Junyang He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junyang He has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoheng Deng
Central South University
3 shared publications - Xiangjian He
University of Nottingham Ningbo China
2 shared publications - Geyong Min
University of Exeter
1 shared publication - Jingjing Zhang
Central South University
1 shared publication - Jinsong Gui
Central South University
1 shared publication - Pan Zhao1 shared publication
Latest Publications
- 1 November 2026
- Published by Elsevier in Pattern Recognition
- Vol. 184
SFD-CAM: A spatial–frequency domain driven framework for multi-structure OCTA image segmentation
- 1 November 2026
- Published by Elsevier in Pattern Recognition
- Vol. 184
SFD-CAM: A spatial–frequency domain driven framework for multi-structure OCTA image segmentation
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-15
Energy-Efficient and Stable Task Offloading and Resource Allocation in Space-Air-Ground Integrated Networks
Task scheduling in sixth-generation (6G) space-air-ground integrated networks (SAGIN) faces fundamental challenges due to limited terrestrial infrastructure, time-varying wireless links, and stochastic task arrivals. In such dynamic environments, task offloading and resource scheduling decisions are strongly coupled over time through queue evolution, which makes it difficult to simultaneously guarantee service stability and energy efficiency. To address this issue, we formulate a long-term stochastic optimization problem that minimizes the average system energy consumption while stabilizing task queues. Leveraging Lyapunov drift-plus-penalty optimization, we develop an online Four-Phase Computation Offloading and Resource Scheduling (FCORS) algorithm that decomposes the per-slot control into four tractable subproblems and operates without any offline training. Simulation results demonstrate that FCORS achieves performance parity with state-of-the-art Deep Reinforcement Learning (DRL) baselines. Specifically, under heavy traffic loads, it reduces energy consumption by approximately 51.7 (QOA) while suppressing queue backlogs by approximately 90.4 (GEA). Therefore, FCORS provides a robust and lowcomplexity solution for energy-efficient task scheduling in future 6G SAGIN-enabled MEC systems.
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-15
Energy-Efficient and Stable Task Offloading and Resource Allocation in Space-Air-Ground Integrated Networks
Task scheduling in sixth-generation (6G) space-air-ground integrated networks (SAGIN) faces fundamental challenges due to limited terrestrial infrastructure, time-varying wireless links, and stochastic task arrivals. In such dynamic environments, task offloading and resource scheduling decisions are strongly coupled over time through queue evolution, which makes it difficult to simultaneously guarantee service stability and energy efficiency. To address this issue, we formulate a long-term stochastic optimization problem that minimizes the average system energy consumption while stabilizing task queues. Leveraging Lyapunov drift-plus-penalty optimization, we develop an online Four-Phase Computation Offloading and Resource Scheduling (FCORS) algorithm that decomposes the per-slot control into four tractable subproblems and operates without any offline training. Simulation results demonstrate that FCORS achieves performance parity with state-of-the-art Deep Reinforcement Learning (DRL) baselines. Specifically, under heavy traffic loads, it reduces energy consumption by approximately 51.7 (QOA) while suppressing queue backlogs by approximately 90.4 (GEA). Therefore, FCORS provides a robust and lowcomplexity solution for energy-efficient task scheduling in future 6G SAGIN-enabled MEC systems.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 16142-16154
MDNet: Multimodal Cooperative Perception via Spatial Alignment of Modal Decision-Making
Through internet of things (IOT) communication technology, collaborative perception enhances a vehicle’s capacity to discern its surroundings while driving by integrating and synchronizing sensor data from multiple agents. With the advancement of cooperative perception techniques in single-modality methods, there has been a growing trend toward integrating multi-modal data from heterogeneous sensors in recent years. However, due to the data heterogeneity inherent in diverse sensors, Bird’s Eye View (BEV) maps generated from different types of sensors may exhibit local discrepancies in the spatial representation of entity positions. Furthermore, individual agents may produce uncertain and flawed feature representations in real noisy environments. The influence of this indeterminacy exacerbates the issue of local inconsistency, leading to misalignment of the detected target during BEV alignment and fusion, thereby reducing detection accuracy. To address these problems, we propose a modal decision-making spatial alignment cooperative perception network (MDNet). First, the network generates BEV feature maps through dense depth image supervision for voxel feature extraction and model-guided selective feature fusion. Subsequently, we achieve enhanced accuracy in object detection by performing spatial alignment of BEV representations generated from two distinct sensors, both globally and locally within the spatial domain. Besides, we employ a cascaded centralized pyramid strategy during the message fusion stage, facilitating flexible sampling across horizontal and vertical spatial dimensions, promoting deep interaction among multiple agents. We conduct quantitative and qualitative experiments on the public OPV2V and DAIR-V2X-C benchmarks, and our proposed MDNet exhibits superior performance and stronger robustness in the 3D object detection task, providing more precise target detection results.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (11) , 16142-16154
MDNet: Multimodal Cooperative Perception via Spatial Alignment of Modal Decision-Making
Through internet of things (IOT) communication technology, collaborative perception enhances a vehicle’s capacity to discern its surroundings while driving by integrating and synchronizing sensor data from multiple agents. With the advancement of cooperative perception techniques in single-modality methods, there has been a growing trend toward integrating multi-modal data from heterogeneous sensors in recent years. However, due to the data heterogeneity inherent in diverse sensors, Bird’s Eye View (BEV) maps generated from different types of sensors may exhibit local discrepancies in the spatial representation of entity positions. Furthermore, individual agents may produce uncertain and flawed feature representations in real noisy environments. The influence of this indeterminacy exacerbates the issue of local inconsistency, leading to misalignment of the detected target during BEV alignment and fusion, thereby reducing detection accuracy. To address these problems, we propose a modal decision-making spatial alignment cooperative perception network (MDNet). First, the network generates BEV feature maps through dense depth image supervision for voxel feature extraction and model-guided selective feature fusion. Subsequently, we achieve enhanced accuracy in object detection by performing spatial alignment of BEV representations generated from two distinct sensors, both globally and locally within the spatial domain. Besides, we employ a cascaded centralized pyramid strategy during the message fusion stage, facilitating flexible sampling across horizontal and vertical spatial dimensions, promoting deep interaction among multiple agents. We conduct quantitative and qualitative experiments on the public OPV2V and DAIR-V2X-C benchmarks, and our proposed MDNet exhibits superior performance and stronger robustness in the 3D object detection task, providing more precise target detection results.