Epileptic-Net: An Improved Epileptic Seizure Detection System Using Dense Convolutional Block with Attention Network from EEG

Abstract

Epilepsy is a complex neurological condition that affects a large number of people worldwide. Electroencephalography (EEG) measures the electrical activity of the brain and is widely used in epilepsy diagnosis, but it usually requires manual inspection, which can be hours long, by a neurologist. Several automatic systems have been proposed to detect epilepsy but still have some unsolved issues. In this study, we proposed a dynamic method using a deep learning model (Epileptic-Net) to detect an epileptic seizure. The proposed method is largely heterogeneous and comprised of the dense convolutional blocks (DCB), feature attention modules (FAM), residual blocks (RB), and hypercolumn technique (HT). Firstly, DCB is used to get the discriminative features from the EEG samples. Then, FAM extracts the essential features from the samples. After that, RB learns more vital parts as it entirely uses information in the convolutional layer. Finally, HT retains the efficient local features extracted from the layers situated at the different levels of the model. Its performance has been evaluated on the University of Bonn EEG dataset, divided into five distinct classes. The proposed Epileptic-Net achieves the average accuracy of 99.95% in the two-class classification, 99.98% in the three-class classification, 99.96% in the four-class classification, and 99.96% in classifying the complicated five-class problem. Thus the proposed approach shows more competitive results than the existing model to detect epileptic seizures. We also hope that this method can support experts in achieving objective and reliable results, lowering the misdiagnosis rate, and assisting in decision-making.

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

“…1D-CNN model on the A vs. B vs. C vs. D, A vs. B vs. C vs. E, and A vs. B vs. D vs. E datasets is lower than that of the Epileptic-Net model in the study byIslam et al (2022), the length of the inputted EEG with 1 s is considerably lower than that of the Epileptic-Net model. In a comprehensive comparison, the proposed model still has advantages with four-class classifications.…”

“…The suddenness of epileptic seizures, as well as their self-sustained discharges lasting from a few minutes to several hours, greatly increases the difficulty of detecting them. Therefore, it is clinically important to detect seizures early and intervene to reduce greater suffering for patients (Islam et al, 2022).…”

STC-NLSTMNet: An Improved Human Activity Recognition Method Using Convolutional Neural Network with NLSTM from WiFi CSI

“…Besides, the proposed FAM only selects the most important features, which also lowers the probability of over-fitting. In this work, we adopt the early stopping technique [ 53 ], which stops the current training epoch if it is noticed that the validation accuracy has not increased for six successive epochs. The model that has the least amount of lost value is the one that is kept as the best model.…”

EEG seizure detection: concepts, techniques, challenges, and future trends

“…Md Shafiqul Islam suggested a dynamic approach utilizing a deep learning model (Epileptic-Net) to detect an epileptic seizure. This approach included dense convolutional blocks, feature attention modules, residual blocks, and the hypercolumn technique [49]. Gaetano Zazzaro and Luigi Pavone evaluate the performance of a seizure detection system by studying its performance in correctly identifying seizures and in minimizing false alarms and to decide if it is generalizable to several patients [146].…”