RESUMO
Electroencephalography (EEG)-based brain-computer interface (BCI) systems have been extensively used in various applications, such as communication, control, and rehabilitation. However, individual anatomical and physiological differences cause subject-specific variability of EEG signals for the same task, and BCI systems thus require a calibration procedure that adjusts system parameters to each subject. To overcome this problem, we propose a subject-invariant deep neural network (DNN) using baseline-EEG signals that can be recorded from subjects resting in comfortable states. We first modeled the deep features of EEG signals as a decomposition of subject-invariant and subject-variant features corrupted by anatomical/physiological characteristics. Subject-variant features were then removed from the deep features by learning the network with a baseline correction module (BCM) using the underlying individual information in baseline-EEG signals. The subject-invariant loss forces the BCM to assemble subject-invariant features that have the same class, irrespective of the subject. Using 1-min baseline-EEG signals of the new subject, our algorithm can eliminate subject-variant components from test data without the calibration process. The experimental results show that our subject-invariant DNN framework significantly increases decoding accuracies of the conventional DNN methods for BCI systems. Furthermore, feature visualizations illustrate that the proposed BCM extracts subject-invariant features that are close to each other in the same class.
RESUMO
Transcranial current stimulation is a neuromodulation technique used to modulate brain oscillations and, in turn, to enhance human cognitive function in a non-invasive manner. This study investigated whether cross-frequency coupled transcranial alternating current stimulation (CFC-tACS) improved working memory performance. Participants in both the tACS-treated and sham groups were instructed to perform a modified Sternberg task, where a combination of letters and digits was presented. Theta-phase/high-gamma-amplitude CFC-tACS was administered over electrode F3 and its four surrounding return electrodes (Fp1, Fz, F7, and C3) for 20 min. To identify neurophysiological correlates for the tACS-mediated enhancement of working memory performance, we analyzed EEG alpha and theta power, cross-frequency coupling, functional connectivity, and nodal efficiency during the retention period of the working memory task. We observed significantly reduced reaction times in the tACS-treated group, with suppressed treatment-mediated differences in frontal alpha power and unidirectional Fz-delta-phase to Oz-high-gamma-amplitude modulation during the second half of the retention period when network analyses revealed tACS-mediated fronto-occipital dissociative neurodynamics between alpha suppression and delta/theta enhancement. These findings indicate that tACS modulated top-down control and functional connectivity across the fronto-occipital regions, resulting in improved working memory performance. Our observations are indicative of the feasibility of enhancing cognitive performance by the CFC-formed tACS.
RESUMO
Non-invasive brain-computer interfaces (BCIs) have been widely used for neural decoding, linking neural signals to control devices. Hybrid BCI systems using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) have received significant attention for overcoming the limitations of EEG- and fNIRS-standalone BCI systems. However, most hybrid EEG-fNIRS BCI studies have focused on late fusion because of discrepancies in their temporal resolutions and recording locations. Despite the enhanced performance of hybrid BCIs, late fusion methods have difficulty in extracting correlated features in both EEG and fNIRS signals. Therefore, in this study, we proposed a deep learning-based early fusion structure, which combines two signals before the fully-connected layer, called the fNIRS-guided attention network (FGANet). First, 1D EEG and fNIRS signals were converted into 3D EEG and fNIRS tensors to spatially align EEG and fNIRS signals at the same time point. The proposed fNIRS-guided attention layer extracted a joint representation of EEG and fNIRS tensors based on neurovascular coupling, in which the spatially important regions were identified from fNIRS signals, and detailed neural patterns were extracted from EEG signals. Finally, the final prediction was obtained by weighting the sum of the prediction scores of the EEG and fNIRS-guided attention features to alleviate performance degradation owing to delayed fNIRS response. In the experimental results, the FGANet significantly outperformed the EEG-standalone network. Furthermore, the FGANet has 4.0% and 2.7% higher accuracy than the state-of-the-art algorithms in mental arithmetic and motor imagery tasks, respectively.
