1st Edition
Automated EEG-Based Diagnosis of Neurological Disorders Inventing the Future of Neurology
Based on the authors’ groundbreaking research, Automated EEG-Based Diagnosis of Neurological Disorders: Inventing the Future of Neurology presents a research ideology, a novel multi-paradigm methodology, and advanced computational models for the automated EEG-based diagnosis of neurological disorders. It is based on the ingenious integration of three different computing technologies and problem-solving paradigms: neural networks, wavelets, and chaos theory. The book also includes three introductory chapters that familiarize readers with these three distinct paradigms.
After extensive research and the discovery of relevant mathematical markers, the authors present a methodology for epilepsy diagnosis and seizure detection that offers an exceptional accuracy rate of 96 percent. They examine technology that has the potential to impact and transform neurology practice in a significant way. They also include some preliminary results towards EEG-based diagnosis of Alzheimer’s disease.
The methodology presented in the book is especially versatile and can be adapted and applied for the diagnosis of other brain disorders. The senior author is currently extending the new technology to diagnosis of ADHD and autism. A second contribution made by the book is its presentation and advancement of Spiking Neural Networks as the seminal foundation of a more realistic and plausible third generation neural network.
Basic Concepts
Introduction
Time-Frequency Analysis: Wavelet Transforms
Signal Digitization and Sampling
Time and Frequency Domain Analyses
Time-Frequency Analysis
Types of Wavelets
Advantages of the Wavelet Transform
Chaos Theory
Introduction
Attractors in Chaotic Systems
Chaos
Classifier Designs
Data Classification
Cluster Analysis
k-Means Clustering
Discriminant Analysis
Principal Component
Artificial Neural Networks
Automated EEG-Based Diagnosis of Epilepsy
Electroencephalograms and Epilepsy
Spatio-Temporal Activity in the Human
EEG: A Spatio-Temporal Data
Data Mining Techniques
Multi-Paradigm Data Mining Strategy for EEGs
Epilepsy and Epileptic Seizures
Analysis of EEGs in an Epileptic Patient Using Wavelet Transform
Introduction
Wavelet Analysis of a Normal
Characterization of the 3-Hz Spike and Slow Wave Complex in
Absence Seizures Using Wavelet
Concluding Remarks
Wavelet-Chaos Methodology for Analysis of EEGs and EEG Sub-Bands
Introduction
Wavelet-Chaos Analysis of EEG
Application and Results
Concluding Remarks
Mixed-Band Wavelet-Chaos Neural Network Methodology
Introduction
Wavelet-Chaos Analysis: EEG Sub-Bands and Feature Space Design
Data Analysis
Band-Specific Analysis: Selecting Classifiers and Feature
Mixed-Band Analysis: Wavelet-Chaos-Neural Network
Concluding Remarks
Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network
Introduction
Principal Component Analysis for Feature
Cosine Radial Basis Function Neural Network: EEG Classification
Applications and Results
Concluding Remarks and Clinical Significance
Automated EEG-Based Diagnosis of Alzheimer’s Disease
Alzheimer’s Disease and Models of Computation: Imaging, Classification, and Neural Models
Introduction
Neurological Markers of Alzheimer’s
Imaging Studies
Classification Models .
Neural Models of Memory and Alzheimer’s Disease
Approaches to Neural Modeling
Alzheimer’s Disease: Models of Computation and Analysis of EEGs
EEGs for Diagnosis and Detection of Alzheimer’s Disease
Time-Frequency Analysis
Wavelet Analysis
Chaos Analysis
Concluding Remarks
A Spatio-Temporal Wavelet-Chaos Methodology for EEG Based Diagnosis of Alzheimer’s Disease
Introduction
Methodology
Description of the EEG
Results
Complexity and Chaoticity of the EEG: Results of the
Three-Way Factorial ANOVA
Discussion
Concluding Remarks
Third Generation Neural Networks: Spiking Neural Networks
Spiking Neural Networks: Spiking Neurons and Learning Algorithms
Introduction
Information Encoding and Evolution of Spiking
Mechanism of Spike Generation in Biological Neurons
Models of Spiking Neurons
Spiking Neural Networks (SNNs)
Unsupervised Learning
Supervised Learning
Improved Spiking Neural Networks with Application to EEG Classification and Epilepsy and Seizure Detection
XOR Classification Problem
Fisher Iris Classification Problem
EEG Classification Problem
Input and Output Encoding
Concluding Remarks
A New Supervised Learning Algorithm for Multiple Spiking Neural Networks
Introduction
Multi-Spiking Neural Network (MuSpiNN) and Neuron Model
Multi-SpikeProp: Backpropagation Learning Algorithm for MuSpiNN
Applications of Multiple Spiking Neural Networks: EEG Classification and Epilepsy and Seizure Detection
Parameter Selection and Weight Initialization
Heuristic Rules for Multi-SpikeProp
XOR Problem
Fisher Iris Classification Problem
EEG Classification Problem
Discussion and Concluding Remarks
The Future
Bibliography
Index
Biography
Hojjat Adeli is the Abba G. Lichtenstein Professor at The Ohio State University, Editor-in-Chief of the International Journal of Neural Systems, and author of 14 pioneering books. Samanwoy Ghosh-Dastidar is Principal Biomedical Engineer at ANSAR Medical Technologies in Philadelphia. Nahid Dadmehr is a board-certified neurologist in practice in Ohio since 1991.