Skip to main content
SpringerLink
Log in

Balanced Graph-based regularized semi-supervised extreme learning machine for EEG classification

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Machine learning algorithms play a critical role in electroencephalograpy (EEG)-based brain-computer interface (BCI) systems. However, collecting labeled samples for classifier training and calibration is still difficult and time-consuming, especially for patients. As a promising alternative way to address the problem, semi-supervised learning has attracted much attention by exploiting both labeled and unlabeled samples in the training process. Nowadays, semi-supervised extreme learning machine (SS-ELM) is widely used in EEG classification due to its fast training speed and good generalization performance. However, the classification performance of SS-ELM largely depends on the quality of sample graph. The graphs of most semi-supervised algorithms are constructed by the similarity between labeled and unlabeled data called manifold graph. The more similar the structural information between samples, the greater probability they belong to the same class. In this paper, the label-consistency graph (LCG) and sample-similarity graph (SSG) are combined to constrain the model output. When the SSG is not accurate enough, the weight of LCG needs to be increased, and vice versa. The weight ratio of two graphs is optimized to obtain an optimal adjacency graph, and finally the best output weight vector is achieved. To verify the effectiveness of the proposed algorithm, it was validated and compared with several existing methods on two real datasets: BCI Competition IV Dataset 2a and BCI Competition III Dataset 4a. Experimental results show that our algorithm has achieved the promising results, especially when the number of labeled samples is small.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Brunner C, Birbaumer N, Blankertz B et al (2015) BNCI Horizon 2020: towards a roadmap for the BCI community. Brain-Comput Interfaces 2(1):1–10

    Article  Google Scholar 

  2. Lotte F, Bougrain L, Cichocki A, Clerc M, Congedo M, Rakotomamonjy A et al (2018) A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J Neural Eng 15(3):031005

    Article  Google Scholar 

  3. Tu WT, Sun SL et al (2013) Semi-supervised feature extraction for EEG classification. Pattern Anal Appl 16(2):213–222

    Article  MathSciNet  Google Scholar 

  4. She Q, Gan H, Ma Y et al (2016) Scale-dependent signal identification in low-dimensional subspace: motor imagery task classification. Neural Plasticity. https://doi.org/10.1155/2016/7431012

    Article  Google Scholar 

  5. Ma YL, Ding XH, She QS, Luo ZZ et al (2016) Classification of motor imagery EEG signals with support vector machines and particle swarm optimization. Comput Math Methods Med. https://doi.org/10.1155/2016/4941235

    Article  MathSciNet  MATH  Google Scholar 

  6. Li RH, Potter T, Huang WT, Zhang YC et al (2017) Enhancing performance of a hybrid EEG-FNIRS system using channel selection and early temporal features. Front Hum Neurosci 11:462

    Article  Google Scholar 

  7. Liang NY, Saratchandran P, Huang GB et al (2006) Classification of mental tasks from EEG signals using extreme learning machine. Int J Neural Syst 16(01):29–38

    Article  Google Scholar 

  8. Huang GB, Zhu QY, Siew CK et al (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501

    Article  Google Scholar 

  9. Huang GB, Zhou H, Ding X et al (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(2):513–529

    Article  Google Scholar 

  10. Gu Z, Yu Z, Shen Z et al (2013) An online semi-supervised brain-computer interface. IEEE Trans Biomed Eng 60(9):2614–2623

    Article  Google Scholar 

  11. Zhu X, Goldberg AB (2009) Introduction to semi-supervised learning. Synth Lect Artif Intell Mach Learn 3(1):130

    MATH  Google Scholar 

  12. Nicolas-Alonso LF, Corralejo R, Gomez-Pilar J et al (2015) Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces. Neurocomputing 159:186–196

    Article  Google Scholar 

  13. Tian X, Gasso G, Canu S et al (2012) A multiple kernel framework for inductive semi-supervised SVM learning. Neurocomputing 90:46–58

    Article  Google Scholar 

  14. Xu H, Plataniotis KN et al (2017) Affective states classification using EEG and semi-supervised deep learning approaches. IEEE International Workshop on Multimedia Signal Processing, 7813351

  15. Culp M, Michailidis G et al (2008) Graph-based semi-supervised learning. IEEE Trans Pattern Anal Mach Intell 30(1):174–179

    Article  Google Scholar 

  16. Liu W, Wang J, Chang SF et al (2012) Robust and scalable graph-based semisupervised learning. Proc IEEE 100(9):2624–2638

    Article  Google Scholar 

  17. Peng Y, Wang S, Long X et al (2015) Discriminative graph regularized extreme learning machine and its application to face recognition. Neurocomputing 149:340–353

    Article  Google Scholar 

  18. Chang YC et al (2018) Graph-based data augmentation approach for electroencephalogram analysis. Int J Multidiscip Res Stud 1(3):298–307

    Google Scholar 

  19. Guan G et al (2013) Joint Rayleigh coefficient maximization and graph based semi-supervised for the classification of motor imagery EEG. IEEE International Conference on Information and Automation, pp 379–383

  20. Zhong JY, Xu L, Yao DZ et al (2009) Semi-supervised learning based on manifold in BCI. J Electron Sci Technol 7(1):22–26

    Google Scholar 

  21. Li YF, Wang SB, Zhou ZH et al (2016) Graph quality judgement: a large margin expedition. International joint conference on artificial intelligence AAAI Press, pp 9–15

