Objectives: The temporal and spatial information of electroencephalogram (EEG) signals is crucial for recognizing features in emotion classification models, but it excessively relies on manual feature extraction. The transformer model has the capability of performing automatic feature extraction; however, its potential has not been fully explored in the classification of emotion-related EEG signals. To address these challenges, the present study proposes a novel model based on transformer and convolutional neural networks (TCNN) for EEG spatial–temporal (EEG ST) feature learning to automatic emotion classification. Methods: The proposed EEG ST-TCNN model utilizes position encoding (PE) and multi-head attention to perceive channel positions and timing information in EEG signals. Two parallel transformer encoders in the model are used to extract spatial and temporal features from emotion-related EEG signals, and a CNN is used to aggregate the EEG’s spatial and temporal features, which are subsequently classified using Softmax. Results: The proposed EEG ST-TCNN model achieved an accuracy of 96.67% on the SEED dataset and accuracies of 95.73%, 96.95%, and 96.34% for the arousal–valence, arousal, and valence dimensions, respectively, for the DEAP dataset. Conclusions: The results demonstrate the effectiveness of the proposed ST-TCNN model, with superior performance in emotion classification compared to recent relevant studies. Significance: The proposed EEG ST-TCNN model has the potential to be used for EEG-based automatic emotion recognition.

The traditional imagery task for brain–computer interfaces (BCIs) consists of motor imagery (MI) in which subjects are instructed to imagine moving certain parts of their body. This kind of imagery task is difficult for subjects. In this study, we used a less studied yet more easily performed type of mental imagery—visual imagery (VI)—in which subjects are instructed to visualize a picture in their brain to implement a BCI. In this study, 18 subjects were recruited and instructed to observe one of two visual-cued pictures (one was static, while the other was moving) and then imagine the cued picture in each trial. Simultaneously, electroencephalography (EEG) signals were collected. Hilbert–Huang Transform (HHT), autoregressive (AR) models, and a combination of empirical mode decomposition (EMD) and AR were used to extract features, respectively. A support vector machine (SVM) was used to classify the two kinds of VI tasks. The average, highest, and lowest classification accuracies of HHT were 68.14 3.06%, 78.33%, and 53.3%, respectively. The values of the AR model were 56.29 2.73%, 71.67%, and 30%, respectively. The values obtained by the combination of the EMD and the AR model were 78.40 2.07%, 87%, and 48.33%, respectively. The results indicate that multiple VI tasks were separable based on EEG and that the combination of EMD and an AR model used in VI feature extraction was better than an HHT or AR model alone. Our work may provide ideas for the construction of a new online VI-BCI.

Compared with the efficacy of traditional physical therapy, a new therapy utilizing motor imagery can induce brain plasticity and allows partial recovery of motor ability in patients with hemiplegia after stroke. Here, we proposed an updated paradigm utilizing motor coordination imagery involving the lower limbs (normal gait imagery and hemiplegic gait imagery after stroke) and decoded such imagery via an electroencephalogram‐ (EEG‐) based brain network. Thirty subjects were recruited to collect EEGs during motor coordination imagery involving the lower limbs. Time‐domain analysis, power spectrum analysis, time‐frequency analysis, brain network analysis, and statistical analysis were used to explore the neural mechanisms of motor coordination imagery involving the lower limbs. Then, EEG‐based brain network features were extracted, and a support vector machine was used for decoding. The results showed that the two employed motor coordination imageries mainly activated sensorimotor areas; the frequency band power was mainly concentrated within theta and alpha bands, and brain functional connections mainly occurred in the right forehead. The combination of the network attributes of the EEG‐based brain network and the spatial features of the adjacency matrix had good separability for the two kinds of gait imagery (p < 0.05), and the average classification accuracy of the combination feature was 92.96% ± 7.54%. Taken together, our findings suggest that brain network features can be used to identify normal gait imagery and hemiplegic gait imagery after stroke.

