MCMinghui Chen

Minghui Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Minghui Chen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:

  • Chen Zhang

    Three Gorges Hi‐Tech Information Technology Co., Ltd. Yichang China

    1 shared publication
  • Fuming Fan

    Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China

    1 shared publication
  • Haoran Zuo

    Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China

    1 shared publication
  • Jiaxiang Xu

    Three Gorges Hi‐Tech Information Technology Co., Ltd. Yichang China

    1 shared publication
  • Jieke Lu

    Electric Power Research Institute of Guangxi Power Grid Co., Ltd., Nanning 530000, China

    1 shared publication
  • Linya Peng

    Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China

    1 shared publication

Latest Publications

  • Deep Reinforcement Learning Microservice Deployment Algorithm Based on Simulated Annealing Optimization in Edge Computing Scenarios

    by Chen Zhang, Zhenhua Wang, Minghui Chen, Jiaxiang Xu, Yunsheng Xu, Haoran Zuo, Yu Xiao, Tianping Deng

    With the rapid development of microservice architectures, edge computing has become an important paradigm for service deployment. However, microservice deployment in edge environments still faces challenges such as resource constraints, network latency, bandwidth limitations, and load balancing. Achieving efficient and scalable deployment requires effective coordination of distributed resources under dynamic and heterogeneous conditions. Existing studies often overlook the time‐varying characteristics and resource heterogeneity of edge environments and lack a unified optimization framework for service quality, system stability, and migration cost. To address these issues, this paper proposes an efficient microservice deployment algorithm that combines Simulated Annealing (SA) and Deep Reinforcement Learning (DRL). The proposed SA‐DRL hybrid method monitors resource usage and network conditions in real time and dynamically adjusts deployment decisions to optimize service quality and resource utilization. Compared with three representative deployment baselines, the proposed SA‐DRL method achieves better overall performance in terms of convergence speed, resource balance, and robustness. It also maintains high efficiency and adaptability under scenarios of node‐scale expansion and workload increase. Experimental results demonstrate that the proposed method provides an effective solution for microservice deployment optimization in edge computing environments.

  • Open Access

    Physics-Aware Spatiotemporal Consistency for Transferable Defense of Autonomous Driving Perception

    by Yang Liu, Zishan Nie, Tong Yu, Minghui Chen, Zhiheng Yao, Jieke Lu, Linya Peng, Fuming Fan

    Autonomous driving perception systems are vulnerable to physical adversarial attacks. Existing defenses largely adopt loosely coupled architectures where visual and kinematic cues are processed in isolation, thus failing to exploit physical spatiotemporal consistency as a structural prior and often struggling to balance adversarial robustness, transferability, accuracy, and efficiency under realistic attacks. We propose a physics-aware trajectory–appearance consistency defense that detects and corrects spatiotemporal inconsistencies by tightly coupling visual semantics with physical dynamics. The module combines a dual-stream spatiotemporal encoder with endogenous feature orchestration and a frequency-domain kinematic embedding, turning tracking artifacts that are usually discarded as noise into discriminative cues. These inconsistencies are quantified by a Trajectory–Appearance Mutual Exclusion (TAME) energy, which supports a physics-aware switching rule to override flawed visual predictions. Operating on detector backbone features, outputs, and tracking states, the defense can be attached as a plug-in module behind diverse object detectors. Experiments on nuScenes, KITTI, and BDD100K show that the proposed defense substantially improves robustness against diverse categories of attacks: on nuScenes, it improves Correction Accuracy (CA) from 86.5% to 92.1% while reducing the computational overhead from 42 ms to 19 ms. Furthermore, the proposed defense maintains over 71.0% CA when transferred to unseen detectors and sustaining 72.4% CA under adaptive attackers.