Xueyan Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xueyan Cao has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Shubin Wang
Inner Mongolia University
14 shared publications - Jun Cui
Inner Mongolia University
11 shared publications - Yuzheng Ren
University of Science and Technology Beijing
10 shared publications - Xiaolong Wu
Inner Mongolia Key Laboratory of Intelligent Communication and Sensing and Signal Processing, Inner Mongolia University, Hohhot, China
6 shared publications - Gerile Ge
Inner Mongolia Key Laboratory of Intelligent Communication and Sensing and Signal Processing, Inner Mongolia University, Hohhot, China
5 shared publications - Fei Richard Yu
Shenzhen University
3 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 23666-23682
Meta-Optimization for Discovering Adaptive Routing Rules in Dynamic Heterogeneous LEO Satellite Networks
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 23666-23682
Meta-Optimization for Discovering Adaptive Routing Rules in Dynamic Heterogeneous LEO Satellite Networks
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (22) , 54304-54317
Partitioned Sensing-Communication Tradeoff for Dual-STAR-RIS-Aided ISAC Systems
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (22) , 54304-54317
Partitioned Sensing-Communication Tradeoff for Dual-STAR-RIS-Aided ISAC Systems
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 21901-21918
A Layered Optimization-Learning Framework for Secure and Adaptive ISAC in IRS-Assisted UAV Networks
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 21901-21918
A Layered Optimization-Learning Framework for Secure and Adaptive ISAC in IRS-Assisted UAV Networks
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20409-20424
TD3-Based Joint Trajectory-Power-Beamforming Optimization for Secure and Covert UAV-Aided Vehicular Edge Computing
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20409-20424
TD3-Based Joint Trajectory-Power-Beamforming Optimization for Secure and Covert UAV-Aided Vehicular Edge Computing
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19441-19454
UAV-Assisted Security-Aware Vehicular Edge Computing: A TD3-Enhanced Scheme
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 19441-19454
UAV-Assisted Security-Aware Vehicular Edge Computing: A TD3-Enhanced Scheme
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (19) , 44718-44732
Reinforcement Learning-Based Resource Allocation for IRS-Enhanced V2X Communication and Computation Systems
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (19) , 44718-44732
Reinforcement Learning-Based Resource Allocation for IRS-Enhanced V2X Communication and Computation Systems
- Open Access
- 10 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 64-68
Near-Field SWIPT Performance Enhancement via Initial Blind Scanning
- 10 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 64-68
Open AccessNear-Field SWIPT Performance Enhancement via Initial Blind Scanning
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-14
ARIS-Aided Multi-UAV-Enabled V2X Communication and Computation: Resource Allocation and Performance Optimization
Vehicle-to-everything (V2X) communication and computation are confronted with substantial transmission latency and energy consumption. This paper presents an energy-efficient, active, reconfigurable intelligent surface-aided V2X integrated communication and computation system utilizing unmanned aerial vehicles to enhance vehicular communication and computation. A new performance metric, termed “effective energy efficiency”, is introduced to capture the trade-offs between network energy costs, communication, and computation utilities. An optimization problem that maximizes effective energy efficiency by optimizing communication and computational resources is proposed and solved using Dinkelbach's algorithm and fractional decomposition. The multiple association optimization sub-problem is solved using convex optimization and integer programming methods. The joint beamforming design and computation resource allocation sub-problems are reformulated as convex optimization problems through a first-order Taylor series approximation and solved using a convex optimization method. Finally, an efficient communication and computation resource allocation (ECCRA) scheme is ultimately achieved based on the block coordinate descent (BCD) framework. Simulations confirm that the proposed BCD-based ECCRA scheme significantly enhances system energy efficiency compared to benchmark testing schemes, thereby promoting the development of intelligent and sustainable transportation ecosystems.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-14
ARIS-Aided Multi-UAV-Enabled V2X Communication and Computation: Resource Allocation and Performance Optimization
Vehicle-to-everything (V2X) communication and computation are confronted with substantial transmission latency and energy consumption. This paper presents an energy-efficient, active, reconfigurable intelligent surface-aided V2X integrated communication and computation system utilizing unmanned aerial vehicles to enhance vehicular communication and computation. A new performance metric, termed “effective energy efficiency”, is introduced to capture the trade-offs between network energy costs, communication, and computation utilities. An optimization problem that maximizes effective energy efficiency by optimizing communication and computational resources is proposed and solved using Dinkelbach's algorithm and fractional decomposition. The multiple association optimization sub-problem is solved using convex optimization and integer programming methods. The joint beamforming design and computation resource allocation sub-problems are reformulated as convex optimization problems through a first-order Taylor series approximation and solved using a convex optimization method. Finally, an efficient communication and computation resource allocation (ECCRA) scheme is ultimately achieved based on the block coordinate descent (BCD) framework. Simulations confirm that the proposed BCD-based ECCRA scheme significantly enhances system energy efficiency compared to benchmark testing schemes, thereby promoting the development of intelligent and sustainable transportation ecosystems.
