Neuro-Fuzzy and Fuzzy-Neural Applications in Telecommunications

Neuro-Fuzzy and Fuzzy-Neural Applications in Telecommunications

by Peter Stavroulakis (Editor)

Paperback(Softcover reprint of the original 1st ed. 2004)

Use Standard Shipping. For guaranteed delivery by December 24, use Express or Expedited Shipping.

Product Details

ISBN-13: 9783642622816
Publisher: Springer Berlin Heidelberg
Publication date: 10/24/2012
Series: Signals and Communication Technology
Edition description: Softcover reprint of the original 1st ed. 2004
Pages: 339
Product dimensions: 6.10(w) x 9.25(h) x 0.03(d)

Table of Contents

1 Introduction.- 2 Integration of Neural and Fuzzy.- 2.1 Introduction.- 2.2 Hybrid Artificial Intelligent Systems.- 2.2.1 Neuro-Fuzzy Systems.- 2.2.2 Examples [12–18].- References.- 3 Neuro-Fuzzy Applications in Speech Coding and Recognition.- 3.1 Introduction.- 3.2 Soft Computing.- 3.3 FuGeNeSys: A Neuro-Fuzzy Learning Tool for Fuzzy Modeling.- 3.3.1 Genetic Algorithms.- 3.3.2 The Fuzzy Inferential Method Adopted and its Coding.- 3.3.3 Fuzzy Inference Complexity.- 3.4 Conventional Speech Coding and Recognition Techniques.- 3.4.1 Speech Recognition.- 3.4.2 Speech Coding.- 3.5 A Soft Computing-Based Approach in Speech Classification.- 3.6 Neuro-Fuzzy Applications in Speech Coding and Recognition.- 3.6.1 Voiced/Unvoiced Classification.- 3.6.2 Voice Activity Detection.- 3.6.3 Endpoint Detection.- 3.7 Conclusions.- References.- 4 Image/Video Compression Using Neuro-Fuzzy Techniques.- 4.1 Introduction.- 4.1.1 Image Compression.- 4.1.2 Video Compression.- 4.1.3 Fuzzy Theory and Neural Networks.- 4.2 Neuro-Fuzzy Techniques.- 4.2.1 Fuzzy Kohonen Clustering Networks (FKCN).- 4.2.2 Fuzzy-ART Networks.- 4.2.3 Self-Constructing Fuzzy Neural Networks (SCFNN).- 4.3 Neuro-Fuzzy Based Vector Quantization for Image Compression.- 4.3.1 VQ Encoding/Decoding.- 4.3.2 Clustering by SCFNN.- 4.3.3 Experimental Results.- 4.4 Image Transmission by NITF.- 4.4.1 Encoding a VQ Compressed NITF Image.- 4.4.2 Decoding a VQ Compressed NITF Image.- 4.5 Neuro-Fuzzy Based Video Compression.- 4.5.1 System Overview.- 4.5.2 Clustering by SCFNN.- 4.5.3 Labeling Segments.- 4.5.4 Human Object Estimation.- 4.5.5 Human Object Refinement.- 4.5.6 Experimental Results.- References.- 5 A Neuro-Fuzzy System for Source Location and Tracking in Wireless Communications.- 5.1 Introduction.- 5.2 Problem Statement.- 5.2.1 Signal Model.- 5.2.2 The Periodogram as a Motivational Tool for a Neuro-Fuzzy System.- 5.2.3 Fuzzy Logic for Model-Free Function Approximation.- 5.3 The Architecture of the Fuzzy-Neural Network.- 5.3.1 Fuzzification.- 5.3.2 Inference.- 5.3.3 Defuzzification.- 5.4 Design of the Rule Base.- 5.4.1 Initialization.- 5.4.2 Training of the Neuro-Fuzzy System.- 5.4.3 Back-Propagation Algorithm.- 5.4.4 Steps to Follow in the Design of the Rule Base.- 5.5 Simulations.- 5.5.1 Gaussian Fuzzy Sets.- 5.5.2 Triangular Fuzzy Sets.- 5.6 Neuro-Fuzzy System Evaluation.- References.- 6 Fuzzy-Neural Applications in Handoff.- 6.1 Introduction.- 6.2 Application of a Neuro-Fuzzy System to Handoffs in Cellular Communications.- 6.2.1 Introduction.- 6.2.2 Handoff Algorithms.- 6.2.3 Analysis of Handoff Algorithms.- 6.2.4 Neural Encoding Based Neuro-Fuzzy System.