Huadong Dai
Research Subjects
Huadong Dai has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Wenjing Yang
National university of defense technology, Changsha, China
2 shared publications - Xiaodong Yi
National University of Defense Technology
2 shared publications - Zimian Wei
National University of Defense Technology
2 shared publications - Chenlin Huang
National University of Defense Technology
1 shared publication Chuanwang Hou
School of Computer, National University of Defense Technology, Changsha, Hunan, China
1 shared publication- Dongsheng Li
PDL Lab, College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China
1 shared publication
Latest Publications
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 44 (07338716) , 4552-4569
Self-Attention Proximal Policy Optimization for Beam Tracking in mmWave Communications
Millimeter-wave (mmWave) communication systems are highly sensitive to user mobility and environmental changes, often suffering from rapid beam direction shifts and frequent link blockages. These dynamics pose significant challenges to maintaining reliable beam tracking. To enable accurate and robust beam tracking in dynamic environments, we propose a Self-Attention Proximal Policy Optimization (SAPPO) algorithm. The beam tracking task is modeled as a Partially Observable Markov Decision Process (POMDP), where the agent aims to maximize Received Signal Strength (RSS) using only current and previous signal observations, without relying on channel models or complex signal processing. By integrating a multi-head self-attention (MHSA) mechanism with a Gated Recurrent Unit (GRU), the policy network effectively captures temporal dependencies, enhancing the agent’s perception of user motion and channel state variations. To validate the approach, we construct three test scenarios with varying mobility and blockage complexity using the DeepMIMO dataset. Experimental results demonstrate that SAPPO consistently outperforms baseline methods such as DQN and PPO in terms of tracking accuracy, stability, and robustness. Notably, in challenging environments with frequent Line-Of-Sight (LOS)/Non-Line-Of-Sight (NLOS) transitions, SAPPO achieves a beam tracking success rate exceeding 95%, highlighting its strong adaptability and reliable performance under dynamic conditions.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 44 (07338716) , 4552-4569
Self-Attention Proximal Policy Optimization for Beam Tracking in mmWave Communications
Millimeter-wave (mmWave) communication systems are highly sensitive to user mobility and environmental changes, often suffering from rapid beam direction shifts and frequent link blockages. These dynamics pose significant challenges to maintaining reliable beam tracking. To enable accurate and robust beam tracking in dynamic environments, we propose a Self-Attention Proximal Policy Optimization (SAPPO) algorithm. The beam tracking task is modeled as a Partially Observable Markov Decision Process (POMDP), where the agent aims to maximize Received Signal Strength (RSS) using only current and previous signal observations, without relying on channel models or complex signal processing. By integrating a multi-head self-attention (MHSA) mechanism with a Gated Recurrent Unit (GRU), the policy network effectively captures temporal dependencies, enhancing the agent’s perception of user motion and channel state variations. To validate the approach, we construct three test scenarios with varying mobility and blockage complexity using the DeepMIMO dataset. Experimental results demonstrate that SAPPO consistently outperforms baseline methods such as DQN and PPO in terms of tracking accuracy, stability, and robustness. Notably, in challenging environments with frequent Line-Of-Sight (LOS)/Non-Line-Of-Sight (NLOS) transitions, SAPPO achieves a beam tracking success rate exceeding 95%, highlighting its strong adaptability and reliable performance under dynamic conditions.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 12084-12100
Semantic-Oriented Image Transmission and Resource Allocation for UAV Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 12084-12100
Semantic-Oriented Image Transmission and Resource Allocation for UAV Networks
- Open Access
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1356-1369
UGPU: Dynamically Constructing Unbalanced GPUs for Enhanced Resource Efficiency
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1356-1369
Open AccessUGPU: Dynamically Constructing Unbalanced GPUs for Enhanced Resource Efficiency
- 27 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9146-9153
micROS.BT: An Event-Driven Behavior Tree Framework for Swarm Robots
In this paper, we propose micROS.BT, an event-driven behavior tree (BT) framework aiming at supporting swarm-robot coordination. Compared with other BT frame-works, micROS.BT implements the event-driven way under the multi-thread mode, which can effectively save computing resources. Moreover, in order to ensure swarm-robot coordination, we optimize the implementation of the traditional blackboard and propose the multi-mode blackboard, which supports inner-tree, inter-tree, and inter-robot data sharing. Furthermore, considering the limited modularity of a single tree, micROS.BT realizes a mechanism called hierarchical tree management which involves inter-tree notifying and waiting functionalities, while ensuring that each tree is independent and self-scheduled. The effectiveness of micROS.BT is verified by simulation and real-robot experiments for different system settings, showing that a substantial improvement is achieved in comparison with the traditional BT implementations.
