Robust Approach Based on Convolutional Neural Networks for Identification of Focal EEG Signals

Abstract

Electroencephalogram (EEG) signals provide important information for the identification of the epileptogenic area. Identification of focal EEG signals locates the epileptogenic area, which is an important task for successful surgery. In this article, a convolutional neural networks (CNNs) based framework is proposed for automatic identification of focal EEG signals. The proposed intelligent system initially uses a window for randomly segment the input EEG signals. The short-time Fourier transform is applied on to the segmented EEG signals for conversion of input EEG signals into time-frequency (T-F) representation. The T-F representation of EEG signals is used as T-F images. Instead of training an end-to-end CNNs which necessitates more input images and time, we opt to use a pretrained CNNs model for transfer learning. Specifically, deep feature extraction (DFE) is employed for acquiring the more convenient features from the input EEG images. The deep features extracted from AlexNet, VGG16, VGG19, and Resnet50 models are used as input to different variants of the k-nearest neighbor (k-NN) classifier. The conducted experimental works show that AlexNet, VGG16, and Resnet50 achieve promising results. Specifically, the fc6 layers of AlexNet, VGG16, and fc1000 layer of Resnet50 produce a 99.8% accuracy score with the weighted-k-NN approach. The comparative study shows that the proposed method provides better performance in comparison to state-of-the-art methods.