摘要
为了提高多分类运动想象脑电信号的解码精度,以此促进脑机接口系统在生产生活中的应用。采用基于深度卷积网络的LeNet和AlexNet模型分析四分类运动想象脑电特性。将脑电信号通过预处理、数据归一化和数据增强,然后分别输入两个模型中进行分类。通过与现有不同的特征提取和分类方法对比,实验结果表明,在多分类运动想象脑电解码研究领域中,深度卷积网络模型取得的分类效果较好。
In order to accurately extract and classify the EEG features of motor imagination,so as to promote the application of the brain-computer interface system in production and life.The LeNet and AlexNet models based on deep convolutional networks are used to analyze the four-category motor imagery EEG characteristics in this paper.The EEG signals are preprocessed,data normalized and data enhanced,and then input into two models for classification.By comparing with the existing different feature extraction and classification methods,the experimental results show that the deep convolutional network model achieves better classification results in the field of multi-class motor imaging EEG decoding research.
出处
《工业控制计算机》
2021年第6期103-106,共4页
Industrial Control Computer
关键词
脑机接口
运动想象
深度卷积网络
脑电分类
brain-computer interface
motor imagination
deep convolutional network
EEG classification
