- Explores machine learning techniques that have been modified and validated for the purpose of EEG signal classification using Discrete Wavelet Transform for the identification of epileptic seizures
- Encompasses machine learning techniques, providing an easily understood resource for both non-specialized readers and biomedical researchers
- Provides a number of experimental analyses, with their results discussed and appropriately validated
Table of Contents:1. INTRODUCTION
- 1.1 Problem Statement
- 1.2 General and Specific Goals
- 1.3 Basic Concepts of EEG Signal
- 1.4 Overview of Machine Learning Techniques
- 1.5 Swarm Intelligence
- 1.6 Tools for Feature Extraction
- 1.7 Our Contributions
- 1.8 Summary and Structure of Thesis
2. LITERATURE SURVEY
- 2.1 EEG Signal Analysis Methods
- 2.2 Pre-processing of EEG Signal
- 2.3 Tasks of EEG Signal
- 2.4 Classical vs. Machine Learning Methods for EEG Classification
- 2.5 Machine Learning Methods for Epilepsy Classification
- 2.6 Summary
3. EMPIRICAL STUDY ON THE PERFORMANCE OF THE CLASSIFIERS IN EEG CLASSIFICATION
- 3.1 Multilayer Perceptron Neural Network
- 3.1.1 MLPNN with Back-Propagation
- 3.1.2 MLPNN with Resilient-Propagation
- 3.1.3 MLPNN with Manhatan Update Rule
- 3.2 Radial Basis Function
- 3.3 Probabilistic Neural Network
- 3.4 Recurrent Neural Network
- 3.5 Support Vector Machines
- 3.6 Experimental Study
- 3.6.1 Datasets and Environment
- 3.6.2 Parameters
- 3.6.3 Results and Analysis
- 3.7 Summary
4. EEG SIGNAL CLASSIFICATION USING RBF NEURAL NETWORK TRAINED WITH IMPROVED PSO ALGORITHM FOR EPILEPSY IDENTIFICATION
- 4.1 Related Work
- 4.2 Radial Basis Function Neural Network
- 4.2.1 RBFNN Architecture
- 4.2.2 RBFNN Training Algorithm
- 4.3 Particle Swarm Optimization
- 4.3.1 Architecture
- 4.3.2 Algorithm
- 4.4 RBFNN with Improved PSO Algorithm
- 4.4.1 Architecture of Proposed Model
- 4.4.2 Algorithm for Proposed Model
- 4.5 Experimental Study
- 4.5.1 Dataset Preparation and Environment
- 4.5.2 Parameters
- 4.5.3 Results and Analysis
- 4.6 Summary
5. ABC OPTIMIZED RBFNN FOR CLASSIFICATION OF EEG SIGNAL FOR EPILEPTIC SEIZURE IDENTIFICATION
- 5.1 Related Work
- 5.2 Artificial Bee Colony algorithm
- 5.2.1 Architecture
- 5.2.2 Algorithm
- 5.3 RBFNN with Improved ABC Algorithm
- 5.3.1 Architecture of Proposed Model
- 5.3.2 Algorithm for Proposed Model
- 5.4 Experimental Study
- 5.4.1 Dataset Preparation and Environment
- 5.4.2 Parameters
- 5.4.3 Results and Analysis
- 5.5 Performance Comparison between Modified PSO and Modified ABC Algorithms
- 5.6 Summary
6. CONCLUSION AND FUTURE RESEARCH
- 6.1 Findings and Constraints of Our Work
- 6.2 Future Research Work
References