Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (8): 2480-2483.DOI: 10.11772/j.issn.1001-9081.2018122553

• Frontier & interdisciplinary applications • Previous Articles     Next Articles

Motor imagery electroencephalogram signal recognition method based on convolutional neural network in time-frequency domain

HU Zhangfang, ZHANG Li, HUANG Lijia, LUO Yuan   

  1. National Engineering Research and Development Center for Information Accessibility, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Received:2018-12-27 Revised:2019-03-04 Online:2019-08-10 Published:2019-04-08
  • Supported by:
    This work is partially supported by the National Natural Science Fundation of China (61703067).

基于时频域的卷积神经网络运动想象脑电信号识别方法

胡章芳, 张力, 黄丽嘉, 罗元   

  1. 重庆邮电大学 国家信息无障碍工程研发中心, 重庆 400065
  • 通讯作者: 张力
  • 作者简介:胡章芳(1969-),女,重庆人,教授,硕士,主要研究方向:智能信号处理、数字图像处理;张力(1994-),男,湖北孝感人,硕士研究生,主要研究方向:脑机接口、人机交互;黄丽嘉(1999-),女,重庆人,主要研究方向:脑机接口、人机交互;罗元(1972-),女,湖北宜昌人,教授,博士,主要研究方向:数字图像处理、智能信号处理。
  • 基金资助:
    国家自然科学基金资助项目(61703067)。

Abstract: To solve the problem of low recognition rate of motor imagery ElectroEncephaloGram (EEG) signals, considering that EEG signals contain abundant time-frequency information, a recognition method based on Convolutional Neural Network (CNN) in time-frequency domain was proposed. Firstly, Short-Time Fourier Transform (STFT) was applied to preprocess the relevant frequency bands of EEG signals to construct a two-dimensional time-frequency domain map composed of multiple time-frequency maps of electrodes, which was regarded as the input of the CNN. Secondly, focusing on the time-frequency characteristic of two-dimensional time-frequency domain map, a novel CNN structure was designed by one-dimensional convolution method. Finally, the features extracted by CNN were classified by Support Vector Machine (SVM). Experimental results based on BCI dataset show that the average recognition rate of the proposed method is 86.5%, which is higher than that of traditional motor imagery EEG signal recognition method, and the proposed method has been applied to the intelligent wheelchair, which proves its effectiveness.

Key words: motor imagery, ElectroEncephaloGram (EEG), time-frequency domain, Convolutional Neural Network (CNN), intelligent wheelchair

摘要: 针对目前运动想象脑电(EEG)信号识别率较低的问题,考虑到脑电信号蕴含着丰富的时频信息,提出一种基于时频域的卷积神经网络(CNN)运动想象脑电信号识别方法。首先,利用短时傅里叶变换(STFT)对脑电信号的相关频带进行预处理,并将多个电极的时频图组合构造出一种二维时频图;然后,针对二维时频图的时频特性,通过一维卷积的方法设计了一种新颖的CNN结构;最后,通过支持向量机(SVM)对CNN提取的特征进行分类。基于BCI数据集的实验结果表明,所提方法的平均识别率为86.5%,优于其他传统运动想象脑电信号识别方法;同时将该方法应用在智能轮椅上,验证了其有效性。

关键词: 运动想象, 脑电, 时频域, 卷积神经网络, 智能轮椅

CLC Number: