Deep comparisons of Neural Networks from the EEGNet family

Most of the Brain-Computer Interface (BCI) publications, which propose artificial neural networks for Motor Imagery (MI) Electroencephalography (EEG) signal classification, are presented using one of the BCI Competition datasets. However, these databases contain MI EEG data from less than or equal to 10 subjects . In addition, these algorithms usually include only bandpass filtering to reduce noise and increase signal quality. In this article, we compared 5 well-known neural networks (Shallow ConvNet, Deep ConvNet, EEGNet, EEGNet Fusion, MI-EEGNet) using open-access databases with many subjects next to the BCI Competition 4 2a dataset to acquire statistically significant results. We removed artifacts from the EEG using the FASTER algorithm as a signal processing step. Moreover, we investigated whether transfer learning can further improve the classification results on artifact filtered data. We aimed to rank the neural networks; therefore, next to the classification accuracy, we introduced two additional metrics: the accuracy improvement from chance level and the effect of transfer learning. The former can be used with different class-numbered databases, while the latter can highlight neural networks with sufficient generalization abilities. Our metrics showed that the researchers should not avoid Shallow ConvNet and Deep ConvNet because they can perform better than the later published ones from the EEGNet family.

Closed loop BCI System for Cybathlon 2020

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