- 27 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9146-9153
micROS.BT: An Event-Driven Behavior Tree Framework for Swarm Robots
In this paper, we propose micROS.BT, an event-driven behavior tree (BT) framework aiming at supporting swarm-robot coordination. Compared with other BT frame-works, micROS.BT implements the event-driven way under the multi-thread mode, which can effectively save computing resources. Moreover, in order to ensure swarm-robot coordination, we optimize the implementation of the traditional blackboard and propose the multi-mode blackboard, which supports inner-tree, inter-tree, and inter-robot data sharing. Furthermore, considering the limited modularity of a single tree, micROS.BT realizes a mechanism called hierarchical tree management which involves inter-tree notifying and waiting functionalities, while ensuring that each tree is independent and self-scheduled. The effectiveness of micROS.BT is verified by simulation and real-robot experiments for different system settings, showing that a substantial improvement is achieved in comparison with the traditional BT implementations.
- Open Access
- 13 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 132438-132447
Person Re-Identification Based on Multi-Parts of Local Feature Network
Person re-identification has become increasing popular because of its widely application in computer vision. In this paper, we propose a novel, simple and efficient person re-id network called MPLFN. The network combines two tasks: the classification task and the metric learning task. In the classification task, we uniformly partition N feature parts from an image, and compute the person classification loss in each part separately. Computing the part loss separately guides the network to focus on every body part and learn discriminative representations for each of them. And then in the metric learning task, we recalculate the distance of two images by the shortest path between two sets of feature parts. Then the distances are put into a triplet loss to perform a dynamic part alignment during the training. With the joint learning of these two tasks, the performance of the network is significantly enhanced. Compared with existing person re-id works, MPLFN achieves a better performance on three mainstream person re-identification datasets. Extensive experiments have been conducted to validate our proposed method.
- 13 September 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 132438-132447
Open AccessPerson Re-Identification Based on Multi-Parts of Local Feature Network
Person re-identification has become increasing popular because of its widely application in computer vision. In this paper, we propose a novel, simple and efficient person re-id network called MPLFN. The network combines two tasks: the classification task and the metric learning task. In the classification task, we uniformly partition N feature parts from an image, and compute the person classification loss in each part separately. Computing the part loss separately guides the network to focus on every body part and learn discriminative representations for each of them. And then in the metric learning task, we recalculate the distance of two images by the shortest path between two sets of feature parts. Then the distances are put into a triplet loss to perform a dynamic part alignment during the training. With the joint learning of these two tasks, the performance of the network is significantly enhanced. Compared with existing person re-id works, MPLFN achieves a better performance on three mainstream person re-identification datasets. Extensive experiments have been conducted to validate our proposed method.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Enhanced Visual Loop Closing for Laser-Based SLAM
Three-dimensional (3D) laser-based simultaneous localization and mapping (SLAM) can provide real-time pose information and construct accurate 3D map. However, detecting loop closures is a challenging task in the 3D laser-based SLAM because of the heavy computational overheads. In this paper, we propose a visual method to simultaneously detect and correct loop closures in the 3D laser-based SLAM based on prior work. In particular, we improve the experiments and evaluate our method by analyzing computational errors. The experimental results on the KITTI dataset prove that our method can efficiently reduce motion accumulation errors and successfully ensure the consistency performance of loop closure correction.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Enhanced Visual Loop Closing for Laser-Based SLAM
Three-dimensional (3D) laser-based simultaneous localization and mapping (SLAM) can provide real-time pose information and construct accurate 3D map. However, detecting loop closures is a challenging task in the 3D laser-based SLAM because of the heavy computational overheads. In this paper, we propose a visual method to simultaneously detect and correct loop closures in the 3D laser-based SLAM based on prior work. In particular, we improve the experiments and evaluate our method by analyzing computational errors. The experimental results on the KITTI dataset prove that our method can efficiently reduce motion accumulation errors and successfully ensure the consistency performance of loop closure correction.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 254-259
A research on metric learning in computer vision and pattern recognition
Metric learning refers to the task of learning a distance function among objects. Recently, metric learning has drawn wide attention in the field of computer vision and pattern recognition. This paper seeks to examine metric learning from two different perspectives: conventional metric learning and deep metric learning. The formulation and principal of different metric learning are delineated and the advantages and disadvantages are then presented. The paper concludes with the discussion on the future direction of the development of metric learning.
