Version 1
: Received: 26 April 2024 / Approved: 26 April 2024 / Online: 28 April 2024 (08:23:16 CEST)
How to cite:
Mwata-Velu, T.; Zamora, E.; Vasquez-Gomez, J.I.; Ruiz-Pinales, J.; Azuela, J.H.S. EEG-Visual Multiclass Classification Based on a Channel Selection, MNE Algorithm and Deep Network Architectures. Preprints2024, 2024041809. https://doi.org/10.20944/preprints202404.1809.v1
Mwata-Velu, T.; Zamora, E.; Vasquez-Gomez, J.I.; Ruiz-Pinales, J.; Azuela, J.H.S. EEG-Visual Multiclass Classification Based on a Channel Selection, MNE Algorithm and Deep Network Architectures. Preprints 2024, 2024041809. https://doi.org/10.20944/preprints202404.1809.v1
Mwata-Velu, T.; Zamora, E.; Vasquez-Gomez, J.I.; Ruiz-Pinales, J.; Azuela, J.H.S. EEG-Visual Multiclass Classification Based on a Channel Selection, MNE Algorithm and Deep Network Architectures. Preprints2024, 2024041809. https://doi.org/10.20944/preprints202404.1809.v1
APA Style
Mwata-Velu, T., Zamora, E., Vasquez-Gomez, J.I., Ruiz-Pinales, J., & Azuela, J.H.S. (2024). EEG-Visual Multiclass Classification Based on a Channel Selection, MNE Algorithm and Deep Network Architectures. Preprints. https://doi.org/10.20944/preprints202404.1809.v1
Chicago/Turabian Style
Mwata-Velu, T., Jose Ruiz-Pinales and Juan Humberto Sossa Azuela. 2024 "EEG-Visual Multiclass Classification Based on a Channel Selection, MNE Algorithm and Deep Network Architectures" Preprints. https://doi.org/10.20944/preprints202404.1809.v1
Abstract
This work addresses the challenge of EEG visual multiclass classification into 40 classes for Brain-Computer interface applications, by using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage, since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, performing multiclassifiers based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and Minimum-Norm Estimate algorithms are implemented to select discriminant channels and enhance EEG data. Hence, deep EEGNet and Convolutional-recurrent neural networks are implemented separately to classify EEG data of image visualization into 40 labels. By using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures, respectively. Satisfactory results obtained with this method offer a new implementation opportunity for multi-task BCI applications by utilizing a reduced number of channels (<50%), compared to those presented in the related literature where the whole set of channels is used.
Computer Science and Mathematics, Signal Processing
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.