A Deep Learning Method for Classification of EEG Data Based on Motor Imagery

  • Xiu An
  • Deping Kuang
  • Xiaojiao Guo
  • Yilu Zhao
  • Lianghua He
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8590)


Effectively extracting EEG data features is the key point in Brain Computer Interface technology. In this paper, aiming at classifying EEG data based on Motor Imagery task, Deep Learning (DL) algorithm was applied. For the classification of left and right hand motor imagery, firstly, based on certain single channel, a weak classifier was trained by deep belief net (DBN); then borrow the idea of Ada-boost algorithm to combine the trained weak classifiers as a more powerful one. During the process of constructing DBN structure, many RBMs (Restrict Boltzmann Machine) are stacked on top of each other by setting the hidden layer of the bottom layer RBM as the visible layer of the next RBM, and Contrastive Divergence (CD) algorithm was also exploited to train multilayered DBN effectively. The performance of the proposed DBN was tested with different combinations of hidden units and hidden layers on multiple subjects, the experimental results showed that the proposed method performs better with 8 hidden layers. The recognition accuracy results were compared with Support vector machine (SVM) and DBN classifier demonstrated better performance in all tested cases. There was an improvement of 4 – 6% for certain cases.


Deep Learning Motor Imagery EEG Brain-computer interface Ada-boost 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Reza, K., Chai, Q.: A Brain-Computer Interface for classifying EEG correlates of chronic mental stress. In: Proceedings of International Joint Conference on Neural Networks, pp. 757–762 (2011)Google Scholar
  2. 2.
    Li, K., Rui, Q.: Classification of EEG Signals by Multi-Scale Filtering and PCA. In: IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009, pp. 362–366 (2009)Google Scholar
  3. 3.
    Gorge, H.S.O.: A fast learning algorithm for deep belief nets. Neural Computation, 1527–1554 (2006)Google Scholar
  4. 4.
    Wu, S., Wu, W.: Common Spatial Pattern and Linear Discriminant Analysis for Motor Imagery Classification. In: 2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), pp. 146–151 (2013)Google Scholar
  5. 5.
    Yoshua, B., Pascal, L.: Greedy layer-wise training of deep networks. NIPS (2006)Google Scholar
  6. 6.
    Jarrett, K., Kavukcuoglu, K.: What is the best – stage architecture for object recognition. In: ICCV (2009)Google Scholar
  7. 7.
    Yohei, Y., Mitsukura, Y.: Hemodynamic characteristics for improvement of EEG-BCI performance. In: 2013 The 6th International Conference on Human System Interaction (HSI), pp. 495–500 (2013)Google Scholar
  8. 8.
    Yohei, T., Yasue, M.: Boosted Network Classifiers for Local Feature Selection. IEEE Transactions on Neural Networks and Learning Systems, 1767–1778 (2012)Google Scholar
  9. 9.
    Plamen, D., Jesse, S.: Classification of Imagined Motor Tasks for BCI. In: 2008 IEEE Region 5 Conference, pp. 1–6 (2008)Google Scholar
  10. 10.
    Karl, J.: Characterizing Functional Asymmetries with Brain Mapping, pp. 161–186. The MIT Press (2003)Google Scholar
  11. 11.
    Guger, C., Schlogl, C., Neuper, D., Walterspacher, T., Strein, G.: Rapid prototyping of an EEG-based brain computer interface (BCI). IEEE Trans. on Neural Systems and Rehabilitation Engineering, 49–58 (2001)Google Scholar
  12. 12.
    Wolpaw, J., Birbaumer, N.: Brian-computer interfaces for communication and control. Clinical Neurophysiology, 767–791 (2002)Google Scholar
  13. 13.
    Bengio, Y., Lecun, Y.: Scaling learning algorithms towards AI. Large-Scale Kernel Machines, 1–34 (2007)Google Scholar
  14. 14.
    Jonathan, R., Wolpaw, N., Birbaumer, D.: Brain-computer interfaces for communication and control. Clin. Neurophysiol., 767–791 (2002)Google Scholar
  15. 15.
    Kirkup, L., Searle, A.: EEG-based system for rapid on-off switching without prior learning. Medical and Biological Engineering and Computing, 504–509 (2007)Google Scholar
  16. 16.
    Hochberg, L., Serruya, M.: Neuronal ensemble control of prosthetic devices by a human with tetraplegia. Nature, 164–170 (2006)Google Scholar
  17. 17.
    Cheng, M., Gao, X.: Design and implementation of a brain-computer interface with high transfer rates. IEEE Transactions on Biomedical Engineering, 1181–1186 (2002)Google Scholar
  18. 18.
    Shoker, L., Sanei, S.: Distinguishing between left and right finger movement from EEG using SVM. In: Engineering in Medicine and Biology 27th Annual Conference, pp. 5420–5423 (2005)Google Scholar
  19. 19.
    Ohkawa, Y., Suryanto, C.: Image set-based hand shape recognition using camera selection driven by multi-class Ada Boosting. Advances in Visual Computing, 555–566 (2011)Google Scholar
  20. 20.
    Shen, C., Li, H.: Boosting through optimization of margin distributions. IEEE Trans. Neural Netw. Learn. Syst., 659–666 (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Xiu An
    • 1
    • 2
  • Deping Kuang
    • 1
    • 2
  • Xiaojiao Guo
    • 1
    • 2
  • Yilu Zhao
    • 1
    • 2
  • Lianghua He
    • 1
    • 2
  1. 1.The Key Laboratory of Embedded System and Service Computing, Ministry of EducationTongji UniversityShanghaiChina
  2. 2.Department of Computer Science and TechnologyTongji UniversityShanghaiChina

Personalised recommendations