1
SeizureNet: a model for robust detection of epileptic seizures using EEG
signals based on convolutional neural network
Wei Zhao
1
, Wenfeng Wang
2*
1
Chengyi University College, Jimei University, Jimei Ave 199, Xiamen, People's Republic of China
2
School of Electronic and Electrical Engineering, Shanghai Institute of Technology, Haiquan Road 100,
Shanghai, People's Republic of China
*
Email: wangwenfeng@nimte.ac.cn
Abstract: The epilepsy is a neurological disorder and generally detected by electroencephalogram (EEG) signals. The manual
inspection of epileptic seizures is a time-consuming and laborious process. Extensive automatic detection algorithms were
proposed by using traditional approaches, which show good accuracy for several specific EEG classification problems but
perform poorly in others. To address this issue, we present a novel model, named SeizureNet, for robust detection of epileptic
seizures using EEG signals based on convolutional neural network. Firstly, we utilize two CNNs to extract time-invariant
features from single-channel EEG signals. Then, a fully connected layer is employed to learn high-level features. Finally, these
features are supplied to a softmax layer to classify. We evaluated the model on a benchmark database provided by the
University of Bonn and adopted a ten-fold cross-validation approach. The proposed model has achieved the accuracy of
98.50%~100.00% in classifying non-seizure and seizure, 97.00%~99.00% in classifying healthy, inter-ictal and ictal, and 95.84%
in classifying among five-class EEG states.
1. Introduction
Epileptic seizures are caused by a disturbance in the
electrical activity of the brain. Electroencephalogram (EEG)
is an electrophysiological monitoring method to record the
electrical activity of the brain. The EEG is the prime signal
that has been widely used for detecting epilepsy [1-3]. The
visual inspection of EEG is a time-consuming and laborious
process. Hence, automatic EEG signal analysis for clinical
screening is necessary for the diagnosis of epilepsy.
Recently, numerous research work has been carried
out to automatic detection of epileptic seizures using EEG
signals and evaluated on the University of Bonn EEG
dataset, a widely used benchmark database for seizure
recognition. The published work related to EEG-based
epileptic seizure detection mainly involves three
classification problems: two-class classification, three-class
classification, and five-class classification. The details will
be introduced in later section. The approaches fall into two
major groups: traditional methods and deep learning
methods. Most conventional methods first extract features
from raw EEG and then fed to the classifier for
classification. The feature exaction techniques contain
Fourier transform (FT) [4-5], discrete wavelet transform
(DWT) [6-10], approximate entropy (ApEn), [7, 9], Tsallis
entropy [11], local mean decomposition (LMD) [12],
tunable-Q wavelet transform (TQWT) [13] and so on.
Besides, several methods use multiple feature extraction
techniques. Such as Bhattacharyya et al. [13] utilized
TQWT and k-nearest neighbor entropy (KNNE) to exact the
features of EEG. The commonly used classifier involves the
artificial neural network (ANN) [9], decision trees (DT) [4],
k-nearest neighbor (KNN) [10], support vector machine
(SVM) [8] and so on. Also, many techniques adopted an
optimized classifier for classification. For example, Zhang et
al. [11] employed SVM optimized by genetic algorithm
(GA-SVM) for classification.
The performance of these traditional techniques
depends on handwrought feature extractors, as well as
selected classifiers. To address this issue, many approaches
based on deep learning technology were proposed. Such as
Petrosian et al. [15] applied recurrent neural networks (RNN)
combined with signal wavelet decomposition to learn
temporal patterns for epileptic seizure detection. Lin et al.
[16] proposed a deep learning framework based on stacked
sparse autoencoder (SSAE) to learn the sparse and high-
level representations of EEG signals. Hussein et al. [1]
developed an optimized deep neural network based on long
short-term memory (LSTM) to learn the temporal
dependencies in EEG data for the robust detection of
epileptic seizures.
Epilepsy detection based on convolutional neural
networks (CNN) has also attracted much attention. Acharya
et al. [17] implemented a 13-layer deep CNN algorithm to
detect normal, preictal, and seizure classes. Liu et al. [18]
also developed their models based on CNN, which show
good accuracy for two-class classification but perform
poorly for three-class classification. Besides, Zhao et al. [19]
designed a model based on CNN, which consists of three
convolutional blocks and three fully-connected (FC) layers.
And each convolutional block composes of five types of
layers. They achieved good experimental results on two-
class and three-class classifications.
Besides, several approaches that combine CNN with
traditional technologies have been proposed for seizure
detection. Ullah et al. [2] implemented a system that is an
ensemble of pyramidal one-dimensional CNN models,
which combined CNN with a majority vote (MV). San-
Segundo et al. [20] presented a model based on FT and
CNN. Gao et al. [21] proposed a method based on ApEn,
recurrence quantification analysis (RQA), and CNN. Türk et
al. [22] obtained two-dimensional (2D) frequency-time
scalograms of EEG records by using continuous wavelet
transform (CWT), then fed into CNN.