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
. 2018 Oct 28:2018:9593682.
doi: 10.1155/2018/9593682. eCollection 2018.

Sparse Representation-Based Extreme Learning Machine for Motor Imagery EEG Classification

Qingshan She  1 , Kang Chen  1 , Yuliang Ma  1 , Thinh Nguyen  2 , Yingchun Zhang  1   2
Affiliations

Sparse Representation-Based Extreme Learning Machine for Motor Imagery EEG Classification

Qingshan She et al. Comput Intell Neurosci. .

Abstract

Classification of motor imagery (MI) electroencephalogram (EEG) plays a vital role in brain-computer interface (BCI) systems. Recent research has shown that nonlinear classification algorithms perform better than their linear counterparts, but most of them cannot extract sufficient significant information which leads to a less efficient classification. In this paper, we propose a novel approach called FDDL-ELM, which combines the discriminative power of extreme learning machine (ELM) with the reconstruction capability of sparse representation. Firstly, the common spatial pattern (CSP) algorithm is adopted to perform spatial filtering on raw EEG data to enhance the task-related neural activity. Secondly, the Fisher discrimination criterion is employed to learn a structured dictionary and obtain sparse coding coefficients from the filtered data, and these discriminative coefficients are then used to acquire the reconstructed feature representations. Finally, a nonlinear classifier ELM is used to identify these features in different MI tasks. The proposed method is evaluated on 2-class Datasets IVa and IIIa of BCI Competition III and 4-class Dataset IIa of BCI Competition IV. Experimental results show that our method achieved superior performance than the other existing algorithms and yielded the accuracies of 80.68%, 87.54%, and 63.76% across all subjects in the above-mentioned three datasets, respectively.

PubMed Disclaimer

Figures

Figure 1
Figure 1
A schematic for the overall framework of the FDDL-ELM-learning algorithm.
Figure 2
Figure 2
Testing accuracy with different parameters on Diabetes. (a) Accuracy in terms of m; (b) accuracy curve in terms of (λ1, λ2).
Figure 3
Figure 3
Testing accuracy with different parameters on liver disorders. (a) Accuracy in terms of m; (b) accuracy curve in terms of (λ1, λ2).
Figure 4
Figure 4
Testing accuracy with different parameters on waveform. (a) Accuracy in terms of m; (b) accuracy curve in terms of (λ1, λ2).
Figure 5
Figure 5
Testing accuracy with different parameters on COIL-20. (a) Accuracy in terms of m; (b) accuracy curve in terms of (λ1, λ2).
See this image and copyright information in PMC

References

    1. Sun S., Zhou J. A review of adaptive feature extraction and classification methods for EEG-based brain-computer interfaces. Proceedings of IEEE International Joint Conference on Neural Networks (IJCNN); 2014; Beijing, China. pp. 1746–1753.
    1. Wolpaw J., Wolpaw E. W. Brain-Computer Interfaces: Principles and Practice. Oxford, UK: OUP; 2012.
    1. Wang Y., Gao S., Gao X. Common spatial pattern method for channel selection in motor imagery based brain-computer interface. Proceedings of IEEE International Conference on Engineering in Medicine and Biology Society; 2005; Shanghai, China. pp. 5392–5395. - PubMed
    1. She Q., Gan H., Ma Y., et al. Scale-dependent signal identification in low-dimensional subspace: motor imagery task classification. Neural Plasticity. 2016;2016:1–15. doi: 10.1155/2016/7431012.7431012 - DOI - PMC - PubMed
    1. Park C., Looney D., ur Rehman N., et al. Classification of motor imagery BCI using multivariate empirical mode decomposition. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2013;21(1):10–22. doi: 10.1109/tnsre.2012.2229296. - DOI - PubMed

LinkOut - more resources