Skip to main content

Advertisement

SpringerLink
Log in

EEG classification across sessions and across subjects through transfer learning in motor imagery-based brain-machine interface system

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Transfer learning enables the adaption of models to handle mismatches of distributions across sessions or across subjects. In this paper, we proposed a new transfer learning algorithm to classify motor imagery EEG data. By analyzing the power spectrum of EEG data related to motor imagery, the shared features across sessions or across subjects, namely, the mean and variance of model parameters, are extracted. Then, select the data sets that were most relevant to the new data set according to Euclidean distance to update the shared features. Finally, utilize the shared features and subject/session-specific features jointly to generate a new model. We evaluated our algorithm by analyzing the motor imagery EEG data from 10 healthy participants and a public data set from BCI competition IV. The classification accuracy of the proposed transfer learning is higher than that of traditional machine learning algorithms. The results of the paired t test showed that the classification results of PSD and the transfer learning algorithm were significantly different (p = 2.0946e-9), and the classification results of CSP and the transfer learning algorithm were significantly different (p = 1.9122e-6). The test accuracy of data set 2a of BCI competition IV was 85.7% ± 5.4%, which was higher than that of related traditional machine learning algorithms. Preliminary results suggested that the proposed algorithm can be effectively applied to the classification of motor imagery EEG signals across sessions and across subjects and the performance is better than that of the traditional machine learning algorithms. It can be promising to be applied to the field of brain-computer interface (BCI).

Graphical abstract

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
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Wolpaw JR, Birbaumer N, McFarland DJ et al (2002) Brain-computer interfaces for communication and control. Clin Neurophysiol 113(7):67–91. https://doi.org/10.1016/S1388-2457(02)00057-3

    Article  Google Scholar 

  2. Shih JJ, Krusienski DJ, Wolpaw JR (2012) Brain-computer interfaces in medicine. Mayo Clin Proc 87(3):268–279. https://doi.org/10.1016/j.mayocp.2011.12.008

    Article  PubMed  PubMed Central  Google Scholar 

  3. Kübler A, Neumann N, Kaiser J, Kotchoubey B, Hinterberger T, Birbaumer NP (2001) Brain-computer communication: self- regulation of slow cortical potentials for verbal communication. Arch Phys Med Rehabil 82(11):1533–1539. https://doi.org/10.1053/apmr.2001.26621

    Article  PubMed  Google Scholar 

  4. Birbaumer N (2006) Breaking the silence: brain-computer interfaces (BCI) for communication and motor control. Psycho-physiology 43(6):517–532. https://doi.org/10.1111/j.1469-8986.2006.00456.x

    Article  Google Scholar 

  5. Birbaumer N, Murguialday AR, Cohen L (2008) Brain-computer interface in paralysis. Curr Opin Neurol 21(6):634–638. https://doi.org/10.1097/wco.0b013e328315ee2d

    Article  PubMed  Google Scholar 

  6. Fuchs T, Birbaumer N, Lutzenberger W et al (2003) Neurofeedback treatment for attention-deficit/hyperactivity disorder in children: a comparison with methylphenidate. Appl Psychophysiol Biofeedback 28(1):1–12. https://doi.org/10.1023/a:1022353731579

    Article  PubMed  Google Scholar 

  7. Chen XG, Wang YJ (2018) Research progress of non - invasive brain machine interface based on EEG. Sci Technol Rev 36(12):22–30

    Google Scholar 

  8. Xu M, Xiao X, Wang Y et al (2018) A brain-computer interface based on miniature-event-related potentials induced by very small lateral visual stimuli. IEEE Trans Biomed Eng 65(5):1166–1175. https://doi.org/10.1109/TBME.2018.2799661

    Article  PubMed  Google Scholar 

  9. Pfurtscheller G, Silva FHLD (1999) Event-related eeg/meg synchronization and desynchronization. Clin Neurophysiol 110(11):1842–1857. https://doi.org/10.1016/S1388-2457(99)00141-8

