EEG motor imagery classification using deep learning approaches in naïve BCI users

Abstract

Motor Imagery (MI)-Brain Computer-Interfaces (BCI) illiteracy defines that not all subjects can achieve a good performance in MI-BCI systems due to different factors related to the fatigue, substance consumption, concentration, and experience in the use. To reduce the effects of lack of experience in the use of BCI systems (naïve users), this paper presents the implementation of three Deep Learning (DL) methods with the hypothesis that the performance of BCI systems could be improved compared with baseline methods in the evaluation of naïve BCI users. The methods proposed here are based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM)/Bidirectional Long Short-Term Memory (BiLSTM), and a combination of CNN and LSTM used for upper limb MI signal discrimination on a dataset of 25 naïve BCI users. The results were compared with three widely used baseline methods based on the Common Spatial Pattern (CSP), Filter Bank Common Spatial Pattern (FBCSP), and Filter Bank Common Spatial-Spectral Pattern (FBCSSP), in different temporal window configurations. As results, the LSTM-BiLSTM-based approach presented the best performance, according to the evaluation metrics of Accuracy, F-score, Recall, Specificity, Precision, and ITR, with a mean performance of 80% (maximum 95%) and ITR of 10 bits/min using a temporal window of 1.5 s. The DL Methods represent a significant increase of 32% compared with the baseline methods (p<0.05). Thus, with the outcomes of this study, it is expected to increase the controllability, usability, and reliability of the use of robotic devices in naïve BCI users.

Influence of Temporal and Frequency Selective Patterns Combined with CSP Layers on Performance in Exoskeleton-Assisted Motor Imagery Tasks

“…This section presents the CSP configurations used in this study: CSP, FBCSP, and Filter Bank Common Spectral Spatial Patterns (FBCSSP). For more information on each of the methods, please refer to our previous works [26,32]. A graphical representation of each of the CSP variations is shown in Figure 1.…”

“…Several authors have reported the use of a mutual information-based feature selection stage, which was implemented in this study to obtain more selective features from EEG signals [19]. In addition, previous works have demonstrated that filter banks of 8-15 Hz, 15 -22 Hz, and 22-30 Hz show adequate accuracy rates for binary classification [26,32]. Note that this method uses spectral filtering (using the filter bank) and spatial filtering through the CSP layer, which is implemented following the same configuration presented in the previous section.…”

“…The variation implemented to increase the number of CSP layers uses a filter bank, previously extracted using FBCSP, and applies an additional CSP layer that combines each of the sub-CSPs calculated for each filter bank [32,38]. This method is called FBCSSP, see Figure 1.…”

“…Other efforts have focused on improving the accuracy of computational methods to recognize mental tasks. For instance, Guerrero et al [32] performed a comparative study between methods based on CSP and Deep Learning (DL) to discriminate hand MI tasks, evaluating performance with different time windows and filter banks. DL achieved better performance than CSP but with additional computational cost.…”

Brain–Computer Interface Based on PLV-Spatial Filter and LSTM Classification for Intuitive Control of Avatars

“…Wang et al [27] proposed a hybrid 2D CNN-LSTM model for MI EEG classification. Guerrero-Méndez et al [28] applied various models, such as the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM)/Bidirectional Long Short-Term Memory (BiLSTM), and a combination of CNN and LSTM, in the same context (MI EEG).…”