ASTERI: image-based representation of EEG signals for motor imagery classification

Abstract

Electroencephalography (EEG) signals are valuable in the monitoring and investigation of neurological diseases and in the control of brain-machine interfaces (BCI). However, these signals are noisy and are non-linear and non-stationary in nature. Signal analysis is an expensive task and can lead to misdiagnosis. Deep learning can be used to overcome these challenges. The most used deep architectures are based on convolutional neural networks (CNNs). Representing EEG signals as images can be useful to use deep architectures based on CNNs in solutions based on intelligent EEG-based systems. Methods: In this work, we propose the ASTERI method, for representing EEG signals in two dimensions using the backprojection reconstruction method. To validate the proposal, experiments were performed with motor imagery EEG signals from the BCI Competition IV 2b motor imagery database. To extract attributes from the EEG signal windows, we used the ASTERI representation and investigated the pre-trained networks VGG16 and LeNet. To classify the final classification of imagined movements to the right and to the left, we used Random Forests. Results: For the original database, the validation with 100 trees achieved an average accuracy and kappa index of 88.97% and 0.78, respectively. In the case of augmented databases with synthetic instances, the average accuracies were 89.10% and 89.13% for increases of 50% and 150% for each class, respectively. Conclusion: The experimental results showed that the ASTERI method, together with hybrid deep architectures based on CNN and Random Forests, can generate competitive results in solving motor imagery problems. The representation of signals as images can also con tribute to the exploration of new solutions of applied neuroscience problems based on deep architectures.

Current Trends, Challenges, and Future Research Directions of Hybrid and Deep Learning Techniques for Motor Imagery Brain–Computer Interface

“…A summary of these methods is given on Table 7. [110]. Pseudosinogram images were fed to the pretrained model to extract features and then to a random forest classifier.…”

Evaluation of molecular docking by deep learning and Random Forests: A hybrid approach based on pseudo-convolutions

“…These models have demonstrated impressive performance in support diagnosis applications based on biomedical images, signals and clinical parameters, like in breast cancer, Covid-19, mental disorders, and in neurodegenerative diseases like Alzheimer's and Parkinson's (Azevedo et al, 2015;Barbosa et al, 2022;F.R. Cordeiro, Santos, & Silva-Filho, 2016b;de Lima, da Silva-Filho, & dos Santos, 2016;De Oliveira et al, 2020;de Santana, de Freitas Barbosa, de Cássia Fernandes de Lima, & dos Santos, 2022;de Santana et al, 2018; Santos Lucas e Silva, dos Santos, de Lima, & Initiative, 2021;Espinola, Gomes, Pereira, & dos Santos, 2021a, 2021bFonseca et al, 2022;Gomes et al, 2020;Gomes, de Santana, Masood, de Lima, & dos Santos, 2023;Gomes, Rodrigues, & dos Santos, 2022;Santana et al, 2018;Shirahige et al, 2022;Wanderley Espinola, Gomes, Mônica Silva Pereira, & dos Santos, 2022). Such models have been used successfully in accurately predicting protein-protein binding affinities.…”