Multiclass Classification of Spatially Filtered Motor Imagery EEG Signals Using Convolutional Neural Network for BCI Based Applications

被引:31
作者
Shajil, Nijisha [1 ]
Mohan, Sasikala [1 ]
Srinivasan, Poonguzhali [1 ]
Arivudaiyanambi, Janani [1 ]
Arasappan Murrugesan, Arunnagiri [1 ]
机构
[1] Anna Univ, Ctr Med Elect, Dept Elect & Commun Engn, Coll Engn Guindy CEG, Chennai 600025, Tamil Nadu, India
关键词
Brain-computer interface; EEG data; Motor imagery; Convolutional neural network; Common spatial pattern; Spectrogram;
D O I
10.1007/s40846-020-00538-3
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Purpose Brain-Computer Interface (BCI) system offers a new means of communication for those with paralysis or severe neuromuscular disorders. BCI systems based on Motor Imagery (MI) Electroencephalography (EEG) signals enable the user to convert their thoughts into actions without any voluntary muscle movement. Recently, Convolutional neural network (CNN) is used for the classification of MI signals. However, to produce good MI classification, it is necessary to effectively represent the signal as an input image to the CNN and train the deep learning classifier using large training data. Methods In this work, EEG signals are acquired over 16 channels and are filtered using a bandpass filter with the frequency range of 1 to 100 Hz. The processed signal is spatially filtered using Common Spatial Pattern (CSP) filter. The spectrograms of the spatially filtered signals are given as input to CNN. A single convolutional layer CNN is designed to classify left hand, right hand, both hands, and feet MI EEG signals. The size of the training data is increased by augmenting the spectrograms of the EEG signals. Results The CNN classifier was evaluated using MI signals acquired from twelve healthy subjects. Results show that the proposed method achieved an average classification accuracy of 95.18 +/- 2.51% for two-class (left hand and right hand) and 87.37 +/- 1.68% for four-class (Left hand, Right hand, Both hands, and Feet) MI. Conclusion Thus, the method manifests that this 2D representation of 1D EEG signal along with image augmentation shows a high potential for classification of MI EEG signals using the designed CNN model.
引用
收藏
页码:663 / 672
页数:10
相关论文
共 50 条
  • [21] MOTOR IMAGERY FOR EEG BIOMETRICS USING CONVOLUTIONAL NEURAL NETWORK
    Das, Rig
    Maiorana, Emanuele
    Campisi, Patrizio
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2062 - 2066
  • [22] Convolutional neural network based features for motor imagery EEG signals classification in brain-computer interface system
    Taheri, Samaneh
    Ezoji, Mehdi
    Sakhaei, Sayed Mahmoud
    SN APPLIED SCIENCES, 2020, 2 (04):
  • [23] Motor Imagery EEG Signal Classification Using Optimized Convolutional Neural Network
    Thiyam, Deepa Beeta
    Raymond, Shelishiyah
    Avasarala, Padmanabha Sarma
    PRZEGLAD ELEKTROTECHNICZNY, 2024, 100 (08): : 273 - 279
  • [24] Multiclass classification of motor imagery tasks based on multi-branch convolutional neural network and temporal convolutional network model
    Yu, Shiqi
    Wang, Zedong
    Wang, Fei
    Chen, Kai
    Yao, Dezhong
    Xu, Peng
    Zhang, Yong
    Wang, Hesong
    Zhang, Tao
    CEREBRAL CORTEX, 2024, 34 (02)
  • [25] Comparison of Motor Imagery EEG Classification using Feedforward and Convolutional Neural Network
    Majoros, Tamas
    Oniga, Stefan
    IEEE EUROCON 2021 - 19TH INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES, 2021, : 25 - 29
  • [26] Classification of Visual Perception and Imagery based EEG Signals Using Convolutional Neural Networks
    Bang, Ji-Seon
    Jeong, Ji-Hoon
    Won, Dong-Ok
    2021 9TH IEEE INTERNATIONAL WINTER CONFERENCE ON BRAIN-COMPUTER INTERFACE (BCI), 2021, : 30 - 35
  • [27] Fusion Convolutional Neural Network for Multi-Class Motor Imagery of EEG Signals Classification
    Echtioui, Amira
    Zouch, Wassim
    Ghorbel, Mohamed
    Mhiri, Chokri
    Hamam, Habib
    IWCMC 2021: 2021 17TH INTERNATIONAL WIRELESS COMMUNICATIONS & MOBILE COMPUTING CONFERENCE (IWCMC), 2021, : 1642 - 1647
  • [28] Multi-classification for EEG motor imagery signals using data evaluation-based auto-selected regularized FBCSP and convolutional neural network
    Yang An
    Hak Keung Lam
    Sai Ho Ling
    Neural Computing and Applications, 2023, 35 : 12001 - 12027
  • [29] SincMSNet: a Sinc filter convolutional neural network for EEG motor imagery classification
    Liu, Ke
    Yang, Mingzhao
    Xing, Xin
    Yu, Zhuliang
    Wu, Wei
    JOURNAL OF NEURAL ENGINEERING, 2023, 20 (05)
  • [30] TSPNet: a time-spatial parallel network for classification of EEG-based multiclass upper limb motor imagery BCI
    Bi, Jingfeng
    Chu, Ming
    Wang, Gang
    Gao, Xiaoshan
    FRONTIERS IN NEUROSCIENCE, 2023, 17