    Article  CAS  PubMed  Google Scholar 

  10. Birbaumer N, Cohen LG (2007) Brain-computer interfaces: communication and restoration of movement in paralysis. J Physiol (Oxford) 579(3):621–636. https://doi.org/10.1113/jphysiol.2006.125633

    Article  CAS  Google Scholar 

  11. Abdulkader SN, Atia A, Mostafa MSM (2015) Brain computer interfacing: applications and challenges. Egypt Inf J 16(2):213–230. https://doi.org/10.1016/j.eij.2015.06.002

    Article  Google Scholar 

  12. Hsu WY (2012) Fuzzy hopfield neural network clustering for single-trial motor imagery eeg classification. Expert Syst Appl 39(1):1055–1061. https://doi.org/10.1016/j.eswa.2011.07.106

    Article  Google Scholar 

  13. Shi JH, Shen JZ, Wang P (2012) Feature extraction and classification of four-class motor imagery eeg data. J Zhejiang Univ (Eng Sci) 46(2):338–344. https://doi.org/10.3785/j.issn.1008-973X.2012.02.025

    Article  Google Scholar 

  14. Zhao L, Guo XH, Geng LQ (2013) Research on multi-class motor imagery eeg signal processing. Chin J Biomed Eng 92(92):65–81. https://doi.org/10.3969/j.issn.0258-8021.2013.05.019

    Article  Google Scholar 

  15. Blasco JLS, Iáñez E, Ubeda A et al (2012) Visual evoked potential-based brain-machine interface applications to assist disabled people. Expert Syst Appl 39(9):7908–7918. https://doi.org/10.1016/j.eswa.2012.01.110

    Article  Google Scholar 

  16. Chen M, Fang Y, Zheng X (2014) Phase space reconstruction for improving the classification of single trial EEG. Biomed Signal Process Control 11(1):10–16. https://doi.org/10.1016/j.bspc.2014.02.002

    Article  Google Scholar 

  17. Hortal E, Planelles D, Costa A et al (2015) SVM-based brain–machine interface for controlling a robot arm through four mental tasks. Neurocomputing 151:116–121. https://doi.org/10.1016/j.neucom.2014.09.078

    Article  Google Scholar 

  18. Pei YF, Yang SJ (2018) Research progress of EEG algorithm of motor imagery. Beijing Biomed Eng 37(02):208–214

    Google Scholar 

  19. Xiao X, Xu M, Jin J et al (2019) Discriminative canonical pattern matching for single-trial classification of ERP components. IEEE Trans Biomed Eng. https://doi.org/10.1109/TBME.2019.2958641

  20. Wang K, Xu M, Wang Y et al (2020) Enhance decoding of pre-movement EEG patterns for brain–computer interfaces. J Neural Eng 17:016033. https://doi.org/10.1088/1741-2552/ab598f

    Article  PubMed  Google Scholar 

  21. Azab AM, Toth J, Mihaylova LS, Arvaneh M (2018) A review on transfer learning approaches in brain-computer interface. In: Signal processing and machine learning for brain-machine interfaces. The Institution of Engineering and Technology (IET), ch. 5. https://doi.org/10.1049/PBCE114E

  22. Böttger D, Herrmann CS, Cramon DYV (2002) Amplitude differences of evoked alpha and gamma oscillations in two different age groups. Int J Psychophysiol 45(3):245–251. https://doi.org/10.1016/S0167-8760(02)00031-4

    Article  PubMed  Google Scholar 

  23. Bulayeva KB, Pavlova TA, Guseynov GG (1993) Visual evoked potentials: phenotypic and genotypic variability. Behav Genet 23(5):443–447. https://doi.org/10.1007/BF01067978

    Article  CAS  PubMed  Google Scholar 

  24. Kuba M, Kremlacek J, Langrova J, Kubova Z, Szanyi J, Vit F (2012) Aging effect in pattern, motion and cognitive visual evoked potentials. Vis Res 62(none):9–16. https://doi.org/10.1016/j.visres.2012.03.014

