PH.D Dissertation on "Deep Learning Classification of Brain Neurophysiological Signals Using Heterogeneous Computing"
A PH.D dissertation was discussed in Department of Computer Engineering / College of Engineering / University of Mosul entitled "Deep Learning Classification of Brain Neurophysiological Signals Using Heterogeneous Computing" submitted by ( Ali Mukhlif Ahmed Al-Saegh), Supervised by Prof. Dr. Shefa A. Dawwd and Prof. Dr. Jassim M. Abdul-Jabbar on Tuseday, Jan. 04, 2022.
The dissertation proposes a novel data augmentation method for enlarging already available EEG datasets. The proposed CutCat augmentation method generates EEG trials from inter- and intra-subjects and trials. The method relies on cutting a specific portion from an EEG trial and concatenating it with another portion from another trial from the same subject or different subjects. The method has been tested on shallow and Deep Convolutional Neural Networks (DCNN) for the classification of motor imagery MI EEG data.
Two types of input formulations namely images and time-series have been used as input to the neural networks. Short-Time Fourier Transform (STFT) is used for generating training images from the time-series signals. The experimental results demonstrate that the proposed augmentation method is a promising strategy for handling the classification of small-scale datasets. Classification results of two EEG datasets show advancement in comparison with the results of state-of-the-art researches.