A5076077486- Privacy-Preserving Technologies in Data
- UAV Applications and Optimization
- Cryptography and Data Security
- Mobile Crowdsensing and Crowdsourcing
- Network Security and Intrusion Detection
- Opinion Dynamics and Social Influence
- Blockchain Technology Applications and Security
- Advanced Wireless Communication Technologies
- Visual Attention and Saliency Detection
- Distributed Sensor Networks and Detection Algorithms
- Stochastic Gradient Optimization Techniques
- Video Surveillance and Tracking Methods
- Internet Traffic Analysis and Secure E-voting
Dalian Minzu University
2021-2024
Shenzhen Technology University
2024
Minzu University of China
2021-2023
Semantic communication, as a promising technology, has emerged to break through the Shannon limit, which is envisioned key enabler and fundamental paradigm for future 6G networks applications, e.g., smart healthcare. In this paper, we focus on UAV image-sensing-driven task-oriented semantic communications scenarios. The majority of existing work focused designing advanced algorithms high-performance communication. However, challenges, such energy-hungry efficiency-limited image retrieval...
Air access networks have been recognized as a significant driver of various Internet Things (IoT) services and applications. In particular, the aerial computing network infrastructure centered on Drones has set off new revolution in automatic image recognition. This emerging technology relies sharing ground-truth-labeled data between unmanned vehicle (UAV) swarms to train high-quality recognition model. However, such an approach will bring privacy availability challenges. To address these...
With the rapid development of cloud manufacturing, industrial production with edge computing as core architecture has been greatly developed. However, devices often suffer from abnormalities and failures in production. Therefore, detecting these abnormal situations timely accurately is crucial for manufacturing. As such, a straightforward solution that device uploads data to anomaly detection. Industry 4.0 puts forward higher requirements privacy security so it unrealistic upload directly...
Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model. However, current research is generally based on an assumption that the of local clients have ground-truth. Furthermore, FL faces challenge statistical heterogeneity, i.e., distribution client's non-independent identically distributed (non-IID). In this paper, we present robust semi-supervised system design, where aims solve problem availability and...
The straggler effect is the main bottleneck for Federated Learning (FL), where performance of training degraded by slowest member. Another significant problem unreliable communication, which somehow has been neglected in previous studies. That is, transmission local models not successful every time. In this paper, we find that problems and communication are implicitly caused time divergence User Equipments (UEs) each round. Based on this, propose our solutions these two show can be merged...