Jinyu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jinyu Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Chengbin Chen
College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
2 shared publications - Pingping Chen
College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
2 shared publications - Sifan Chen
Fuzhou University Zhicheng College, Fuzhou, China
2 shared publications - Zhiqiang Wu
College of Architecture and Urban Planning, Tongji University, Shanghai, China
2 shared publications Baihe Chen
School of Modern Information Industry, Guangzhou College of Commerce, Guangzhou, China
1 shared publication- Baihe Chen
College of Modern Information Industry, Guangzhou College of Commerce, Guangzhou, China
1 shared publication
Latest Publications
- 19 December 2025
- Published by Elsevier in Aerospace Science and Technology
- Vol. 170
CGF-ICOA: Rapid planning for large scale scenarios UAVs under coupled spatial and resource constraints
- 19 December 2025
- Published by Elsevier in Aerospace Science and Technology
- Vol. 170
CGF-ICOA: Rapid planning for large scale scenarios UAVs under coupled spatial and resource constraints
- 5 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (3) , 3542-3555
FedMES: Robust FL for UAV Swarm Tracking via Adaptive Model Enhancement
With the rapid development of intelligent sensing technology, unmanned aerial vehicles (UAVs) have shown their potential in mobile non-cooperative target (MNCT) tracking tasks. Collaborative learning of target motion characteristics is an effective means of improving tracking stability for UAV swarms. However, UAV swarm-based MNCT tracking faces critical challenges in real-world environments, including sensing interference and data heterogeneity. To address this and realize per-sensing-round updates of the models deployed on the UAV swarm, we propose FedMES, a federated learning framework that jointly optimizes data reliability and model performance. First, we design a data filtering mechanism using polynomial fitting and moving average correction to suppress destructive noise. Second, dynamic aggregation weights are assigned based on historical data confidence to prioritize high-reliability clients. Third, clients selectively adopt the global or local model via a dual-metric evaluation post-aggregation. Evaluated on real-world MNCT trajectories, FedMES reduces mean estimation errors by 10%-22% compared to FedAvg/FedProx, demonstrating superior robustness under high noise and data loss.
- 5 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (3) , 3542-3555
FedMES: Robust FL for UAV Swarm Tracking via Adaptive Model Enhancement
With the rapid development of intelligent sensing technology, unmanned aerial vehicles (UAVs) have shown their potential in mobile non-cooperative target (MNCT) tracking tasks. Collaborative learning of target motion characteristics is an effective means of improving tracking stability for UAV swarms. However, UAV swarm-based MNCT tracking faces critical challenges in real-world environments, including sensing interference and data heterogeneity. To address this and realize per-sensing-round updates of the models deployed on the UAV swarm, we propose FedMES, a federated learning framework that jointly optimizes data reliability and model performance. First, we design a data filtering mechanism using polynomial fitting and moving average correction to suppress destructive noise. Second, dynamic aggregation weights are assigned based on historical data confidence to prioritize high-reliability clients. Third, clients selectively adopt the global or local model via a dual-metric evaluation post-aggregation. Evaluated on real-world MNCT trajectories, FedMES reduces mean estimation errors by 10%-22% compared to FedAvg/FedProx, demonstrating superior robustness under high noise and data loss.