Skip to main content
SpringerLink
Log in

Single-Subject vs. Cross-Subject Motor Imagery Models

  • Conference paper
  • First Online:
HCI International 2022 - Late Breaking Papers. Multimodality in Advanced Interaction Environments (HCII 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13519))

Included in the following conference series:

Abstract

This paper compares the performance of machine learning algorithms trained and tested on single-subject EEG data compared to nine-person cross-subject EEG data from the BCI IV 2a dataset. To compare the performance of single-subject and cross-subject EEG models, we implement eight machine learning algorithms and test them on EEG motor imagery data. Single-subject models had higher average accuracies compared to cross-subject trained models for 7 out of 8 machine learning models.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993–1022 (2003)

    MATH  Google Scholar 

  2. Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 144–152 (1992)

    Google Scholar 

  3. Chen, X., Wang, Z.J., McKeown, M.J.: Shrinkage-to-tapering estimation of large covariance matrices. IEEE Trans. Signal Process. 60(11), 5640–5656 (2012)

    Article  MathSciNet  Google Scholar 

  4. Cimtay, Y., Ekmekcioglu, E.: Investigating the use of pretrained convolutional neural network on cross-subject and cross-dataset EEG emotion recognition. Sensors 20(7), 2034 (2020)

    Article  Google Scholar 

  5. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  6. Duan, L., Zhong, H., Miao, J., Yang, Z., Ma, W., Zhang, X.: A voting optimized strategy based on elm for improving classification of motor imagery BCI data. Cogn. Comput. 6(3), 477–483 (2014)

    Article  Google Scholar 

  7. Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)

    Article  MathSciNet  Google Scholar 

  8. Hersche, M., Rellstab, T., Schiavone, P., Cavigelli, L., Benini, L., Rahimi, A.: Fast and accurate multiclass inference for mi-bcis using large multiscale temporal and spectral features, pp. 1690–1694 (2018). https://doi.org/10.23919/EUSIPCO.2018.8553378

  9. Ho, T.K.: Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 1, pp. 278–282. IEEE (1995)

    Google Scholar 

  10. Hu, J.: Automated detection of driver fatigue based on adaboost classifier with EEG signals. Front. Comput. Neurosci. 11 (2017). https://doi.org/10.3389/fncom.2017.00072,https://www.frontiersin.org/article/10.3389/fncom.2017.00072

  11. Jayarathne, I., Cohen, M., Amarakeerthi, S.: Person identification from EEG using various machine learning techniques with inter-hemispheric amplitude ratio. PloS one 15(9), e0238872 (2020)

    Article  Google Scholar 

  12. Kastrati, A., et al.: Eegeyenet: a simultaneous electroencephalography and eye-tracking dataset and benchmark for eye movement prediction. arXiv preprint arXiv:2111.05100 (2021)

  13. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  14. Ledoit, O., Wolf, M.: A well-conditioned estimator for large-dimensional covariance matrices. J. Multivariate Anal. 88(2), 365–411 (2004)

    Article  MathSciNet  Google Scholar 

  15. Leeb, R., Brunner, C., Müller-Putz, G., Schlögl, A., Pfurtscheller, G.: Bci competition 2008-graz data set b. Graz University of Technology, Austria, pp. 1–6 (2008)

    Google Scholar 

  16. Lotte, F., et al.: A review of classification algorithms for EEG-based brain-computer interfaces: a 10 year update. J. Neural Eng. 15(3), 031005 (2018)

    Article  Google Scholar 

  17. Luo, C., Li, X., Wang, L., He, J., Li, D., Zhou, J.: How does the data set affect CNN-based image classification performance? In: 2018 5th International Conference on Systems and Informatics (ICSAI), pp. 361–366 (2018). https://doi.org/10.1109/ICSAI.2018.8599448

  18. Pandey, P., Seeja, K.: Subject independent emotion recognition from EEG using VMD and deep learning. J. King Saud Univ.-Comput. Inf. Sci. (2019)

    Google Scholar 

  19. Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., arnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates, Inc. (2019), http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf

  20. Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

  21. Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T.H., Faubert, J.: Deep learning-based electroencephalography analysis: a systematic review. J. Neural Eng. 16(5), 051001 (2019)

    Article  Google Scholar 

  22. Wang, Z., Hope, R.M., Wang, Z., Ji, Q., Gray, W.D.: Cross-subject workload classification with a hierarchical bayes model. NeuroImage 59(1), 64–69 (2012)

    Article  Google Scholar 

  23. Zeynali, M., Seyedarabi, H.: Eeg-based single-channel authentication systems with optimum electrode placement for different mental activities. Biomed. J. 42(4), 261–267 (2019)

    Article  Google Scholar 

  24. Zhang, C., Liu, C., Zhang, X., Almpanidis, G.: An up-to-date comparison of state-of-the-art classification algorithms. Expert Syst. Appl. 82, 128–150 (2017). https://doi.org/10.1016/j.eswa.2017.04.003,https://www.sciencedirect.com/science/article/pii/S0957417417302397

Download references

Author information

Authors and Affiliations

  1. Swarthmore College, Swarthmore, PA, 19081, USA

    Joseph Geraghty & George Schoettle

Authors
  1. Joseph Geraghty
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. George Schoettle
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joseph Geraghty .

Editor information

Editors and Affiliations

  1. The Open University of Japan, Chiba, Japan

    Masaaki Kurosu

  2. Tokyo University of Science, Tokyo, Saitama, Japan

    Sakae Yamamoto

  3. Tokyo City University, Tokyo, Japan

    Hirohiko Mori

  4. Soar Technology Inc., Orlando, FL, USA

    Dylan D. Schmorrow

  5. Katmai Government Services, Orlando, FL, USA

    Cali M. Fidopiastis

  6. Smart Future Initiative, Frankfurt am Main, Germany

    Norbert A. Streitz

  7. Kyushu University, Fukuoka, Japan

    Shin'ichi Konomi

A Appendix

A Appendix

Accuracy for each single-subject model. Bold indicates the highest performing accuracy for a subject. The algorithm order is consistent with previous tables in the paper (Table 3, 4, 5, 6, 7, 8, 9, 10 and 11).

Table 3. Subject 1 model accuracies
Full size table
Table 4. Subject 2 model accuracies
Full size table
Table 5. Subject 3 model accuracies
Full size table
Table 6. Subject 4 model accuracies
Full size table
Table 7. Subject 5 model accuracies
Full size table
Table 8. Subject 6 model accuracies
Full size table
Table 9. Subject 7 model accuracies
Full size table
Table 10. Subject 8 model accuracies
Full size table
Table 11. Subject 9 model accuracies
Full size table

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Geraghty, J., Schoettle, G. (2022). Single-Subject vs. Cross-Subject Motor Imagery Models. In: Kurosu, M., et al. HCI International 2022 - Late Breaking Papers. Multimodality in Advanced Interaction Environments. HCII 2022. Lecture Notes in Computer Science, vol 13519. Springer, Cham. https://doi.org/10.1007/978-3-031-17618-0_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-17618-0_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-17617-3

  • Online ISBN: 978-3-031-17618-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation