Zhiyong Yuan

Xue Jiang, Jianhui Zhao, Bo Du et al.

EEG signals are usually simple to obtain but expensive to label. Although supervised learning has been widely used in the field of EEG signal analysis, its generalization performance is limited by the amount of annotated data. Self-supervised learning (SSL), as a popular learning paradigm in computer vision (CV) and natural language processing (NLP), can employ unlabeled data to make up for the data shortage of supervised learning. In this paper, we propose a self-supervised contrastive learning method of EEG signals for sleep stage classification. During the training process, we set up a pretext task for the network in order to match the right transformation pairs generated from EEG signals. In this way, the network improves the representation ability by learning the general features of EEG signals. The robustness of the network also gets improved in dealing with diverse data, that is, extracting constant features from changing data. In detail, the network's performance depends on the choice of transformations and the amount of unlabeled data used in the training process of self-supervised learning. Empirical evaluations on the Sleep-edf dataset demonstrate the competitive performance of our method on sleep staging (88.16% accuracy and 81.96% F1 score) and verify the effectiveness of SSL strategy for EEG signal analysis in limited labeled data regimes. All codes are provided publicly online.

Qianqian Tong, Xiaosa Li, Kai Lin et al.

Haptic feedback is essential to acquire immersive experience when interacting in virtual or augmented reality. Although the existing promising magnetic levitation (maglev) haptic system has advantages of none mechanical friction, its performance is limited by its navigation method, which mainly results from the challenge that it is difficult to obtain high precision, high frame rate and good stability with lightweight design at the same. In this study, we propose to perform the visual-inertial fusion navigation based on sequence-to-sequence learning for the maglev haptic interaction. Cascade LSTM based-increment learning method is first presented to progressively learn the increments of the target variables. Then, two cascade LSTM networks are separately trained for accomplishing the visual-inertial fusion navigation in a loosely-coupled mode. Additionally, we set up a maglev haptic platform as the system testbed. Experimental results show that the proposed cascade LSTM based-increment learning method can achieve high-precision prediction, and our cascade LSTM based visual-inertial fusion navigation method can reach 200Hz while maintaining high-precision (the mean absolute error of the position and orientation is respectively less than 1mm and 0.02°)navigation for the maglev haptic interaction application.

Min Chen, Yixue Hao, Kai Lin et al.

With the development of intelligent applications (e.g., self-driving, real-time emotion recognition, etc), there are higher requirements for the cloud intelligence. However, cloud intelligence depends on the multi-modal data collected by user equipments (UEs). Due to the limited capacity of network bandwidth, offloading all data generated from the UEs to the remote cloud is impractical. Thus, in this article, we consider the challenging issue of achieving a certain level of cloud intelligence while reducing network traffic. In order to solve this problem, we design a traffic control algorithm based on label-less learning on the edge cloud, which is dubbed as LLTC. By the use of the limited computing and storage resources at edge cloud, LLTC evaluates the value of data, which will be offloaded. Specifically, we first give a statement of the problem and the system architecture. Then, we design the LLTC algorithm in detail. Finally, we set up the system testbed. Experimental results show that the proposed LLTC can guarantee the required cloud intelligence while minimizing the amount of data transmission.