.4.2.2 RMS Delay Spread
        3. 2.4.2.3 Fade Distribution, K-Factor
        4. 2.4.2.4 Doppler Spectrum
        5. 2.4.2.5 Spatial Characteristics, Coherence Distance
        6. 2.4.2.6 CCI
      3. 2.4.3 Multiple Input Multiple Output (MIMO) Matrix Models
      4. 2.4.4 Modified Stanford University Interim (SUI) Channel Models
      5. 2.4.5 FCC Model
      6. 2.4.6 ITU-R Models
      7. 2.4.7 Free Space Model
      8. 2.4.8 Two-Ray or Dual Slope Model
      9. 2.4.9 Wideband Tapped Delay Line Channel Model
      10. 2.4.10 Conclusions on Model Selection
    5. 2.5 Classification of Equalizers
      1. 2.5.1 A Note on Historical Development
      2. 2.5.2 Classification of Adaptive Equalizers
        1. 2.5.2.1 Nonlinear Equalizers
      3. 2.5.3 Optimal Symbol-by-Symbol Equalizer
      4. 2.5.4 Symbol-by-Symbol Linear Equalizers
      5. 2.5.5 Block FIR Decision Feedback Equalizers
      6. 2.5.6 Symbol-by-Symbol Adaptive Nonlinear Equalizer
        1. 2.5.6.1 RBF Equalizer
        2. 2.5.6.2 Fuzzy Adaptive Equalizer (FAE)
        3. 2.5.6.3 Equalizer Based on Feedforward Neural Networks
        4. 2.5.6.4 A Type-2 Neuro Fuzzy Adaptive Filter
      7. 2.5.7 Equalizer Based on the Nearest Neighbor Rule
    6. 2.6 Conclusion
    7. Further Reading
  13. 3 Neuro-Fuzzy Equalizers for Cellular Channels
    1. 3.1 Introduction to Neuro-Fuzzy Systems
      1. 3.1.1 Fuzzy Systems and Type-1 Fuzzy Sets
      2. 3.1.2 Type-2 Fuzzy Sets
        1. 3.1.2.1 Extension Principle
      3. 3.1.3 Operations on Type-2 Fuzzy Sets
    2. 3.2 Type-2 Fuzzy Adaptive Filter
      1. 3.2.1 TE for Time-Varying Channels
        1. 3.2.1.1 Designing the Type-2 FAF
        2. 3.2.1.2 Simulations
        3. 3.2.1.3 Observations
      2. 3.2.2 DFE for Time-Varying Channel Using a Type-2 FAF
        1. 3.2.2.1 Design of a DFE Based on a Type-2 FAF
        2. 3.2.2.2 Simulations
        3. 3.2.2.3 Observations
      3. 3.2.3 Inferences
    3. 3.3 Adaptation of the Type-2 FAF for the Indoor Environment
      1. 3.3.1 Log–Distance Path Loss Model
      2. 3.3.2 Ericsson Multiple Breakpoint Model
      3. 3.3.3 Attenuation Factor Model
      4. 3.3.4 DFE for an Indoor Mobile Radio Channel
        1. 3.3.4.1 Channel Equation
      5. 3.3.5 Co-Channel Interference Suppression
    4. 3.4 Conclusion
    5. Further Reading
  14. 4 ANFIS-Based Channel Equalizer
    1. 4.1 Introduction
    2. 4.2 Methods of Channel Equalizer Analysis and Design
      1. 4.2.0.1 FIS
      2. 4.2.0.2 ANFIS
      3. 4.2.1 ANFIS Architecture and Functional Layers
        1. 4.2.1.1 Node Functions
    3. 4.3 Mobile Channel Equalizer Based on ANFIS
      1. 4.3.1 Simulation of a Channel Equalizer Using MATLAB®
      2. 4.3.2 Description of the ANFIS-Based Channel Equalizer
      3. 4.3.3 Results of Simulations
      4. 4.3.4 Interpretation of Results and Observations