    Article  PubMed  Google Scholar 

  25. Zhang B, Lu J , Peitao W, Tang Z (2015) A review on transfer learning for brain-computer interface classification. 2015 5th International Conference on Information Science and Technology (ICIST), 5th international Conferenceon Information Scienceand technology (ICIST). https://doi.org/10.1109/ICIST.2015.7288989

  26. Caseiro R, Henriques JF, Martins P, Batista J(2015) Beyond the shortest path: unsupervised domain adaptation by sampling subspaces along the spline flow. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. https://doi.org/10.1109/CVPR.2015.7299009

  27. Lotte F, Guan C (2011) Regularizing common spatial patterns to improve bci designs: unified theory and new algorithms. IEEE Trans Biomed Eng 58(2):355–362. https://doi.org/10.1109/TBME.2010.2082539

    Article  PubMed  Google Scholar 

  28. Fazli S, Popescu F, Danóczy M, Blankertz B, Müller K-R, Grozea C (2009) Subject-independent mental state classification in single trials. Neural Netw 22(9):1305–1312. https://doi.org/10.1016/j.neunet.2009.06.003

    Article  PubMed  Google Scholar 

  29. Cho H, Ahn M, Kim K, Chan Jun S (2015) Increasing session-to-session transfer in a brain–computer interface with on-site background noise acquisition. J Neural Eng 12(6):066009. https://doi.org/10.1088/1741-2560/12/6/066009

    Article  PubMed  Google Scholar 

  30. Jayaram V, Alamgir M, Altun Y, Schölkopf B, Grosse-Wentrup M (2015) Transfer learning in brain-computer interfaces. IEEE Comput Intell Mag 11(1):20–31. https://doi.org/10.1109/MCI.2015.2501545

    Article  Google Scholar 

  31. Li Z (2012) EEG power spectrum estimation based on motor imagery. Electron Meas Technol

  32. Akin M, Kiymik MK (2000) Application of periodogram and ar spectral analysis to eeg signals. J Med Syst 24(4):247–256. https://doi.org/10.1023/A:1005553931564

    Article  CAS  PubMed  Google Scholar 

  33. Li L, Xiao L, Chen L (2009) Differences of EEG between eyes-open and eyes-closed states based on autoregressive method. J Electron Sci Technol China 7(2):175–179

    Google Scholar 

  34. Koles ZJ, Lazar MS, Zhou SZ (1990) Spatial patterns underlying population differences in the background eeg. Brain Topogr 2(4):275–284. https://doi.org/10.1007/BF01129656

    Article  CAS  PubMed  Google Scholar 

  35. Müller-Gerking J, Pfurtscheller G, Flyvbjerg H (1999) Designing optimal spatial filters for single-trial eeg classification in a movement task. Clin Neurophysiol 110(5):787–798. https://doi.org/10.1016/S1388-2457(98)00038-8

    Article  PubMed  Google Scholar 

  36. Chin ZY, Ang KK, Wang C, Guan C, Zhang H (2009) Multi-class filter bank common spatial pattern for four-class motor imagery BCI. International Conference of the IEEE Engineering in Medicine & Biology Society. Conf Proc IEEE Eng Med Biol Soc. https://doi.org/10.1109/IEMBS.2009.5332383

  37. Lemm S, Blankertz B, Curio G, Muller KR (2005) Spatio-spectral filters for improving the classification of single trial eeg. IEEE Trans Biomed Eng 52(9):1541–1548. https://doi.org/10.1109/TBME.2005.851521

    Article  PubMed  Google Scholar 

  38. Bashashati A, Fatourechi M, Ward RK, Birch GE (2007) A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals. J Neural Eng 4(2):R32–R57. https://doi.org/10.1088/1741-2560/4/2/R03

    Article  PubMed  Google Scholar 

  39. Song-Yun X, Zhen-Zhong Z, Jin-Xiao Y, Kun Z (2007) Research and evaluation on some eeg processing methods. Comput Simul. https://doi.org/10.1016/S1872-2075(07)60067-3

