Weighted Subject-Semi-Independent ERP-based Brain-Computer Interface

Subject-independent brain-computer interfaces (SI-BCIs) which require no calibration process, are increasingly affect researchers in BCI field. The efficiencies (accuracies), however, were not satisfying till now. In this paper, we proposed a weighted subject-semi-independent classification method (WSSICM) for ERP based BCI system in which a few blocks data of target subject were used. 47 participants were attended in this study. We compared the accuracies of proposed method with traditional subject-specific classification method（SSCM） which used 15 blocks data of target subject. The averaged accuracies were 95.2% for the WSSICM at 5 blocks and 95.7% for the SSCM at 15 blocks. The accuracies of two method did not show significant difference (p-value=0.652). The method we proposed in this paper which could reduce the calibration time can be used for future BCI systems.

[1]  Dario Farina,et al.  Detection of movement-related cortical potentials based on subject-independent training , 2013, Medical & Biological Engineering & Computing.

[2]  G Townsend,et al.  Pushing the P300-based brain-computer interface beyond 100 bpm: extending performance guided constraints into the temporal domain. , 2016, Journal of neural engineering.

[3]  Fabien Lotte,et al.  Brain-Computer Interfaces: Beyond Medical Applications , 2012, Computer.

[4]  Fabien Lotte,et al.  Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces , 2015, Proceedings of the IEEE.

[5]  Marc M. Van Hulle,et al.  Faster P300 Classifier Training Using Spatiotemporal Beamforming , 2016, Int. J. Neural Syst..

[6]  W Speier,et al.  Integrating language models into classifiers for BCI communication: a review , 2016, Journal of neural engineering.

[7]  Behzad Mozaffari Tazehkand,et al.  A New Self-Regulated Neuro-Fuzzy Framework for Classification of EEG Signals in Motor Imagery BCI , 2018, IEEE Transactions on Fuzzy Systems.

[8]  Erwei Yin,et al.  Adding Real-Time Bayesian Ranks to Error-Related Potential Scores Improves Error Detection and Auto-Correction in a P300 Speller , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  Alain Rakotomamonjy,et al.  BCI Competition III: Dataset II- Ensemble of SVMs for BCI P300 Speller , 2008, IEEE Transactions on Biomedical Engineering.

[10]  Eryk Dutkiewicz,et al.  Subject-Independent P300 BCI Using Ensemble Classifier, Dynamic Stopping and Adaptive Learning , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[11]  Andrzej Cichocki,et al.  Whether generic model works for rapid ERP-based BCI calibration , 2013, Journal of Neuroscience Methods.

[12]  Eryk Dutkiewicz,et al.  Subject-Independent ERP-Based Brain–Computer Interfaces , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[13]  Helge J. Ritter,et al.  BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm , 2004, IEEE Transactions on Biomedical Engineering.

[14]  Bernhard Schölkopf,et al.  Transfer Learning in Brain-Computer Interfaces , 2015, IEEE Computational Intelligence Magazine.