Wavelets to Enhance Computational Intelligence

Preface.
Acknowledgment.
About the Authors.
1. Introduction.
2. Introduction to Wavelet Analysis.
2.1 Introduction.
2.2 Basic Concept of Wavelets and Wavelet Analysis.
2.3 Mathematical Foundations.
2.4 The Discrete Wavelet Transform (DWT).
2.5 Multi-resolution Analysis.
2.6 Wavelet Bases.
2.7 Computing the DWT.
3. Feature Extraction for Traffic Incident Detection Using Wavelet Transform and Linear Discriminant Analysis.
3.1 Introduction.
3.2 Incident Detection Algorithms.
3.3 Discrete Wavelet Transform (DWT) of Traffic Signals.
3.4 Linear Discriminant Analysis (LDA).
3.5 Data Acquisition.
3.6 Results.
4. Adaptive Conjugate Neural Network-Wavelet Model for Traffic Incident Detection.
4.1 Introduction.
4.2 Improving Traffic Incident Detection.
4.3 Adaptive Conjugate Gradient Neural Network Model.
4.4 Incident Detection Results Using Various Approaches.
4.5 Effect of Data Filtering Using DWT.
4.6 Relative Contribution of DWT and LDA for Feature Extraction.
4.7 Effects of Freeway Geometry on Incident Detection.
4.8 Conclusion.
5. Enhancing Fuzzy Neural Network Algorithms Using Neural Networks.
5.1 Introduction.
5.2 Discrete Wavelet Transform.
5.3 Architecture.
5.4 Training of the Network.
5.5 Filtering of the Traffic Data Using DWT.
5.6 Incident Detection Results.
6. Fuzzy-Wavelet Radial Basis Function Neural Network Model for Freeway Incident Detection.
6.1 Introduction.
6.2 A New Traffic Incident Detection Methodology.
6.3 Selection of Type and Number of Traffic Data.
6.4 Wavelet-Based De-noising.
6.5 Fuzzy Data Clustering.
6.6 Radial Basis Function Neural Network Classifier.
6.7 Fuzzy-Wavelet RBFNN Model for Incident Detection.
6.8 Example.
6.9 Conclusion.
7. Comparison of Fuzzy-Wavelet RBFNN Freeway Incident Detection Model with California Algorithm.
7.1 Introduction.
7.2 California Algorithm #8.
7.3 Evaluation of the Model.
7.4 Concluding Remarks.
8. Incident Detection Algorithm Using Wavelet Energy Representation

Hojjat Adeli is currently Professor of Civil and Environmental Engineering and Geodetic Science and Lichtenstein Professor in Infrastructure Engineering at The Ohio State University. A contributor to 70 Different scholarly journals, he has authored over 400 research and scientific publications in diverse areas of engineering, computer science, and applied mathematics since he received his PhD from Stanford University in 1976 at the age of 26. He has authored/co-authored nine pioneering books. His recent books are: Machine Learning - Neural Networks, Genetic, Algorithms, and Fuzzy Systems, John Wiley & Sons, 1995; Neurocomputing for Design Automation, CRC Press, 1998; Distributed Computer-Aided Engineering, CRC Press, 1999; High Performance computing in Structural Engineering, CRC Press, 1999; and Control, Optimization and Smart Structures - High-Performance bridges and Buildings of the Future, John Wiley & Sons, 1999. He has also edited twelve books including Intelligent Information Systems, IEEE computer Society, 1997. He is the Editor-in-Chiffon two research journals: Computer-Aided Civil and Infrastructure Engineering, which he founded in 1986, and Integrated Computer-Aided Engineering, which he found in 1993. He has been a Keynote/Plenary Lecturer at 53 International computing conference held in 32 different countries. On September 29, 1998, he was awarded a patent for a "Method and apparatus for efficient design automation and optimization, and structures produced thereby (United States Patent Number 5,815,394) (with a former PhD Student). He is the recipient of numerous academic, research and leadership awards, honors, and recognition. In 1998, he was awarded the University Distinguished Scholar Award by the Ohio State University ' 'in recognition of extraordinary accomplishment in research and scholarship' and the Senate of the General Assembly of State of Ohio passed a resolution honoring him as an ' Outstanding Ohioan'. He is the quadruple winner of the