  40. Keirn ZA, Aunon JI (1990) A new mode of communication between man and his surroundings. IEEE Trans Biomed Eng 37(12):1209–1214. https://doi.org/10.1109/10.64464

    Article  CAS  PubMed  Google Scholar 

  41. Buttfield A, Ferrez PW, Millan JR (2006) Towards a robust bci: error potentials and online learning. IEEE Trans Neural Syst Rehab Eng 14(2):164–168. https://doi.org/10.1109/tnsre.2006.875555

    Article  Google Scholar 

  42. Gao S, Zhang Z, Gao XR, Yang F (2006) Neural engineering and neural prostheses. Chin J Med Instrum 30(2):79

    Google Scholar 

  43. Subasi A, Ismail Gursoy M (2010) EEG signal classification using PCA, ICA, LDA and support vector machines. Exp Syst Appl 37(12):8659–8666. https://doi.org/10.1016/j.eswa.2010.06.065

    Article  Google Scholar 

  44. Brunner C, Leeb R, Müller-Putz GR et al. (2008) BCI Competition 2008 – Graz data set A. http://bbci.de/competition/iv/desc_2a.pdf

  45. Wang, J., Chen, Y., Hao, S., Feng, W., & Shen, Z.. (2017). Balanced distribution adaptation for transfer learning. 2017 IEEE International Conference on Data Mining (ICDM). IEEE. https://doi.org/10.1109/ICDM.2017.150

  46. Weiss K, Khoshgoftaar TM, Wang DD (2016) A survey of transfer learning. J Big Data 3(1):9. https://doi.org/10.1186/s40537-016-0043-6

    Article  Google Scholar 

  47. Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  48. Liao X, Xue Y, Carin L(2005) Logistic regression with an auxiliary data source. In: Proceedings of the 22nd international conference on machine learning. ACM 505–512. https://doi.org/10.1145/1102351.1102415

  49. Ben-David S, Blitzer J, Crammer K, Pereira F (2007) Analysis of representations for domain adaptation. Proc NIPS 1(2):137–144

    Google Scholar 

  50. Bergamo A, Torresani L (2010) Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. Proc NIPS 2:181–189

    Google Scholar 

  51. Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: An unsupervised approach. Proc ICCV:999–1006. https://doi.org/10.1109/ICCV.2011.6126344

  52. Huang J, Smola A, Gretton A, Borgwardt K, Scholkopf B (2006) Correcting sample selection bias by unlabeled data. In Proc NIPS 2:601–608

    Google Scholar 

  53. Kulis B, Saenko K, Darrell T (2011) What you saw is not what you get: domain adaptation using asymmetric kernel transforms. Proc CVPR:1785–1792. https://doi.org/10.1109/CVPR.2011.5995702

  54. Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. Proc ECCV:213–226. https://doi.org/10.1007/978-3-642-15561-1_16

  55. Shimodaira H (2000) Improving predictive inference under covariate shift by weighting the log-likelihood function. J Statist Plann Inference 90(2):227–244. https://doi.org/10.1016/S0378-3758(00)00115-4

    Article  Google Scholar 

Download references

Funding

This project is supported by the National Key R&D Program of China (No.2018YFC1312900), National Natural Science Foundation of China (No. 61976133), and 111 Project (No. D18003).

Author information

Authors and Affiliations

  1. School of Mechatronic Engineering and Automation, Research Center of Brain Computer Engineering, Shanghai University, Shanghai, 200444, China

    Minmin Zheng, Banghua Yang & Yunlong Xie

  2. School of Mechanical and Electrical Engineering, Putian University, Putian, Fujian, China

    Minmin Zheng

Authors
  1. Minmin Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Banghua Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yunlong Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Banghua Yang.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, M., Yang, B. & Xie, Y. EEG classification across sessions and across subjects through transfer learning in motor imagery-based brain-machine interface system. Med Biol Eng Comput 58, 1515–1528 (2020). https://doi.org/10.1007/s11517-020-02176-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-020-02176-y

Keywords

Search

Navigation