Fast and Accurate Multiclass Inference for Brain–Computer Interfaces
Accurate, fast, and reliable multiclass classification of electroencephalography (EEG) signals is a challenging task towards the development of motor imagery brain-computer interface (MI-BCI) systems. We propose enhancements to different feature extractors, along with a support vector machine (SVM) classifier, to simultaneously improve classification accuracy and execution time during training and testing. We focus on the well-known common spatial pattern (CSP) and Riemannian covariance methods, and significantly extend these two feature extractors to multiscale temporal and spectral cases. The multiscale CSP features achieve 73.70±15.90% (mean± standard deviation across 9 subjects) classification accuracy that surpasses the state-of-the-art method , 70.6±14.70%, on the 4-class BCI competition IV-2a dataset. The Riemannian covariance features outperform the CSP by achieving 74.27±15.5% accuracy and executing 9x faster in training and 4x faster in testing. Using more temporal windows for Riemannian features results in 75.47±12.8% accuracy with 1.6x faster testing than CSP.
EEG, motor imagery, brain–computer interfaces, multiclass classification, multiscale features, SVM
- Semester thesis by Michael Hersche and Tino Rellstab
- Supervision: Abbas Rahimi, Lukas Cavigelli, Pasquale Davide Schiavone