- 1 March 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 254-259
A research on metric learning in computer vision and pattern recognition
Metric learning refers to the task of learning a distance function among objects. Recently, metric learning has drawn wide attention in the field of computer vision and pattern recognition. This paper seeks to examine metric learning from two different perspectives: conventional metric learning and deep metric learning. The formulation and principal of different metric learning are delineated and the advantages and disadvantages are then presented. The paper concludes with the discussion on the future direction of the development of metric learning.
- 1 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-71
Enabling User-Policy-Confined VM Migration in Trusted Cloud Computing
The trusted cloud environment model, based on the trusted computing technology, provides cloud users the capabilities to remotely attest the trustworthiness of cloud service. But unlike physical machine, the virtual machine is migratory among cloud nodes constantly which makes it hard for cloud users to guarantee the Virtual Machine (VM) is running in a trusted cloud node and its migration is consistent with user's policy. Since the migration operation is entirely transparent to cloud users, it is hard for them to launch the remote attestation with the existing remote attestation scheme. To guarantee the migration of VMs is consistent with user's policy, we propose a User-Policy-Confined VM Migration Protocol (UVMP), which provides a new attestation scheme that addresses the limitation and enables VM migration to be controllable and verifiable by cloud users by introducing the Ciphertext-Policy AttributeBased Encryption(CP-ABE) into attestation field. To demonstrate that UVMP is practical, we incorporate it in the Xen opensource virtualization platform and implement UTVMS: UserPolicy-Confined Trusted VM Migration System. Our evaluation suggests that the attestation scheme cannot lead to the obvious performance on the VM migration by analyzing the migration latency. The attestation scheme can provide greater flexibility for cloud users to control their own VM migration.
- 1 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-71
Enabling User-Policy-Confined VM Migration in Trusted Cloud Computing
The trusted cloud environment model, based on the trusted computing technology, provides cloud users the capabilities to remotely attest the trustworthiness of cloud service. But unlike physical machine, the virtual machine is migratory among cloud nodes constantly which makes it hard for cloud users to guarantee the Virtual Machine (VM) is running in a trusted cloud node and its migration is consistent with user's policy. Since the migration operation is entirely transparent to cloud users, it is hard for them to launch the remote attestation with the existing remote attestation scheme. To guarantee the migration of VMs is consistent with user's policy, we propose a User-Policy-Confined VM Migration Protocol (UVMP), which provides a new attestation scheme that addresses the limitation and enables VM migration to be controllable and verifiable by cloud users by introducing the Ciphertext-Policy AttributeBased Encryption(CP-ABE) into attestation field. To demonstrate that UVMP is practical, we incorporate it in the Xen opensource virtualization platform and implement UTVMS: UserPolicy-Confined Trusted VM Migration System. Our evaluation suggests that the attestation scheme cannot lead to the obvious performance on the VM migration by analyzing the migration latency. The attestation scheme can provide greater flexibility for cloud users to control their own VM migration.
- 1 January 2014
- Published by Springer Nature
- p. 188-199
Cloud-Oriented SAT Solver Based on Obfuscating CNF Formula
- 1 January 2014
- Published by Springer Nature
- p. 188-199
Cloud-Oriented SAT Solver Based on Obfuscating CNF Formula