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6790-6805
Task Chain-Oriented Trajectory and Resource Optimization in UAV-Assisted Multi-Agent Wireless Networks via Cognitively Informed Reinforcement Learning
Unmanned aerial vehicles (UAVs) have emerged as a promising solution to extend coverage and support communication–computation coordination in dynamic, infrastructure-sparse wireless networks. In UAV-assisted multi-agent systems, ground devices often execute task chains consisting of interdependent subtasks with strict sequential constraints, demanding adaptive scheduling and efficient resource coordination under continuous connectivity. However, existing approaches frequently ignore temporal dependencies and the long-term effects of scheduling decisions, leading to cascading delays and inefficient resource utilization. This paper proposes a cognitively informed decision transformer (CIDT) framework for joint trajectory and resource optimization in UAV-assisted multi-agent wireless networks. The framework explicitly captures subtask dependencies and inter-agent interactions to enable coordinated, preference-driven scheduling, and employs future-impact-aware trajectory representations with multi-objective utility modeling to balance latency, energy consumption, and task priorities. Simulation results show that the proposed framework significantly improves task completion efficiency, reduces end-to-end latency, and enhances adaptability under dynamic network conditions compared with state-of-the-art baselines.
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6790-6805
Task Chain-Oriented Trajectory and Resource Optimization in UAV-Assisted Multi-Agent Wireless Networks via Cognitively Informed Reinforcement Learning
Unmanned aerial vehicles (UAVs) have emerged as a promising solution to extend coverage and support communication–computation coordination in dynamic, infrastructure-sparse wireless networks. In UAV-assisted multi-agent systems, ground devices often execute task chains consisting of interdependent subtasks with strict sequential constraints, demanding adaptive scheduling and efficient resource coordination under continuous connectivity. However, existing approaches frequently ignore temporal dependencies and the long-term effects of scheduling decisions, leading to cascading delays and inefficient resource utilization. This paper proposes a cognitively informed decision transformer (CIDT) framework for joint trajectory and resource optimization in UAV-assisted multi-agent wireless networks. The framework explicitly captures subtask dependencies and inter-agent interactions to enable coordinated, preference-driven scheduling, and employs future-impact-aware trajectory representations with multi-objective utility modeling to balance latency, energy consumption, and task priorities. Simulation results show that the proposed framework significantly improves task completion efficiency, reduces end-to-end latency, and enhances adaptability under dynamic network conditions compared with state-of-the-art baselines.
- 19 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-6
DDPG-Based Resource Management in UAV-Aided Integrated Sensing and Edge Computation Systems
Intelligent transportation systems currently face significant challenges in sensing capabilities and computational latency at the network edge. To address these limitations, this paper proposes an unmanned aerial vehicle (UAV)-assisted in tegrated sensing and edge computation (ISEC) framework that jointly optimizes sensing and computational resource allocation in low-altitude networks. We formulate a constrained optimization problem to minimize the maximum computation latency among all UAVs while meeting sensing accuracy requirements, and solve it through a novel deep deterministic policy gradient-based algorithm designed explicitly for ISEC systems. The proposed solution features a hybrid action space for continuous-discrete decision-making and a multi-objective reward function that balances latency and sensing performance. Simulation results demonstrate that our approach achieves a 19.5% reduction in computation latency compared to benchmark schemes while maintaining a certain sensing rate threshold under mobility conditions, significantly enhancing the efficiency of next-generation intelligent transportation systems.
- 19 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-6
DDPG-Based Resource Management in UAV-Aided Integrated Sensing and Edge Computation Systems
Intelligent transportation systems currently face significant challenges in sensing capabilities and computational latency at the network edge. To address these limitations, this paper proposes an unmanned aerial vehicle (UAV)-assisted in tegrated sensing and edge computation (ISEC) framework that jointly optimizes sensing and computational resource allocation in low-altitude networks. We formulate a constrained optimization problem to minimize the maximum computation latency among all UAVs while meeting sensing accuracy requirements, and solve it through a novel deep deterministic policy gradient-based algorithm designed explicitly for ISEC systems. The proposed solution features a hybrid action space for continuous-discrete decision-making and a multi-objective reward function that balances latency and sensing performance. Simulation results demonstrate that our approach achieves a 19.5% reduction in computation latency compared to benchmark schemes while maintaining a certain sensing rate threshold under mobility conditions, significantly enhancing the efficiency of next-generation intelligent transportation systems.