ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2020, Vol. 57 ›› Issue (12): 2481-2489.doi: 10.7544/issn1000-1239.2020.20200723

所属专题: 2020人机混合增强智能的典型应用专题

• 人工智能 • 上一篇    下一篇



  1. 1(北京交通大学计算机与信息技术学院 北京 100044);2(交通数据分析与挖掘北京市重点实验室(北京交通大学) 北京 100044);3(民航旅客服务智能化应用技术重点实验室(中国民用航空局) 北京 100044) (
  • 出版日期: 2020-12-01
  • 基金资助: 

Motor Imagery Classification Based on Multiscale Feature Extraction and Squeeze-Excitation Model

Jia Ziyu1,2, Lin Youfang1,2,3, Liu Tianhang1, Yang Kaixin1, Zhang Xinwang1, Wang Jing1,2,3   

  1. 1(School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044);2(Beijing Key Laboratory of Traffic Data Analysis and Mining (Beijing Jiaotong University), Beijing 100044);3(Key Laboratory of Intelligent Passenger Service of Civil Aviation (Civil Aviation Administration of China), Beijing 100044)
  • Online: 2020-12-01
  • Supported by: 
    This work was supported by the Fundamental Research Funds for the Central Universities (2020YJS025) and the National Natural Science Foundation of China (61603029).

摘要: 基于运动想象的脑机接口技术能够建立大脑与外界之间的联系,逐渐成为人机混合增强智能的重要应用,并广泛应用于医学康复治疗等领域.由于脑电信号具有非线性、非平稳和低信噪比等特点,使得准确的分类运动想象脑电信号具有很大挑战.为此,提出一种新颖的多尺度特征提取与挤压激励模型对运动想象脑电信号进行高精度分类.首先,基于多尺度卷积模块自动提取原始脑电信号的时域、频域和时频域特征;然后,使用残差模块和挤压激励模块分别进行特征的融合和选择;最后,利用全连接网络层进行运动想象脑电信号的分类.实验在2个公开的脑机接口竞赛数据集上进行分析,结果表明该模型与现有先进模型相比,有效地提升了运动想象脑电信号的识别效果,在2个数据集上分别取得了78.0%和82.5%的平均准确度,该模型可以在脑电通道较少的情况下有效地分类脑电信号且无需手动设计特征,具有较高的应用价值.

关键词: 运动想象, 挤压激励模型, 脑电信号, 脑机接口, 多尺度卷积

Abstract: Brain-computer Interface (BCI) technology based on motor imagery (MI) can establish communication between the human brain and outside world. It has been widely used in medical rehabilitation and other fields. Owing to the characteristics of the motor imagery EEG signals,such as non-linear, non-stationary, and low signal-noise ratio, it is a huge challenge to classify motor imagery EEG signals accurately. Hence, we propose a novel multiscale feature extraction and squeeze-excitation model which is applied for the classification of motor imagery EEG signals. Firstly, the proposed deep learning module, which is based on multiscale structure, automatically extracts time domain features, frequency domain features and time-frequency domain features. Then, the residual module and squeeze-excitation module are applied for feature fusion and selection, respectively. Finally, fully connected network layers are used to classify motor imagery EEG signals. The proposed model is evaluated on two public BCI competition datasets. The results show that the proposed model can effectively improve the recognition performance of motor imagery EEG signals compared with the existing several state-of-the-art models. The average accuracy on the two datasets is 78.0% and 82.5%, respectively. Moreover, the proposed model has higher application value because it classifies motor imagery EEG signals efficiently without manual feature extraction when spatial information is insufficient.

Key words: motor imagery, squeeze-excitation model, EEG signal, Brain-computer Interface, multiscale convolution