Distributions of electroencephalogram (EEG) data vary greatly across different subjects. It is a very important issue how to generalize models across subjects. In this paper, an algorithm is proposed to build high-performance cross-subject motor-imagery brain–computer interfaces (BCIs) for a new subject. First, a novel distance metric is proposed to quantify the joint distribution discrepancy (JDD) between data from different subjects. It gives better evaluations for discrepancies between different distributions than conventional probabilistic metrics. Moreover, it can be extended to design many novel algorithms. Second, a support vector machine combined with JDD (JDMSVM) is proposed for cross-subject classification. For dataset dataIVa, the JDMSVM runs best under 9 out of 15 situations and averagely outperforms counterparts by 10.1%, 9.5%, 3.2% and 1.7%, respectively. For GigaDataset, JDMSVM runs best under 8 of 12 conditions. It averagely outperforms its counterparts by 10.4%, 5.3%, 2.7% and 2.4%, respectively. The experiments demonstrate that the proposed algorithm is effective and competitive for cross-subject BCI.

This paper was recommended by Regional Editor Tongquan Wei.

Keywords:

References

1. J. Wang and Q. Wei , Classification of EEG signals based on filter bank and sparse representation in motor imagery brain–computer interfaces, J. Circuits Syst. Comput. 29 (2020) 2050034. Link, Google Scholar
2. Y. Xu et al., Transfer learning based on regularized common spatial patterns using cosine similarities of spatial filters for motor-imagery BCI, J. Circuits Syst. Comput. 28 (2019) 1950123. Link, Web of Science, Google Scholar
3. L. Zhang, Q. Wei and Z. Lu , Combined optimization of frequency band and time segment using quantum particle swarm algorithm for brain–computer interfaces, J. Circuits Syst. Comput. 30 (2021) 2150234. Link, Google Scholar
4. F. Lotte et al., A review of classification algorithms for EEG-based brain–computer interfaces: A 10 year update, J. Neural Eng. 15 (2018) 031005. Crossref, Web of Science, Google Scholar
5. M. Fira, H.-N. Costin and L. Goraş , On the classification of ECG and EEG signals with various degrees of dimensionality reduction, Biosensors 11 (2021) 161. Crossref, Google Scholar
6. Y. Zhang, G. Zhou, J. Jin, Q. Zhao, X. Wang and A. Cichocki , Sparse Bayesian classification of EEG for brain–computer interface, IEEE Trans. Neural Netw. Learn. Syst. 27 (2015) 2256–2267. Crossref, Google Scholar
7. C. Benaroch et al., Long-term BCI training of a tetraplegic user: Adaptive Riemannian classifiers and user training, Front. Hum. Neurosci. 15 (2021) 635–653. Crossref, Google Scholar
8. A. Miladinović et al., Effect of power feature covariance shift on BCI spatial-filtering techniques: A comparative study, Comput. Methods Programs Biomed. 198 (2021) 105808. Crossref, Google Scholar
9. J. Minguillon, M. A. Lopez-Gordo and F. Pelayo , Trends in EEG-BCI for daily-life: Requirements for artifact removal, Biomed. Signal Process. Control 31 (2017) 407–418. Crossref, Web of Science, Google Scholar
10. D. Wu, Y. Xu and B. L. Lu , Transfer learning for EEG-based brain–computer interfaces: A review of progress made since 2016, IEEE Trans. Cogn. Develop. Syst. 14(1) (2020) 4–19. Crossref, Google Scholar
11. Z. Wan et al., A review on transfer learning in EEG signal analysis, Neurocomputing 421 (2021) 1–14. Crossref, Google Scholar
12. J. Quinonero-Candela, M. Sugiyama, A. Schwaighofer and N. D. Lawrence , Dataset Shift in Machine Learning (Mit Press, 2008). Crossref, Google Scholar
13. S. Si, D. Tao and B. Geng , Bregman divergence-based regularization for transfer subspace learning, IEEE Trans. Knowl. Data Eng. 22 (2009) 929–942. Crossref, Google Scholar
