An Automated System for Epilepsy Detection using EEG Brain Signals based on Deep Learning Approach

By Ihsan Ullah, Muhammad Hussain, Emad-ul-Haq Qazi, Hatim Aboalsamh. Expert systems with applications, 2018

551 citations recorded by the source corpus.

Epilepsy is a neurological disorder and for its detection, encephalography (EEG) is a commonly used clinical approach. Manual inspection of EEG brain signals is a time-consuming and laborious process, which puts heavy burden on neurologists and affects their performance. Several automatic techniques have been proposed using traditional approaches to assist neurologists in detecting binary epilepsy scenarios e.g. seizure vs. non-seizure or normal vs. ictal. These methods do not perform well when classifying ternary case e.g. ictal vs. normal vs. inter-ictal; the maximum accuracy for this case by the state-of-the-art-methods is 97+-1%. To overcome this problem, we propose a system based on deep learning, which is an ensemble of pyramidal one-dimensional convolutional neural network (P-1D-CNN) models. In a CNN model, the bottleneck is the large number of learnable parameters. P-1D-CNN works on the concept of refinement approach and it results in 60% fewer parameters compared to traditional CNN models. Further to overcome the limitations of small amount of data, we proposed augmentation schemes for learning P-1D-CNN model. In almost all the cases concerning epilepsy detection, the proposed system gives an accuracy of 99.1+-0.9% on the University of Bonn dataset.

Subfields: Cognitive Neuroscience, Psychiatry and Mental health, Signal Processing

View Paper: https://www.semanticscholar.org/paper/0f0f8c5e671ea6f492de92c73b61fa8600febce0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

Epileptic Seizure Detection Based on EEG Signals and CNN (2018, methodology): “Recently, some studies have begun applying CNNs to EEG signals (Ullah et al., 2018), and research interest in using CNNs for seizure prediction has increased, probably because these methods have been used extensively and are thus better established and more familiar in the research community.”
EEG based multi-class seizure type classification using convolutional neural network and transfer learning (2020, methodology): “…of CNN towards the classification of epileptic seizures have been implemented in recent studies (Acharya, Oh, Hagiwara, Tan, & Adeli, 2018; Achilles, et al., 2018; Birjandtalab, Heydarzadeh, & Nourani, 2017; Truong, et al., 2017; Ullah, ul Haq Qazi, & Aboalsamh, 2018; Zhou et al., 2018).”
Deep learning for electroencephalogram (EEG) classification tasks: a review (2019, methodology): “[72] CNN ReLU (conv) Softmax (FC) N SV N/A N/A SD 99.”
Deep learning-based electroencephalography analysis: a systematic review (2019, methodology): “In [134, 204], overlapping windows were explicitly used as a data augmentation technique.”
Epileptic Seizures Detection Using Deep Learning Techniques: A Review (2020, methodology): “30 [43] Clinical Chainer Filtering, Visualization 2D-CNN NA softmax NA [68] Bonn TensorFlow Data Augmentation P-1D-CNN 10 Majority Voting 99.”
Hybrid CNN-LSTM Model for Short-Term Individual Household Load Forecasting (2020, background): “ture, as discussed in [43] when developing our CNN feature extraction block, where the number of kernels is large in the lower-level layers, which are gradually decreased by a constant as we go down the higher-level layers.”