    4. 4.4 Equalization of UWB Systems Using ANFIS
      1. 4.4.1 Introduction to UWB
      2. 4.4.2 Conventional Channel Models for UWB
        1. 4.4.2.1 The Modified SV/IEEE 802.15.3a Model
        2. 4.4.2.2 The 802.15.4a Model for High Frequencies (4a HF)
        3. 4.4.2.3 The 802.15.4a Model for Low Frequencies (4a LF)
        4. 4.4.2.4 Channel Covariance Matrix (CCM) Formulation
        5. 4.4.2.5 Simulation of an ANFIS Equalizer for UWB Based on CCM
      3. 4.4.3 Conclusions on an ANFIS-Based Equalizer for UWB
    5. 4.5 Conclusion
    6. Further Reading
  15. 5 Compensatory Neuro-Fuzzy Filter (CNFF)
    1. 5.1 Introduction
    2. 5.2 CNFF
      1. 5.2.1 Outline of the CNFF
      2. 5.2.2 Details of Compensatory Operations
    3. 5.3 Structure of CNFFs
      1. 5.3.1 Online Learning Algorithm
        1. 5.3.1.1 Structure Learning Algorithm
        2. 5.3.1.2 Parameter Learning Algorithm
        3. 5.3.1.3 A Digital Communication System with AWGN and CCI
        4. 5.3.1.4 Channel Models and Simulation
      2. 5.3.2 Simulation Results
    4. 5.4 Conclusion
    5. Further Reading
  16. 6 Radial Basis Function Framework
    1. 6.1 Introduction
    2. 6.2 RBF Neural Networks
      1. 6.2.1 Review of Previous Work
        1. 6.2.1.1 Motivation for the Unified Framework
    3. 6.3 Type-2 FAF Equalizer
      1. 6.3.0.1 A Simplified Mathematical Formulation for FAF-II
    4. 6.4 CNFF
      1. 6.4.0.1 A Mathematical Formulation of CNFF
    5. 6.5 ANFIS-Based Channel Equalizer
      1. 6.5.0.1 A Mathematical Formulation of the ANFIS Equalizer
      2. 6.5.0.2 Simulations
    6. 6.6 Conclusion
    7. Further Reading
  17. 7 Modular Approach to Channel Equalization
    1. 7.1 Introduction
    2. 7.2 Nonlinear Channel Models
    3. 7.3 Nonlinear Channel Equalizers
      1. 7.3.1 Nonlinear Equalizers Based on RBF Neural Network
      2. 7.3.2 Nonlinear Equalizers Based on MLPs
      3. 7.3.3 Nonlinear Equalizers Based on FAFs
    4. 7.4 A Modular Approach for Nonlinear Channel Equalizers
    5. 7.5 Simulation Results
    6. 7.6 Conclusion
    7. Further Reading
  18. 8 OFDM and Spatial Diversity
    1. 8.1 Introduction
    2. 8.2 CDMA
      1. 8.2.1 Processing Gain of CDMA Systems
      2. 8.2.2 Generation of CDMA
      3. 8.2.3 CDMA Forward Link Encoding
      4. 8.2.4 CDMA Reverse Link Decoding
    3. 8.3 COFDM
      1. 8.3.1 OFDM Transmission and Reception
        1. 8.3.1.1 Adding a Guard Period to OFDM
    4. 8.4 Conclusion
    5. Further Reading
  19. 9 Conclusion
    1. 9.1 Introduction
    2. 9.2 Major Achievements of the Work
    3. 9.3 Limitations of the Work
    4. 9.4 Scope for Further Research
    5. Further Reading
  20. Index

Product Information

  • Title: Neuro-Fuzzy Equalizers for Mobile Cellular Channels
  • Author(s): K.C. Raveendranathan
  • Release date: November 2017
  • Publisher(s): CRC Press
  • ISBN: 9781351831789