EEG-based human identification has gained a wide range of attention due to the further increase in demand for security. How to improve the accuracy of the human identification system is an issue worthy of attention. Using more features in the human identification system is a potential solution. However, too many features may cause overfitting, resulting in the decline of system accuracy. In this work, the graph convolutional neural network (GCN) was adopted for classification. Multiple features were combined and utilized as the structure matrix of the GCN. Because of the constant signal matrix, the training parameters would not increase as the structure matrix grows. We evaluated the classification accuracy on a classic public dataset. The results showed that utilizing multiple features of functional connectivity (FC) can improve the accuracy of the identity authentication system, the best results of which are at 98.56%. In addition, our methods showed less sensitivity to channel reduction. The method proposed in this paper combines different FCs and reaches high classification accuracy for unpreprocessed data, which inspires reducing the system cost in the actual human identification system.

The main objective of this paper is to use deep neural networks to decode the electroencephalography (EEG) signals evoked when individuals perceive four types of motion stimuli (contraction, expansion, rotation, and translation). Methods for single-trial and multi-trial EEG classification are both investigated in this study. Attention mechanisms and a variant of recurrent neural networks (RNNs) are incorporated as the decoding model. Attention mechanisms emphasize task-related responses and reduce redundant information of EEG, whereas RNN learns feature representations for classification from the processed EEG data. To promote generalization of the decoding model, a novel online data augmentation method that randomly averages EEG sequences to generate artificial signals is proposed for single-trial EEG. For our dataset, the data augmentation method improves the accuracy of our model (based on RNN) and two benchmark models (based on convolutional neural networks) by 5.60%, 3.92%, and 3.02%, respectively. The attention-based RNN reaches mean accuracies of 67.18% for single-trial EEG decoding with data augmentation. When performing multi-trial EEG classification, the amount of training data decreases linearly after averaging, which may result in poor generalization. To address this deficiency, we devised three schemes to randomly combine data for network training. Accordingly, the results indicate that the proposed strategies effectively prevent overfitting and improve the correct classification rate compared with averaging EEG fixedly (by up to 19.20%). The highest accuracy of the three strategies for multi-trial EEG classification achieves 82.92%. The decoding performance for the methods proposed in this work indicates they have application potential in the brain–computer interface (BCI) system based on visual motion perception.

Reinforcement learning (RL) faces a series of challenges, including learning efficiency and generalization. The state representation used to train RL is one of the important factors causing these challenges. In this paper, we explore providing a more efficient state representation for RL. Contrastive learning is used as the representation extraction method in our work. We propose an attention mechanism implementation and extend an existing contrastive learning method by embedding the attention mechanism. Finally an attention-augmented contrastive learning method called A2C is obtained. As a result, using the state representation from A2C, the robot achieves better learning efficiency and generalization than those using state-of-the-art representations. Moreover, our attention mechanism is proven to be able to calculate the correlation of arbitrary distance among pixels, which is conducive to capturing more accurate obstacle information. What is more, we remove the attention mechanism from A2C. It is shown that the rewards available for the attention-removed A2C are reduced by more than 70%, which indicates the important role of the attention mechanism.

Deep learning methods based on convolution neural networks (CNNs) have achieved good classification performance in decoding electroencephalography (EEG). In this paper, a novel framework combining gating mechanism and dilated convolution neural network (GDCNN) is proposed for decoding EEG signals evoked by four different driving intentions. GDCNN provides different receptive fields and controls the information flow between convolution layers, which help to detect different sizes of information in EEG signals. The proposed method reaches accuracies of 93.17% and 73.33% for the subject-dependent and subject-independent experiments, outperforming several benchmark methods. The data augmentation that randomly concatenates multi-trial EEG sequences is adopted to promote generalization of decoding model. This strategy effectively prevents overfitting and improves the decoding accuracies of EEGNet, DeepConvNet, and GDCNN by 4.3%, 4.75%, and 3.92%, respectively. These results indicate GDCNN is beneficial for decoding EEG and it has application potential in the brain-computer interface (BCI) systems based on video stimuli.

Unmanned Aerial Vehicle (UAV) has been widely used in military reconnaissance, smart transportation, public security and other fields. UAV-based person tracking is attracting incremental attention for its wide application requirements. Currently, some state-of-the-art visual tracking methods have achieved promising performance in common scenarios. However, in the scene of UAV-based person tracking, there will be long-term target disappearance and unpredictable dramatic target appearance changes, which still pose a huge challenge to UAV-based person tracking. In this work, a human-machine hybrid augmented tracking system based on eye tracking is proposed to cope with the challenge. During tracking, through the interaction between humans and machines, humans can provide real-time guidance and corrections to the tracker, and the tracker can also learn interesting targets from humans to enhance itself. The experimental results show that human-in-the-loop can remarkable improve the success rate and robustness of the tracking and our tracking system outperforms the state-of-the-art tracker in complex environments.