Formative semi-supervised learning based on adaptive combined model for brain–computer interface | International Journal of Machine Learning and Cybernetics Skip to main content
Springer Nature Link
Log in

Formative semi-supervised learning based on adaptive combined model for brain–computer interface

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

Abstract

The recognition of Electroencephalogram (EEG) signals has been an important research field in Brain–computer interface. The semi-supervised classification can improve the classification performance of EEG. Formative Semi-Supervised Learning (FSSL) uses the affinity matrix between samples and Expectation-maximization (EM) to mine hidden features between samples. It isn’t effective to apply FSSL to EEG classification directly due to the non-stationary and nonlinear of EEG. FSSL only uses Euclidean distances in the affinity matrix, which is not sufficient to process EEG signals and may restrict the effect of subsequent feature extraction. In response to this problem, combined model formative Semi-Supervised Learning (CMFSSL) was proposed to construct a combined model based on Euclidean metric and Riemannian metric. The weight update strategy is designed to constrain the model in the EM algorithm, and the weights of the combined model are constantly adjusted to construct a better basic model. Then the hidden features extracted based on the combined model are used to construct the training set and the Broad Learning System is used for classification. The algorithm is verified on three BCI data sets and compared with several state-of-the-art methods. The experimental results show that the algorithm achieves better results on three data sets: 74.86%, 73.52%, 75.49% and has a good effect on cross-domain classification. The combined model uses adaptive weights to build a better data model for subsequent hidden features, which not only maintains the original security advantages, but also improves the classification results.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The datasets used during the current study are available. The BCI Competition III Dataset 4a can be obtained from https://www.bbci.de/competition/iii/desc_IVa.html. The BCI Competition IV Dataset 2a can be obtained from http://www.bbci.de/competition/iv/desc_2a.pdf. The BCI Competition IV Dataset 1 can be obtained from http://www.bbci.de/competition/iv/desc_1.html.

References

  1. Banan A, Nasiri A, Taheri-Garavand A (2020) Deep learning-based appearance features extraction for automated carp species identification[J]. Aquacult Eng 89:102053

    Article  Google Scholar 

  2. Barachant A, Bonnet S, Congedo M et al (2011) Multiclass brain-computer interface classification by Riemannian geometry[J]. IEEE Trans Biomed Eng 59(4):920–928

    Article  Google Scholar 

  3. Bishop CM, Nasrabadi NM (2006) Pattern recognition and machine learning[M]. Springer, New York

    Google Scholar 

  4. Blankertz B, Dornhege G, Krauledat M et al (2007) The non-invasive Berlin brain-computer interface: fast acquisition of effective performance in untrained subjects[J]. NeuroImage 37(2):539–550

    Article  Google Scholar 

  5. Blum A, Chawla S, et al (2001) Learning from labeled and unlabeled data using graph mincuts[C]. Proceedings of the 18th international conference on machine learning: 19-26

  6. Chen CLP, Liu Z (2017) Broad learning system: an effective and efficient incremental learning system without the need for deep architecture[J]. IEEE Trans Neural Netw Learn Syst 29(1):10–24

    Article  MathSciNet  Google Scholar 

  7. Chen W, Sharifrazi D, Liang G et al (2022) Accurate discharge coefficient prediction of streamlined weirs by coupling linear regression and deep convolutional gated recurrent unit[J]. Eng Appl Comput Fluid Mech 16(1):965–976

    Google Scholar 

  8. Congedo M, Barachant A, Bhatia R (2017) Riemannian geometry for EEG-based brain-computer interfaces: a primer and a review[J]. Brain Comput Interfaces 4(3):155–174

    Article  Google Scholar 

  9. Dong A, Chung FL, Deng Z et al (2015) Semi-supervised SVM with extended hidden features[J]. IEEE Trans Cybern 46(12):2924–2937

    Article  Google Scholar 

  10. Dong A, Chung F, Wang S (2016) Semi-supervised classification method through oversampling and common hidden space[J]. Inform Sci 349:216–228

    Article  Google Scholar 

  11. Dornhege G, Blankertz B, Curio G et al (2004) Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms[J]. IEEE Trans Biomed Eng 51(6):993–1002

    Article  Google Scholar 

  12. Fan Y, Xu K, Wu H et al (2020) Spatiotemporal modeling for nonlinear distributed thermal processes based on KL decomposition, MLP and LSTM network[J]. IEEE Access 8:25111–25121

    Article  Google Scholar 

  13. Gan H, Sang N, Huang R (2015) Manifold regularized semi-supervised Gaussian mixture model[J]. J Opt Soc Am A 32(4):566–575

    Article  Google Scholar 

  14. Gong X, Zhang T, Chen C L P, et al (2021) Research review for broad learning system: algorithms, theory, and applications[J]. IEEE Trans Cybern

  15. Graimann B, Allison B, Pfurtscheller G (2010) Brain-computer interfaces: a gentle introduction[J]. Revolut Hum Comput Interact Brain Comput Interfaces: 1–27

  16. Li Y, Guan C (2006) A semi-supervised SVM learning algorithm for joint feature extraction and classification in brain computer interfaces[C]. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 2570-2573

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

    Article  Google Scholar 

  18. Joachims T (1999) Transductive inference for text classification using support vector machines[C]. In: Proceedings of the 16th international conference on machine learning 99: 200–209