  22. Wang H, Wang SB, Li YF et al (2016) Instance selection method for improving graph-based semi-supervised learning. Proceedings of the 14th Pacific Rim international conference on artificial intelligence, pp 565–573

  23. Yi Y, Qiao S, Zhou W et al (2018) Adaptive multiple graph regularized semi-supervised extreme learning machine. Soft Comput 22(11):3545–3562

    Article  Google Scholar 

  24. Huang G, Song S, Gupta JND et al (2014) Semi-supervised and unsupervised extreme learning machines. IEEE Trans Cybern 44(12):2405–2417

    Article  Google Scholar 

  25. Zhou Y, Liu B, Xia S et al (2015) Semi-supervised extreme learning machine with manifold and pairwise constraints regularization. Neurocomputing 149:180–186

    Article  Google Scholar 

  26. She Q, Hu B, Gan H et al (2018) Safe semi-supervised extreme learning machine for EEG signal classification. IEEE Access 6:49399–49407

    Article  Google Scholar 

  27. Melacci S, Belkin M et al (2011) Laplacian support vector machines trained in the primal. J Mach Learn Res 12(5):1149–1184

    MathSciNet  MATH  Google Scholar 

  28. Gan H, Sang N, Huang R et al (2015) Manifold regularized semi-supervised gaussian mixture model. J Opt Soc Am A 32:566–575

    Article  Google Scholar 

  29. Jebara T, Jun W, Shih-Fu C et al (2009) Graph construction and b-matching for semi-supervised learning. Proceedings of the 26th annual international conference on machine learning, pp 441–448

  30. Gan H, Li Z, Wu W et al (2018) Safety-aware graph-based semi-supervised learning. Expert Syst Appl 107:243–254

    Article  Google Scholar 

  31. Zhou YH, Zhou ZH et al (2016) Large margin distribution learning with cost interval and unlabeled data. IEEE Trans Knowl Data Eng 28:1749–1763

    Article  Google Scholar 

  32. Chen X, Wang T (2017) Combining active learning and semi-supervised learning by using selective label spreading. IEEE international conference on data mining workshops, New Orleans, USA, 17448855

  33. Nie F, Li J, Li X et al (2016) Parameter-free auto-weighted multiple graph learning: a framework for multiview clustering and semi-supervised classification. International joint conference on artificial intelligence AAAI Press, New York, USA, pp 1881–1887

  34. Song J, Gao L et al (2016) Optimized graph learning using partial tags and multiple features for image and video annotation. IEEE Trans Image Process 25(11):4999–5011

    Article  MathSciNet  Google Scholar 

  35. Biggs N et al (1998) Spectral graph theory. Bull Lond Math Soc 30(2):196–223

    Article  Google Scholar 

  36. Joachims T et al (1999) Transductive inference for text classification using support vector machines. Proceedings of the 16th international conference on machine learning, San Francisco, USA, 99: 200–209

  37. Tangermann M, Muller KR, Aertsen A, Birbaumer N, Braun C, Brunner C et al (2012) Review of the BCI competition IV. Front Neurosci 6:55

    Article  Google Scholar 

  38. Ang KK, Chin ZY, Wang CC, Guan CT, Zhang HH et al (2012) Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci 6:39

    Article  Google Scholar 

  39. Meng M, Zhu JQ, She QS, Ma YL et al (2016) Two-level feature extraction method for multi-class motor imagery EEG. Acta Automatica Sinica 42:1915–1922

    Google Scholar 

  40. Blankertz B, Klaus-Robert M, Krusienski DJ et al (2006) The BCI competition III: validating alternative approaches to actual BCI problems. IEEE Trans Neural Syst Rehabil Eng 14(2):153–159

    Article  Google Scholar 

  41. Gan HT, Sang N, Huang R et al (2015) Manifold regularized semi-supervised gaussian mixture model. J Opt Soc Am A-Opt Image Sci Vis 32:566–575

    Article  Google Scholar 

  42. Gan HT, Luo ZZ, Meng M, Ma YL, She QS et al (2016) A risk degree-based safe semi-supervised learning algorithm. Int J Mach Learn Cybern 7:85–94

    Article  Google Scholar 

  43. Hamilton W L, Ying R, Leskovec J et al (2017) Inductive representation learning on large graphs. Proceedings of the 31th Conference on Neural Information Processing Systems, Long Beach, CA, USA, pp 1024–1034

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China under Grant Nos. 61871427 and 61971168, Key Research & Development Project of Zhejiang Province (2020C04009) and Graduate Education & Teaching Reform Project of Hangzhou Dianzi University (No. JXGG2019ZD001).

Author information

Authors and Affiliations

  1. School of Automation, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China

    Qingshan She, Jie Zou, Ming Meng, Yingle Fan & Zhizeng Luo

  2. Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, 310018, Zhejiang, China

    Qingshan She

Authors
  1. Qingshan She
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Zou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ming Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yingle Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhizeng Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qingshan She.

Ethics declarations

Conflict of interests

The authors declare that there is no conflict of interests regarding the publication of this article.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

She, Q., Zou, J., Meng, M. et al. Balanced Graph-based regularized semi-supervised extreme learning machine for EEG classification. Int. J. Mach. Learn. & Cyber. 12, 903–916 (2021). https://doi.org/10.1007/s13042-020-01209-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-020-01209-0

Keywords

Search

Navigation