Optimisation of deep neural networks for identification of epileptic abnormalities from electroencephalogram signals

Abstract

An electroencephalogram (EEG) measures and records the electrical activity of the brain. It provides valuable information that can be used to identify epileptic abnormalities. However, the visual identification of such abnormalities from EEG signals by expert neurologists is time consuming. Therefore, several researchers have proposed using deep neural networks (DNNs) to automate the identification of these abnormalities. Their studies have examined the use of different numbers of layers, different numbers of parameters, and various operation types arranged in different architectures. This paper presents the shallowest 11-layer DNN architecture capable of classifying three classes of EEG signals: normal, preictal, and seizure. When the proposed architecture was applied to the standard University of Bonn EEG signal dataset, it achieved accuracy, specificity, and sensitivity values of 99.43%, 99.57%, and 99.10%, respectively. It not only had a better performance than the state of the art DNN architectures, but also had shallower layers with fewer parameters. This allowed it to more quickly identify epileptic abnormalities. Experiments were also conducted where the length of the EEG signals was reduced to 65% (2,662 samples with a period of 15.26 s), which in turn minimised the total parameters of the proposed architecture so that it was comparable to the smallest state-of-the-art architecture and decreased the lag time for identification. Even in these experiments, it was capable of producing equal performance measures, with the execution time reduced to only 69% of that when employing the full length of EEG signals.

Classification of Ictal and Preictal Seizure using EEG Signals based on Convolutional Neural Network

“…The authors made use of data augmentation techniques to handle the smaller size of the dataset which helps to achieve a good performance. Kurdthongmee et al combined two CNN architectures from the works of Acharya et al and Abiyev et al to make an optimized model capable of classifying normal, preictal, and seizure [12], [14], [15]. The shallow layers helped to predict abnormalities more quickly and the proposed system achieved good performance upon application to the BONN dataset.…”

Translational Applications of Neuroimaging

“…However, these methods require domain expertise and complex EEG feature extraction tasks. Although the recognition model is relatively simple, it has a low recognition rate and poor generalization ability (Kurdthongmee, 2020). With the rapid development of deep learning technology, it is increasingly being applied in the field of brain science, such as neural signal recognition , EEG classification , and seizure detection (Hernández et al, 2018).…”

Automatic epileptic seizure detection based on EEG using a moth-flame optimization of one-dimensional convolutional neural networks

“…However, these methods require domain expertise and complex EEG feature extraction tasks. Although the recognition model is relatively simple, it has a low recognition rate and poor generalization ability (Kurdthongmee, 2020). With the rapid development of deep learning technology, it is increasingly being applied in the field of brain science, such as neural signal recognition (Zhang H. et al, 2022), EEG classification (Li et al, 2022), and seizure detection (Hernández et al, 2018).…”