基于空-频特征图学习三维卷积神经网络的运动想象脑电解码方法  

Three-dimensional convolutional neural network based on spatial-spectral feature pictures learning for decoding motor imagery electroencephalography signal

作　　者：吴雪健 褚亚奇 赵新刚[1,2] 赵忆文 WU Xuejian;CHU Yaqi;ZHAO Xingang;ZHAO Yiwen(State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,P.R.China;University of Chinese Academy of Sciences(UCAS),Beijing 100049,P.R.China)

机构地区：[1]中国科学院沈阳自动化研究所机器人学国家重点实验室,沈阳110016 [2]中国科学院大学,北京100049

出　　处：《生物医学工程学杂志》2024年第6期1145-1152,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金(62203430,62273335,U22A2067);中国博士后科学基金(2022M723312);辽宁省博士科研启动基金计划项目(2022-BS-025);机器人学国家重点实验室自主课题(2023-Z05);国家重点研发计划(2022YFB4703200)。

摘　　要：运动想象脑电(EEG)的脑机接口因其无创采集和易用性等优势,在神经康复领域展现了巨大潜力。然而,运动想象EEG具有较低的信噪比和时空分辨率,且传统神经网络仅关注其时空特征,导致运动想象任务的解码识别率较低。为解决这一问题,本文从EEG信号的频域和空间域角度出发,提出了一种基于空-频特征图学习的三维卷积神经网络解码方法。首先,利用Welch方法计算EEG的频带功率谱,结合电极空间拓扑分布的二维矩阵将时序EEG转换为包含空-频信息的脑地形图。然后,设计一维和二维卷积串行结构的三维网络,以有效学习EEG空-频特征。最后,该方法与多种经典方法进行对比实验,结果显示平均解码识别率达86.89%,较对照方法更优,验证了该方法在运动想象EEG解码领域的有效性。The brain-computer interface(BCI)based on motor imagery electroencephalography(EEG)shows great potential in neurorehabilitation due to its non-invasive nature and ease of use.However,motor imagery EEG signals have low signal-to-noise ratios and spatiotemporal resolutions,leading to low decoding recognition rates with traditional neural networks.To address this,this paper proposed a three-dimensional(3D)convolutional neural network(CNN)method that learns spatial-frequency feature maps,using Welch method to calculate the power spectrum of EEG frequency bands,converted time-series EEG into a brain topographical map with spatial-frequency information.A 3D network with one-dimensional and two-dimensional convolutional layers was designed to effectively learn these features.Comparative experiments demonstrated that the average decoding recognition rate reached 86.89%,outperforming traditional methods and validating the effectiveness of this approach in motor imagery EEG decoding.

关 键 词：运动想象脑电 脑机接口系统 空-频特征图 特征选择 信号解码 

分 类 号：R318[医药卫生—生物医学工程] TP183[医药卫生—基础医学] TN911.7[自动化与计算机技术—控制理论与控制工程]