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


Loading...

Date

2018

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

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 [1], 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 9× faster in training and 4× faster in testing. Using more temporal windows for Riemannian features results in 75.47±12.8% accuracy with 1.6× faster testing than CSP.

Publication status

published

Editor

Book title

2018 26th European Signal Processing Conference (EUSIPCO)

Journal / series

Volume

Pages / Article No.

1690 - 1694

Publisher

IEEE

Event

26th European Signal Processing Conference (EUSIPCO 2018)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

EEG; Motor imagery; Brain-computer interfaces; Multiclass classification; Multiscale features; SVM

Organisational unit

03996 - Benini, Luca / Benini, Luca check_circle

Notes

Funding

608881 - ETH Zurich Postdoctoral Fellowship Program II (EC)

Related publications and datasets