Abstract:Brain-computer interface (BCI) is a system that extracts the information of brain thinking activities through certain technical
means without relying on peripheral nerves and muscles. It directly decodes the signals of the brain and identifies the human brain through
computer technology. In this paper, two kinds of convolution neural networks (CNN) based on deep learning were proposed to classify
electroencephalogram using the data of brain-computer interface competition (BCI Competition III). The experimental results showed that
both convolution neural networks can train better models and get better classification accuracy for training data sets, compared with the
traditional back propagation neural network, with an improved the recognition accuracy of 6%.
陈娇. 基于深度卷积网络的脑电运动想象分类方法[J]. 中国医疗设备, 2019, 34(8): 37-41.
CHEN Jiao. Classification of Brain Electrical Movement Imagination Based on Deep Convolution Network. China Medical Devices, 2019, 34(8): 37-41.