基于相频特性的稳态视觉诱发电位深度学习分类模型  

A Deep Learning Method for SSVEP Classification Based on Phase and Frequency Characteristics

作　　者：林艳飞 臧博宇 郭嵘骁 刘志文[1] 高小榕[2] LIN Yanfei;ZANG Boyu;GUO Rongxiao;LIU Zhiwen;GAO Xiaorong(School of Information and Electronics,Beijing Institute of Technology,Beijing 100081,China;School of Medicine,Tsinghua University,Beijing 100084,China)

机构地区：[1]北京理工大学信息与电子学院,北京100081 [2]清华大学医学院,北京100084

出　　处：《电子与信息学报》2022年第2期446-454,共9页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61601028,61431007);北京市科技计划(Z201100004420015)。

摘　　要：针对现有深度学习分类方法对稳态视觉诱发电位相位与频率信息利用不充分的问题,该文提出一种用于稳态视觉诱发电位(SSVEP)分类的卷积神经网络模型。该模型以经过快速傅里叶变换后的复向量作为输入,首先对各个导联的实部向量和虚部向量进行卷积,学习相位信息;随后引入空间注意力机制,对判别频率信息进行增强;然后使用2维卷积和最大池化层进一步提取空域和频域信息;最后使用全连接层进行分类。实验结果表明利用该方法在跨受试情况下准确率可达到81.21%,通过在训练集增加标准正弦信号模板准确率可进一步提升至83.17%,相比典型相关分析方法获得了更好的分类效果。A deep learning method for Steady-State Visual Evoked Potential(SSVEP)classification is proposed to solve the problem that phase and frequency information are not fully used in existing deep learning models.First,the proposed model uses complex vectors of fast Fourier transform as input and operates convolution on real and imaginary vectors to learn phase information,and then utilizes the spatial attention module to enhance discriminative frequency information.Next,two-dimensional convolution and max pooling are used to extract further spatial and frequency features.Finally,fully connected layers are utilized to classify.The accuracy of proposed model can reach 81.21%in the case of cross subject,and the accuracy can be further improved to 83.17%by adding the standard sinusoidal signal templates to the training set.The results show that the proposed model achieves better performance than canonical correlation analysis algorithm.

关 键 词：深度学习 卷积神经网络 稳态视觉诱发电位 

分 类 号：TN911.7[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]