Advertisement

Medical & Biological Engineering & Computing

, Volume 57, Issue 1, pp 147–157 | Cite as

A hierarchical semi-supervised extreme learning machine method for EEG recognition

  • Qingshan SheEmail author
  • Bo Hu
  • Zhizeng Luo
  • Thinh Nguyen
  • Yingchun ZhangEmail author
Original Article
  • 205 Downloads

Abstract

Feature extraction and classification is a vital part in motor imagery-based brain-computer interface (BCI) system. Traditional deep learning (DL) methods usually perform better with more labeled training samples. Unfortunately, the labeled samples are usually scarce for electroencephalography (EEG) data, while unlabeled samples are available in large quantity and easy to collect. In addition, traditional DL algorithms are notoriously time-consuming for the training process. To address these issues, a novel method of hierarchical semi-supervised extreme learning machine (HSS-ELM) is proposed in this paper and applied for motor imagery (MI) task classification. Firstly, the deep architecture of hierarchical ELM (H-ELM) approach is employed for feature learning automatically, and then these new high-level features are classified using the semi-supervised ELM (SS-ELM) algorithm which can exploit the information from both labeled and unlabeled data. Extensive experiments were conducted on some benchmark datasets and EEG datasets to evaluate the effectiveness of the proposed method. Compared with several state-of-the-art methods, including SVM, ELM, SAE, H-ELM, and SS-ELM, our HSS-ELM method can achieve better classification accuracy, a mean kappa value of 0.7945 and 0.5701 across all subjects in the training and evaluation sessions of BCI Competition IV Dataset 2a, respectively. Finally, it comes to the conclusion that the proposed method has achieved superior performance for feature extraction and classification of EEG signals.

Graphical abstract

The schematic of the proposed HSS-ELM algorithm.

Keywords

Motor imagery electroencephalography Extreme learning machines Semi-supervised learning Hierarchical Deep learning 

Notes

Acknowledgments

This work is supported by National Nature Science Foundation under Grant (No.61201302, 61671197 and 61601162), Zhejiang Province Natural Science Foundation (LY15F010009), Guangdong Provincial Work Injury Rehabilitation Center and the University of Houston. The authors would like to acknowledge the BCI Competition IV Dataset 2a which was used to test the algorithms proposed in this study.

Compliance with ethical standards

Conflict of interests

The authors declare that they have no conflict of interests.

