Closed loop BCI System for Cybathlon 2020

TL;DR

This paper presents a BCI system designed for Cybathlon 2020, utilizing FFT-based features and SVM classifiers to enable tetraplegic subjects to control a computer game through mental commands, with promising offline results.

Contribution

The study introduces novel feature extraction methods (Feature Range) and demonstrates their effectiveness in classifying EEG signals for BCI control in a competitive setting.

Findings

Range40 method with ensemble SVM achieved 46.07% accuracy on PhysioNet data.

Our approach outperformed the EEGNet baseline in classification accuracy.

27 out of 59 gameplay trials reached the qualification time limit.

Abstract

We present our Brain-Computer Interface (BCI) System, developed for the BCI discipline of Cybathlon 2020 competition. In the BCI discipline, subjects with tetraplegia are required to control a computer game with mental commands. The absolute of the Fast-Fourier Transformation amplitude was calculated as a feature (FFTabs) from one-second-long electroencephalographic (EEG) signals. To extract the final features, we introduced two methods, namely the Feature Average, where the average of the FFTabs for a specific frequency band was calculated, and the Feature Range, which was based on generating multiple Feature Averages for non-overlapping 2 Hz wide frequency bins. The resulting features were fed to a Support Vector Machine classifier. The algorithms were tested on the PhysioNet database and our dataset, which contains 16 offline experiments recorded with 2 tetraplegic subjects. 27 gameplay trials (out of 59) with our tetraplegic subjects reached the 240-second qualification time limit. The Feature Average of canonical frequency bands (alpha, beta, gamma, and theta) were compared with our suggested range30 and range40 methods. On the PhysioNet dataset, the range40 method combined with an ensemble SVM classifier significantly reached the highest accuracy level (0.4607), with a 4-class classification, and outperformed the state-of-the-art EEGNet.