Leveraging Machine Learning for Enhanced Detection and Classification of Brain Pathologies Using EEG

Abstract

Maintaining brain health is vital due to its role in controlling all body functions. This thesis introduces novel methods for the problem of automated brain diagnostic tasks using electroencephalogram (EEG). Several contributions have been made, including wavelet-based feature extraction methods and novel deep-learning architectures for detecting and classifying brain pathologies. Additionally, novel methods of feature dimensionality reduction, data fusion, and data augmentation are proposed. The proposed solutions are rigorously assessed using extensive EEG datasets consisting of patients from a wide demographic range to evaluate the generalization capabilities. This thesis offers significant contributions to biomedical signal processing for diagnostic tasks.