14. M. Baktashmotlagh, M. Harandi and M. Salzmann , Distribution-matching embedding for visual domain adaptation, J. Mach. Learn. Res. 17 (2016) 1–30. Google Scholar
15. S. J. Pan, I. W. Tsang, J. T. Kwok and Q. Yang , Domain adaptation via transfer component analysis, IEEE Trans. Neural Netw. 22 (2010) 199–210. Crossref, Google Scholar
16. T. Tommasi, F. Orabona and B. Caputo , Learning categories from few examples with multi model knowledge transfer, IEEE Trans. Pattern Anal. Mach. Intell. 36 (2013) 928–941. Crossref, Google Scholar
17. P. Zanini, M. Congedo, C. Jutten, S. Said and Y. Berthoumieu , Transfer learning: A Riemannian geometry framework with applications to brain–computer interfaces, IEEE Trans. Biomed. Eng. 65 (2017) 1107–1116. Crossref, Web of Science, Google Scholar
18. C. Cortes, M. Mohri, M. Riley and A. Rostamizadeh , Sample selection bias correction theory, ALT 2008: Algorithmic Learning Theory, Lecture Notes in Computer Science, Vol. 5254 (Springer, 2008), pp. 38–53. Crossref, Google Scholar
19. M. Sugiyama, S. Nakajima, H. Kashima, P. Buenau and M. Kawanabe , Direct importance estimation with model selection and its application to covariate shift adaptation, Adv. Neural Inf. Process. Syst. 20 (2007) 1–8. Google Scholar
20. S. Bickel, M. Brückner and T. Scheffer , Discriminative learning for differing training and test distributions, Proc. 24th Int. Conf. Machine Learning (Association for Computing Machinery, 2007), pp. 81–88. Crossref, Google Scholar
21. B. Gong, K. Grauman and F. Sha , Connecting the dots with landmarks: Discriminatively learning domain-invariant features for unsupervised domain adaptation, PMLR 28 (2013) 222–230. Google Scholar
22. Q. Sun, R. Chattopadhyay, S. Panchanathan and J. Ye , A two-stage weighting framework for multi-source domain adaptation, in Advances in Neural Information Processing Systems, Vol 24 (NIPS, 2011), pp. 1–9. Google Scholar
23. M. Long, J. Wang, G. Ding, S. J. Pan and S. Y. Philip , Adaptation regularization: A general framework for transfer learning, IEEE Trans. Knowl. Data Eng. 26 (2013) 1076–1089. Crossref, Google Scholar
24. K. Zhang, B. Schölkopf, K. Muandet and Z. Wang , Domain adaptation under target and conditional shift, PMLR 28 (2013) 819–827. Google Scholar
25. M. Gong, K. Zhang, T. Liu, D. Tao, C. Glymour and B. Schölkopf , Domain adaptation with conditional transferable components, PMLR 48 (2016) 2839–2848. Google Scholar
26. A. Iyer, S. Nath and S. Sarawagi , Maximum mean discrepancy for class ratio estimation: Convergence bounds and kernel selection, PMLR 32 (2014) 530–538. Google Scholar
27. B. Schölkopf, J. Platt and T. Hofmann , Analysis of representations for domain adaptation, in Advances in Neural Information Processing Systems, Vol. 19 (NIPS, 2007), pp. 1–8. Google Scholar
28. K. M. Borgwardt, A. Gretton, M. J. Rasch, H.-P. Kriegel, B. Schölkopf and A. J. Smola , Integrating structured biological data by kernel maximum mean discrepancy, Bioinformatics 22 (2006) e49–e57. Crossref, Web of Science, Google Scholar
29. L. Song, K. Fukumizu and A. Gretton , Kernel embeddings of conditional distributions: A unified kernel framework for nonparametric inference in graphical models, IEEE Signal Process. Mag. 30 (2013) 98–111. Crossref, Google Scholar
30. J. Nocedal and S. Wright , Numerical Optimization (Springer Science & Business Media, 2006). Google Scholar
31. G. Dornhege, B. Blankertz, G. Curio and K.-R. Muller , Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms, IEEE Trans. Biomed. Eng. 51 (2004) 993–1002. Crossref, Web of Science, Google Scholar
32. H. Cho, M. Ahn, S. Ahn, M. Kwon and S. C. Jun , EEG datasets for motor imagery brain–computer interface, GigaScience 6 (2017) gix034. Crossref, Web of Science, Google Scholar