Objectives. Brain‐computer interface (BCI) based on functional near‐infrared spectroscopy (fNIRS) is expected to provide an optional active rehabilitation training method for patients with walking dysfunction, which will affect their quality of life seriously. Sparse representation classification (SRC) oxyhemoglobin (HbO) concentration was used to decode walking imagery and idle state to construct fNIRS‐BCI based on walking imagery. Methods. 15 subjects were recruited and fNIRS signals were collected during walking imagery and idle state. Firstly, band‐pass filtering and baseline drift correction for HbO signal were carried out, and then the mean value, peak value, and root mean square (RMS) of HbO and their combinations were extracted as classification features; SRC was used to identify the extracted features and the result of SRC was compared with those of support vector machine (SVM), K‐Nearest Neighbor (KNN), linear discriminant analysis (LDA), and logistic regression (LR). Results. The experimental results showed that the average classification accuracy for walking imagery and idle state by SRC using three features combination was 91.55±3.30%, which was significantly higher than those of SVM, KNN, LDA, and LR (86.37±4.42%, 85.65±5.01%, 86.43±4.41%, and 76.14±5.32%, respectively), and the classification accuracy of other combined features was higher than that of single feature. Conclusions. The study showed that introducing SRC into fNIRS‐BCI can effectively identify walking imagery and idle state. It also showed that different time windows for feature extraction have an impact on the classification results, and the time window of 2–8 s achieved a better classification accuracy (94.33±2.60%) than other time windows. Significance. The study was expected to provide a new and optional active rehabilitation training method for patients with walking dysfunction. In addition, the experiment was also a rare study based on fNIRS‐BCI using SRC to decode walking imagery and idle state.

A brain–computer interface (BCI) based on kinesthetic motor imagery has a potential of becoming a groundbreaking technology in a clinical setting. However, few studies focus on a visual-motor imagery (VMI) paradigm driving BCI. The VMI-BCI feature extraction methods are yet to be explored in depth. In this study, a novel VMI-BCI paradigm is proposed to execute four VMI tasks: imagining a car moving forward, reversing, turning left, and turning right. These mental strategies can naturally control a car or robot to move forward, backward, left, and right. Electroencephalogram (EEG) data from 25 subjects were collected. After the raw EEG signal baseline was corrected, the alpha band was extracted using bandpass filtering. The artifacts were removed by independent component analysis. Then, the EEG average instantaneous energy induced by VMI (VMI-EEG) was calculated using the Hilbert–Huang transform (HHT). The autoregressive model was extracted to construct a 12-dimensional feature vector to a support vector machine suitable for small sample classification. This was classified into two-class tasks: visual imagination of driving the car forward versus reversing, driving forward versus turning left, driving forward versus turning right, reversing versus turning left, reversing versus turning right, and turning left versus turning right. The results showed that the average classification accuracy of these two-class tasks was 62.68 ± 5.08%, and the highest classification accuracy was 73.66 ± 6.80%. The study showed that EEG features of O1 and O2 electrodes in the occipital region extracted by HHT were separable for these VMI tasks.

Brain-computer interaction based on motor imagery (MI) is an important brain-computer interface (BCI). Most methods for MI classification are based on electroencephalogram (EEG), and few studies have investigated signal processing based on MI-Functional Near-Infrared Spectroscopy (fNIRS). In addition, there is a need to improve the classification accuracy for MI fNIRS methods. In this study, a deep belief network (DBN) based on a restricted Boltzmann machine (RBM) was used to classify fNIRS signals of flexion and extension imagery involving the left and right arms. fNIRS signals from 16 channels covering the motor cortex area were recorded for each of 10 subjects executing or imagining flexion and extension involving the left and right arms. Oxygenated hemoglobin (HbO) concentration was used as a feature to train two RBMs that were subsequently stacked with an additional softmax regression output layer to construct DBN. We also explored the DBN model classification accuracy for the test dataset from one subject using training dataset from other subjects. The average DBN classification accuracy for flexion and extension movement and imagery involving the left and right arms was 84.35 ± 3.86% and 78.19 ± 3.73%, respectively. For a given DBN model, better classification results are obtained for test datasets for a given subject when the model is trained using dataset from the same subject than when the model is trained using datasets from other subjects. The results show that the DBN algorithm can effectively identify flexion and extension imagery involving the right and left arms using fNIRS. This study is expected to serve as a reference for constructing online MI-BCI systems based on DBN and fNIRS.