  19. Li YF, Zhou ZH (2014) Towards making unlabeled data never hurt[J]. IEEE Trans Pattern Anal Mach Intell 37(1):175–188

    Google Scholar 

  20. Li YF, Guo LZ, Zhou ZH (2019) Towards safe weakly supervised learning[J]. IEEE Trans Pattern Anal Mach Intell 43(1):334–346

    Google Scholar 

  21. Liu Z, Zhou J, Chen C L P (2017) Broad learning system: feature extraction based on K-means clustering algorithm[C]. In: 2017 4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS). IEEE: 683-687

  22. McFarland DJ, Wolpaw JR (2017) EEG-based brain-computer interfaces[J]. Curr Opin Biomed Eng 4:194–200

    Article  Google Scholar 

  23. Moakher M (2005) A differential geometric approach to the geometric mean of symmetric positive-definite matrices[J]. SIAM J Matrix Anal Appl 26(3):735–747

    Article  MathSciNet  Google Scholar 

  24. Nam CS, Anton N, Fabien L, (eds) (2018) Brain-computer interfaces handbook: technological and theoretical advances[M]. CRC Press

  25. Pfurtscheller G, Neuper C (2001) Motor imagery and direct brain-computer communication[J]. Proc IEEE 89(7):1123–1134

    Article  Google Scholar 

  26. Rao RPN (2013) Brain-computer interfacing: an introduction[M]. Cambridge University Press, Cambridge

    Book  Google Scholar 

  27. Shanechi MM (2019) Brain-machine interfaces from motor to mood[J]. Nat Neurosci 22(10):1554–1564

    Article  Google Scholar 

  28. She Q, Zou J, Meng M et al (2021) Balanced graph-based regularized semi-supervised extreme learning machine for EEG classification[J]. Int J Mach Learn Cybern 12:903–916

    Article  Google Scholar 

  29. Song Z, Yang X, Xu Z, et al (2022) Graph-based semi-supervised learning: a comprehensive review[J]. IEEE Trans Neural Netw Learn Syst

  30. Sun S, Zhou J (2014) A review of adaptive feature extraction and classification methods for EEG-based brain-computer interfaces[C]. In: 2014 International Joint Conference on Neural Networks (IJCNN). IEEE: 1746-1753

  31. Tu W, Sun S (2013) Semi-supervised feature extraction for EEG classification[J]. Pattern Anal Appl 16:213–222

    Article  MathSciNet  Google Scholar 

  32. Vaid S, Singh P, Kaur C (2015) EEG signal analysis for BCI interface: A review[C]. In: 2015 fifth international conference on advanced computing and communication technologies. IEEE, 143-147

  33. Van Engelen JE, Hoos HH (2020) A survey on semi-supervised learning[J]. Mach Learn 109(2):373–440

    Article  MathSciNet  Google Scholar 

  34. Waytowich NR, Lawhern VJ, Bohannon AW et al (2016) Spectral transfer learning using information geometry for a user-independent brain-computer interface[J]. Front Neurosci 10:430

    Article  Google Scholar 

  35. Xu Y, Hua J, Zhang H, et al. (2019) Improved transductive support vector machine for a small labelled set in motor imagery-based brain-computer interface[J]. Comput Intell Neurosci 2019

  36. Yang T, Priebe CE (2011) The effect of model misspecification on semi-supervised classification[J]. IEEE Trans Pattern Anal Mach Intell 33(10):2093–2103

    Article  Google Scholar 

  37. Yger F, Berar M, Lotte F (2016) Riemannian approaches in brain-computer interfaces: a review[J]. IEEE Trans Neural Syst Rehabilit Eng 25(10):1753–1762

    Article  Google Scholar 

  38. Zanini P, Congedo M, Jutten C et al (2017) Transfer learning: a riemannian geometry framework with applications to brain-computer interfaces[J]. IEEE Trans Biomed Eng 65(5):1107–1116

    Article  Google Scholar 

  39. Zhu X (2011) Cross-domain semi-supervised learning using feature formulation[J]. IEEE Trans Syst Man Cybern Part B (Cybern) 41(6):1627–1638

    Article  Google Scholar 

  40. Zhu X, Wu X (2004) Class noise vs. attribute noise: a quantitative study[J]. Artifi Intell Rev 2:177–210

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Nature Science Foundation of China (61971168, 62071161, 62271181), Zhejiang Provincial Natural Science Foundation of China (LZ22F010003).

Author information

Author notes

  1. Mengting Li, Zhen Cao and Ming Meng have contributed equally to this work.

Authors and Affiliations

  1. College of Automation, Hangzhou Dianzi University, Hangzhou, 310018, China

    Yunyuan Gao, Mengting Li, Zhen Cao & Ming Meng

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

    Yunyuan Gao

Authors
  1. Yunyuan Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mengting Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhen Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ming Meng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yunyuan Gao.

Ethics declarations

Conflict of interest

The authors declare that they have no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gao, Y., Li, M., Cao, Z. et al. Formative semi-supervised learning based on adaptive combined model for brain–computer interface. Int. J. Mach. Learn. & Cyber. 15, 371–382 (2024). https://doi.org/10.1007/s13042-023-01914-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-023-01914-6

Keywords

Search

Navigation