Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jul 20:2020:1981728.
doi: 10.1155/2020/1981728. eCollection 2020.

Spatial-Frequency Feature Learning and Classification of Motor Imagery EEG Based on Deep Convolution Neural Network

Minmin Miao  1   2 , Wenjun Hu  1   2 , Hongwei Yin  1   2 , Ke Zhang  1   2
Affiliations

Spatial-Frequency Feature Learning and Classification of Motor Imagery EEG Based on Deep Convolution Neural Network

Minmin Miao et al. Comput Math Methods Med. .

Abstract

EEG pattern recognition is an important part of motor imagery- (MI-) based brain computer interface (BCI) system. Traditional EEG pattern recognition algorithm usually includes two steps, namely, feature extraction and feature classification. In feature extraction, common spatial pattern (CSP) is one of the most frequently used algorithms. However, in order to extract the optimal CSP features, prior knowledge and complex parameter adjustment are often required. Convolutional neural network (CNN) is one of the most popular deep learning models at present. Within CNN, feature learning and pattern classification are carried out simultaneously during the procedure of iterative updating of network parameters; thus, it can remove the complicated manual feature engineering. In this paper, we propose a novel deep learning methodology which can be used for spatial-frequency feature learning and classification of motor imagery EEG. Specifically, a multilayer CNN model is designed according to the spatial-frequency characteristics of MI EEG signals. An experimental study is carried out on two MI EEG datasets (BCI competition III dataset IVa and a self-collected right index finger MI dataset) to validate the effectiveness of our algorithm in comparison with several closely related competing methods. Superior classification performance indicates that our proposed method is a promising pattern recognition algorithm for MI-based BCI system.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflicts of interest.

Figures

Figure 1
Figure 1
Spatial-frequency energy distributions of EEG in different motor imagery states (Finger Dataset).
Figure 2
Figure 2
Spatial-frequency energy distributions of EEG in different motor imagery states (BCI competition III dataset IVa).
Figure 3
Figure 3
The structure diagram of convolutional neural network for motor imagery EEG pattern recognition (Finger Dataset).
Figure 4
Figure 4
Spatial filter brain pattern distribution (Finger Dataset).
Figure 5
Figure 5
Classification accuracy of validation set and training set during CNN training (subject S1 of Finger Dataset).
Figure 6
Figure 6
Classification accuracies of 10-fold cross-validations performed by our method and three other competing methods (BCI competition III dataset IVa).
Figure 7
Figure 7
Classification accuracies derived by CSP, FBCSP, and our method (Finger Dataset).
Figure 8
Figure 8
Running times of CNN training for all subjects in BCI competition III dataset IVa.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Dai M. X., Zheng D. Z., Liu S. C., Zhang P. J. Transfer kernel common spatial patterns for motor imagery brain-computer interface classification. Computational and Mathematical Methods in Medicine. 2018;2018:9. doi: 10.1155/2018/9871603.9871603 - DOI - PMC - PubMed
    1. Chang H. L., Yang J. M. Genetic-based feature selection for efficient motion imaging of a brain-computer interface framework. Journal of Neural Engineering. 2018;15(5) doi: 10.1088/1741-2552/aad567. - DOI - PubMed
    1. Lee S.-B., Kim H.-J., Kim H., Jeong J.-H., Lee S.-W., Kim D.-J. Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification. Information Sciences. 2019;502:190–200. doi: 10.1016/j.ins.2019.06.008. - DOI
    1. Li Y., Zhang X. R., Zhang B., Lei M. Y., Cui W. G., Guo Y. Z. A channel-projection mixed-scale convolutional neural network for motor imagery EEG decoding. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2019;27(6):1170–1180. doi: 10.1109/tnsre.2019.2915621. - DOI - PubMed
    1. Shah S. A., Tan H. L., Tinkhauser G., Brown P. Towards real-time, continuous decoding of gripping force from deep brain local Field potentials. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2018;26(7):1460–1468. doi: 10.1109/tnsre.2018.2837500. - DOI - PMC - PubMed

MeSH terms

LinkOut - more resources