基于卷积循环神经网络的运动想象脑电信号模式识别  

Pattern Recognition of Motion Imagination EEG Signal Based on Convolutional Cyclic Neural Network

作　　者：胡存林 叶晔[1] HU CunLin;YE Ye(College of Mechanical Engineering,Anhui University of Technology,Ma’anshan 243002,China)

机构地区：[1]安徽工业大学机械工程学院,安徽马鞍山243002

出　　处：《洛阳理工学院学报（自然科学版）》2024年第1期50-55,共6页Journal of Luoyang Institute of Science and Technology：Natural Science Edition

摘　　要：脑机接口技术可以帮助运动障碍人员通过外部设备与环境进行交互。为了提高对运动想象激发的脑电信号的识别率,提出一种基于卷积神经网络(Convolutional Neural Network, CNN)和循环神经网络(Recurrent Neural Network, RNN)的混合神经网络模式识别方法,并在实际计算中使用长短期记忆神经网络(Long Short-Term Memory, LSTM)和门控循环单元(Gated Recurrent Unit, GRU)两种不同的RNN进行对比。对原始脑电信号数据进行滤波和分段处理,将处理好的数据输入到混合神经网络中,使用Softmax进行分类,用BCI竞赛IV中的数据集2a和数据集1两种脑电数据集进行验证,此方法能够有效地提高模式识别精度,平均准确率达到了95%以上。Brain-computer interface technology helps people with motor disorders interact with the environment through external devices.In order to improve the pattern recognition rate of EEG signals fuelled by motion imagination,a hybrid neural network pattern recognition based on convolutional neural network(CNN)and recurrent neural network(RNN)is proposed,In the actual calculation,two different RNNs,Long Short-Term Memory(LSTM)and Gated Recurrent Unit(GRU),are used for experimental comparison.Firstly,the original EEG data is filtered and segmented and the processed data are input into the hybrid neural network;Finally,Softmax is used for classification.Two EEG data sets,data set 2a and data set 1 in BCI competition IV,are used for experimental verification.The proposed methods can effectively improve the accuracy of pattern recognition,with an average accuracy more than 95%.

关 键 词：运动想象 模式识别 循环神经网络 卷积神经网络 

分 类 号：TP249[自动化与计算机技术—检测技术与自动化装置]