Author/Authors :
Zhao, Wei Jimei University - Xiamen, China , Zhao, Wenbing Department of Electrical Engineering and Computer Science - Cleveland State University - Cleveland - Ohio, USA , Wang, Wenfeng School of Electronic and Electrical Engineering - Shanghai Institute of Technology - Shanghai, China , Jiang, Xiaolu Jimei University - Xiamen, China , Zhang, Xiaodong Department of Ultrasound - The First Affiliated Hospital of Xiamen University - Xiamen, China , Peng, Yonghong Faculty of Computer Science - University of Sunderland - Sunderland, UK , Zhang, Baocan Jimei University - Xiamen, China , Zhang, Guokai School of Software Engineering - Tongji University - Shanghai, China
Abstract :
2e detection of recorded epileptic seizure activity in electroencephalogram (EEG) segments is crucial for the classification of
seizures. Manual recognition is a time-consuming and laborious process that places a heavy burden on neurologists, and hence,
the automatic identification of epilepsy has become an important issue. Traditional EEG recognition models largely depend on
artificial experience and are of weak generalization ability. To break these limitations, we propose a novel one-dimensional deep
neural network for robust detection of seizures, which composes of three convolutional blocks and three fully connected layers.
2ereinto, each convolutional block consists of five types of layers: convolutional layer, batch normalization layer, nonlinear
activation layer, dropout layer, and max-pooling layer. Model performance is evaluated on the University of Bonn dataset, which
achieves the accuracy of 97.63%∼99.52% in the two-class classification problem, 96.73%∼98.06% in the three-class EEG classification problem, and 93.55% in classifying the complicated five-class problem.
Keywords :
Deep , EEG , Seizures , Novel
