Continual Learning of a Transformer-Based Deep Learning Classifier Using an Initial Model from Action Observation EEG Data to Online Motor Imagery Classification.

The motor imagery (MI)-based brain computer interface (BCI) is an intuitive interface that enables users to communicate with external environments through their minds. However, current MI-BCI systems ask naïve subjects to perform unfamiliar MI tasks with simple textual instruction or a visual/auditory cue. The unclear instruction for MI execution not only results in large inter-subject variability in the measured EEG patterns but also causes the difficulty of grouping cross-subject data for big-data training. In this study, we designed an BCI training method in a virtual reality (VR) environment. Subjects wore a head-mounted device (HMD) and executed action observation (AO) concurrently with MI (i.e., AO + MI) in VR environments. EEG signals recorded in AO + MI task were used to train an initial model, and the initial model was continually improved by the provision of EEG data in the following BCI training sessions. We recruited five healthy subjects, and each subject was requested to participate in three kinds of tasks, including an AO + MI task, an MI task, and the task of MI with visual feedback (MI-FB) three times. This study adopted a transformer- based spatial-temporal network (TSTN) to decode the user's MI intentions. In contrast to other convolutional neural network (CNN) or recurrent neural network (RNN) approaches, the TSTN extracts spatial and temporal features, and applies attention mechanisms along spatial and temporal dimensions to perceive the global dependencies. The mean detection accuracies of TSTN were 0.63, 0.68, 0.75, and 0.77 in the MI, first MI-FB, second MI-FB, and third MI-FB sessions, respectively. This study demonstrated the AO + MI gave an easier way for subjects to conform their imagery actions, and the BCI performance was improved with the continual learning of the MI-FB training process.

The Effect of Degrees of Inversion on the Electronic Structure of Spinel NiCo2O4: A Density Functional Theory Study.

In this study, electronic structure calculations and Bader charge analysis have been completed on the inverse, intermediate, and normal spinel structures of NiCo2O4 in both primitive and conventional cells, using density functional theory with Hubbard U correction. Three spinel structures have been computed in the primitive cell, where the fully inverse spinel, 50% intermediate spinel, and normal spinel can be acquired by swapping Ni and Co atoms on tetrahedral and octahedral sites. Furthermore, NiCo2O4 with different degrees of inversion in the conventional cells was also investigated, along with their doping energies. Confirmed by the assigned formal charges, magnetic moments, and decomposed density of state, our results suggest that the electronic properties of Ni and Co on the tetrahedral site can be altered by swapping Ni and Co atoms, whereas both Ni and Co on the octahedral site are uninfluenced. A simple and widely used model, crystal field theory, is also compared with our calculations and shows a consistent prediction about the cation distribution in NiCo2O4. This study analyzes the correlation between cation arrangements and formal charges, which could potentially be used to predict the desired electronic properties of NiCo2O4 for various applications.