References

  1. 1.
    Wolpaw J, Wolpaw E W (2012) Brain-computer interfaces: principles and practice. OUP USAGoogle Scholar
  2. 2.
    Pfurtscheller G, Neuper C (2001) Motor imagery and direct brain-computer communication. Proc IEEE 89(7):1123–1134CrossRefGoogle Scholar
  3. 3.
    Sanei S, Chambers J A (2013) EEG signal processing. John Wiley & SonsGoogle Scholar
  4. 4.
    Samek W, Kawanabe M, Müller KR (2014) Divergence-based framework for common spatial patterns algorithms. IEEE Rev Biomed Eng 7:50–72CrossRefGoogle Scholar
  5. 5.
    She Q, Gan H, Ma Y et al (2016) Scale-dependent signal identification in low-dimensional subspace: motor imagery task classification. Neural Plast 7431012Google Scholar
  6. 6.
    Thomas E, Fruitet J, Clerc M (2013) Combining ERD and ERS features to create a system-paced BCI. J Neurosci Methods 216(2):96–103CrossRefGoogle Scholar
  7. 7.
    Park C, Looney D, ur Rehman N et al (2013) Classification of motor imagery BCI using multivariate empirical mode decomposition. IEEE Trans Neural Syst Rehab Eng 21(1):10–22CrossRefGoogle Scholar
  8. 8.
    Ang KK, Chin ZY, Wang C et al (2012) Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci 6:39CrossRefGoogle Scholar
  9. 9.
    Park C, Took CC, Mandic DP (2014) Augmented complex common spatial patterns for classification of noncircular EEG from motor imagery tasks. IEEE Trans Neural Syst Rehab Eng 22(1):1–10CrossRefGoogle Scholar
  10. 10.
    Djemal R, Bazyed AG, Belwafi K et al (2016) Three-class EEG-based motor imagery classification using phase-space reconstruction technique. Brain Sci 6(3):36CrossRefGoogle Scholar
  11. 11.
    Bhattacharyya S, Khasnobish A, Chatterjee S et al (2010) Performance analysis of LDA, QDA and KNN algorithms in left-right limb movement classification from EEG data. Proc IEEE Int Conf Syst Med Biol 126–131Google Scholar
  12. 12.
    Übeyli ED (2009) Combined neural network model employing wavelet coefficients for EEG signals classification. Digital Signal Process 19(2):297–308CrossRefGoogle Scholar
  13. 13.
    Wipf D, Nagarajan S (2009) A unified Bayesian framework for MEG/EEG source imaging. NeuroImage 44(3):947–966CrossRefGoogle Scholar
  14. 14.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501CrossRefGoogle Scholar
  15. 15.
    Huang GB, Zhou H, Ding X et al (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B (Cybernetics) 42(2):513–529CrossRefGoogle Scholar
  16. 16.
    Zong W, Huang GB, Chen Y (2013) Weighted extreme learning machine for imbalance learning. Neurocomputing 101:229–242CrossRefGoogle Scholar
  17. 17.
    Lendasse A, He Q, Miche Y et al (2014) Advances in extreme learning machines (ELM2012). Neurocomputing 128:1–3CrossRefGoogle Scholar
  18. 18.
    Duan L, Bao M, Miao J et al (2016) Classification based on multilayer extreme learning machine for motor imagery task from EEG signals. Procedia Comput Sci 88:176–184CrossRefGoogle Scholar
  19. 19.
    Ding S, Zhang N, Xu X et al (2015) Deep extreme learning machine and its application in EEG classification. Math Probl Eng 2015Google Scholar
  20. 20.
    Peng Y, Lu BL (2016) Discriminative manifold extreme learning machine and applications to image and EEG signal classification. Neurocomputing 174:265–277CrossRefGoogle Scholar
  21. 21.
    Zhang Y, Jin J, Wang X et al (2016) Motor imagery EEG classification via Bayesian extreme learning machine. Proc IEEE Int Conf Inf Sci Technol (ICIST) 27–30Google Scholar
  22. 22.
    Tang J, Deng C, Huang GB (2016) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst 27(4):809–821CrossRefGoogle Scholar
  23. 23.
    Kasun LLC, Zhou H, Huang GB et al (2013) Representational learning with ELMs for big data. IEEE Intell Syst 28(6):31–34Google Scholar
  24. 24.
    Uzair M, Shafait F, Ghanem B et al (2015) Representation learning with deep extreme learning machines for efficient image set classification. arXiv preprint arXiv:1503.02445Google Scholar
  25. 25.
    Zhou Y, Liu B, Xia S et al (2015) Semi-supervised extreme learning machine with manifold and pairwise constraints regularization. Neurocomputing 149:180–186CrossRefGoogle Scholar
  26. 26.
    Huang G, Song S, Gupta JND et al (2014) Semi-supervised and unsupervised extreme learning machines. IEEE Trans Cybern 44(12):2405–2417CrossRefGoogle Scholar
  27. 27.
    Yu W, Zhuang F, He Q et al (2015) Learning deep representations via extreme learning machines. Neurocomputing 149:308–315CrossRefGoogle Scholar
  28. 28.
    Gan H, Luo ZZ, Meng M et al (2016) A risk degree-based safe semi-supervised learning algorithm. Int J Mach Learn Cybern 7(1):85–94CrossRefGoogle Scholar
  29. 29.
    Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7(Nov):2399–2434Google Scholar
  30. 30.
    Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507CrossRefGoogle Scholar
  31. 31.
    Vincent P, Larochelle H, Bengio Y et al (2008) Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning, 1096–1103Google Scholar
  32. 32.
    Vincent P, Larochelle H, Lajoie I et al (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11(Dec):3371–3408Google Scholar
  33. 33.
    Salakhutdinov R, Larochelle H (2010) Efficient learning of deep Boltzmann machines. Proc Int Conf Artif Intell Stat 693–700Google Scholar
  34. 34.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  35. 35.
    Blake CC, Merz CJ UCI repository of machine learning databases. Available online: http://archive.ics.uci.edu/ml/
  36. 36.
    The Yale Face Database Available online: http://vision.ucsd.edu/content/yale-face-database
  37. 37.
    Graz University BCI Competition IV Datasets 2a. Available online: http://www.bbci.de/competition/iv/#dataset2a
  38. 38.
    Meng M, Zhu J, She Q et al (2016) Two-level feature extraction method for multi-class motor imagery EEG. Acta Automat Sin 42(12):1915–1922Google Scholar
  39. 39.
    Längkvist M, Karlsson L, Loutfi A (2012) Sleep stage classification using unsupervised feature learning. Adv Artif Neural Syst 2012:5Google Scholar
  40. 40.
    Wu W, Chen Z, Gao X et al (2015) Probabilistic common spatial patterns for multichannel EEG analysis. IEEE Trans Pattern Anal Mach Intell 37(3):639–653CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2018

Authors and Affiliations

  1. 1.Institute of Intelligent Control and RoboticsHangzhou Dianzi UniversityZhejiangChina
  2. 2.Department of Biomedical EngineeringUniversity of HoustonHoustonUSA

Personalised recommendations