- 6.2.5 Pattern Recognition Based Neuro-Fuzzy System.- 6.2.6 Application of a Neuro-Fuzzy Handoff Approach to Various Cellular Systems.- 6.2.7 Conclusion.- References.- 6.3 Handoff Based Quality of Service Control in CDMA Systems Using Neuro-Fuzzy Techniques Bongkarn Homnan, Watit Benjapolakul.- 6.3.1 Introduction.- 6.3.2 Classification of the Problems and Performance Indicators.- 6.3.3 An Overview of IS-95A and IS-95B/cdma2000 SHOs.- 6.3.4 Simple Step Control Algorithm (SSC).- 6.3.5 FIS SHO and FIS&GD SHO.- 6.3.6 System Model, Computer Simulation and Results.- 6.3.7 Evaluation of Handoff as a Quality of Service Controller.- References.- 7 An Application of Neuro-Fuzzy Systems for Access Control in Asynchronous Transfer Mode Networks.- 7.1 Introduction.- 7.2 Traffic Control in ATM Networks.- 7.2.1 Call Admission Control: CAC.- 7.2.2 Usage Parameter Control: UPC.- 7.2.3 Performance Evaluation of Traffic Policing Mechanism.- 7.3 Traffic Source Model and Traffic Policing Mechanism.- 7.3.1 Traffic Source Model used in Simulation Test.- 7.3.2 Structure of Traffic Policing Mechanism for Comparison.- 7.3.3 Structure of Traffic Policing Mechanism Using NFS.- 7.3.4 General Problem Statement.- 7.4 Performance of FLLB Policing Mechanism.- 7.4.1 Effects of Token Pool Size on Policing Performance.- 7.5 Performance of NFS LB Policing Mechanism.- 7.5.1 NN Structure.- 7.5.2 Simulation Results when Tested with Source Model 1.- 7.5.3 Comparison of Processing Time of FL and NFS Controllers.- 7.6 Evaluation of Simulation Results.- References.- Appendix A. Overview of Neural Networks.- A.1 Introduction.- A.2 Learning by Neural Networks.- A.2.1 Multilayer, Feedforward Network Structure.- A.2.2 Training the Feedforward Network: The Delta Rule (DR) and the Generelized Delta Rule (GDR) Back-Propagation.- A.2.3 The Hopfield Approach to Neural Computing.- A.2.4 Unsupervised Classification Learning.- A.3 Examples of Neural Network Structures for PR Applications.- A.3.1 Neural Network Structure.- A.3.2 Learning in Neural Networks.- A.3.3 Reasons to Adapt a Neural Computational Architecture.- References.- Appendix B. Overview of Fuzzy Logic Systems.- B.1 Introduction.- B.2 Overview of Fuzzy Logic.- B.2.1 Fuzzy Rule Generation.- B.2.2 Defuzzification of Fuzzy Logic.- B.3 Examples.- B3.1 Fuzzy Pattern Recognition.- References.- Appendix C. Examples of Fuzzy-Neural and Neuro-Fuzzy Integration.- C.1 Fuzzy-Neural Classification.- C.1.1 Introduction.- C.1.2 Uncertainties with Two-Class Fuzzy-Neural Classification Boundaries.- C.1.3 Multilayer Fuzzy-Neural Classification Networks.- C.2 Fuzzy-Neural Clustering.- C.2.1 Fuzzy Competitive Learning for Fuzzy Clustering.- C.2.2 Adaptive Fuzzy Leader Clustering.- C.3 Fuzzy-Neural Models for Image Processing.- C.3.1 Fuzzy Self Supervised Multilayer Network for Object Extraction.- C.4 Fuzzy-Neural Networks for Speech Recognition.- C.4.1 Introduction.- C.4.2 Problem Definition.- C.4.3 Fuzzy-Neural Approach.- C.5 Fuzzy-Neural Hybrid Systems for System Diagnosis.- C.5.1 Introduction.- C.5.2 Hybrid Systems.- C.6 Neuro-Fuzzy Adaptation of Learning Parameters — An Application in Chromatography.- C.6.1 Introduction.- C.6.2 Fuzzy Training of Neural Networks.- C.6.3 Conclusions.- References.

Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews