Zhongyun Tang

Dr. Zhongyun Tang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
ZTZhongyun Tang
Zhongyun Tang
HHHaiyang Hou
Haiyang Hou
CXChonghuan Xu
Chonghuan Xu
凯赵凯迪 赵
凯迪 赵
Nowadays people are mostly focused on their work while ignoring their health which in turn is creating a drastic effect on their health in the long run. Remote health monitoring through telemedicine can help people discover potential health threats in time. In the COVID-19 pandemic, remote health monitoring can help obtain and analyze biomedical signals including human body temperature without direct body contact. This technique is of great significance to achieve safe and efficient health monitoring in the COVID-19 pandemic. Existing remote biomedical signal monitoring methods cannot effectively analyze the time series data. This paper designs a remote biomedical signal monitoring framework combining the Internet of Things (IoT), 5G communication and artificial intelligence techniques. In the constructed framework, IoT devices are used to collect biomedical signals at the perception layer. Subsequently, the biomedical signals are transmitted through the 5G network to the cloud server where the GRU-AE deep learning model is deployed. It is noteworthy that the proposed GRU-AE model can analyze multi-dimensional biomedical signals in time series. Finally, this paper conducts a 24-week monitoring experiment for 2000 subjects of different ages to obtain real data. Compared with the traditional biomedical signal monitoring method based on the AutoEncoder model, the GRU-AE model has better performance. The research has an important role in promoting the development of biomedical signal monitoring techniques, which can be effectively applied to some kinds of remote health monitoring scenario.

19 December 2025 in Information Technology And Control
Verified
Journal Article
Open access
PDF file
ZTZhongyun Tang
Zhongyun Tang
HXHanyi Xu
Hanyi Xu
HHHaiyang Hou
Haiyang Hou
CXChonghuan Xu
Chonghuan Xu
WZWeiyu Zhang
Weiyu Zhang
In the era of industrial automation and smart manufacturing, the reliability of industrial equipment is of paramount importance as equipment failures can trigger severe production disruptions and safety hazards. While Bayesian Learning effectively handles uncertainties and enhances fault detection interpretability, it faces challenges in data privacy and centralized processing, whereas Federated Learning safeguards data privacy. Bayesian Federated Learning (BFL) integrates their strengths for privacy-preserving probabilistic modeling with superior generalization. This paper innovatively proposes BFL-CI (Bayesian Federated Learning with Channel Importance), presenting a comprehensive framework and detection process that analyzes channel parameter distributions and transmits selected channel distributions as prior distributions for subsequent clients. Experiments on bearing and gearbox datasets simulating multi-sensor scenarios verify BFL-CI’s effectiveness in improving fault detection accuracy and robustness. This paper fills the gap in applying BFL to industrial equipment fault detection, offering a cutting-edge privacy-preserving solution for reliable intelligent industrial monitoring.