Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features

• Published in: 2018 26th European Signal Processing Conference (EUSIPCO) pp. 1690 - 1694
• Main Authors: Hersche, Michael, Rellstab, Tino, Schiavone, Pasquale Davide, Cavigelli, Lukas, Benini, Luca, Rahimi, Abbas
• Format: Conference Proceeding
• Language: English
• Published: EURASIP 01.09.2018
• Subjects: brain-computer interfaces; Covariance matrices; EEG; Electroencephalography; Europe; Feature extraction; motor imagery; multiclass classification; multiscale features; Support vector machines; SVM; Testing; Training
• ISSN: 2076-1465
• DOI: 10.23919/EUSIPCO.2018.8553378

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 \pmb{73.70\pm15.90\%} (\mathbf{mean}\pm standard deviation across 9 subjects) classification accuracy that surpasses the state-of-the-art method [1], \pmb{70.6\pm 14.70\%} , on the 4-class BCI competition IV-2a dataset. The Riemannian covariance features outperform the CSP by achieving \pmb{74.27\pm15.5\%} accuracy and executing 9x faster in training and 4x faster in testing. Using more temporal windows for Riemannian features results in \pmb{75.47\pm 12.8\%} accuracy with 1.6x faster testing than CSP.