HDHuazheng Du

Huazheng Du

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huazheng Du has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

    • 19 November 2026
    • Published by MDPI AG in Preprints.org
      • https://doi.org/10.20944/preprints202611.2003.v1
    Open Access

    Feedback-Guided Frame Replication for Deadline-Sensitive Industrial Wireless Networks

    by Zijian Wang, Na Xia, Huazheng Du, Bohao Zhao, Ruiqi Hu, Yunhe Yu

    Industrial sensing and automation require wireless updates to arrive within short deadlines despite contention and temporary link degradation. Sending copies over two paths creates additional delivery opportunities, while coordinating their admission and release controls queue buildup. This paper proposes a feedback-guided frame-replication framework that jointly manages primary admission and backup timing. The core Paced policy tracks packets awaiting transmission or completion feedback on both paths, using this information to select paths, regulate packet admission, and schedule backup copies. Guarded multilayer perceptron (MLP) timing and offline Kolmogorov--Arnold network (KAN) protection models provide complementary prediction-based designs. The framework is implemented on four AntSDR E200 radios. A nine-policy confirmation comprises 43,200 original packets across four conditions and three restarted sessions. Paced achieves the highest aggregate timely-delivery ratio among the nine evaluated policies. In its prespecified comparison against fixed 5-ms waiting with a two-frame backup-queue threshold, Paced increases 10-ms source-clock application-receipt attainment from 93.92% to 95.19%, reducing deadline misses by 20.89% and access-point submissions by 4.63%. More timely returns and fewer submissions are observed in each session total. Packet-level analyses connect delivery outcomes to admission, backup budgets, and execution timing, demonstrating the value of coordinated admission and selective replication for deadline-sensitive industrial wireless communication.

  • Open Access

    HDAO: A Hierarchical Curiosity-Driven Reinforcement Learning Approach for AUV Dynamic Obstacle Avoidance

    by Huazheng Du, Qian Liu, Xu Liu, Na Xia

    Autonomous obstacle avoidance is a critical capability for Autonomous Underwater Vehicles (AUVs) to operate safely in dynamic and uncertain marine environments. Traditional AUV control methods rely on precise physical modeling and preset rules, yet they struggle to adapt to multiple sources of uncertainty, such as random initial states, dynamic obstacles, and varying currents. In recent years, deep reinforcement learning has provided a new avenue for data-driven adaptive policy learning. However, it remains insufficient for handling long-horizon tasks with sparse rewards. While hierarchical reinforcement learning can mitigate reward sparsity through temporal abstraction, it often faces challenges including exploration–exploitation imbalance, slow global convergence, and insufficient safety guarantees. Furthermore, most existing studies neglect dynamic environmental disturbances and task continuity, which further limits the practical application of these algorithms. To address these challenges, this paper proposes a hierarchical curiosity-driven AUV obstacle avoidance algorithm (HDAO), designed for autonomous obstacle avoidance in dynamic and uncertain underwater environments. The core design of HDAO incorporates several key innovations. Firstly, it introduces a Collision Threat Index for dynamic obstacles, which enables explicit risk perception and quantifies collision threats, thereby enhancing the policy’s generalization and robustness. Secondly, a task-decoupled hierarchical architecture is employed to synergistically optimize global path planning and local obstacle avoidance behaviors. This approach effectively manages long-horizon navigation tasks while alleviating high-dimensional training pressure. Finally, a novel reward mechanism is designed by integrating hierarchical active exploration with curiosity-driven passive exploration. This mechanism effectively incentivizes the agent to explore unvisited areas under sparse reward conditions and dynamically balances exploration and exploitation. Experimental results demonstrate that HDAO significantly outperforms existing methods in terms of obstacle avoidance success rate, training convergence speed and robustness against external disturbances.

  • Open Access

    Research on AUV Data Collection Method Based on 3D Dirichlet in Underwater Sensor Networks

    by Huazheng Du, Duoli Feng, Na Xia

    How to collect data from network nodes through an autonomous underwater vehicles (AUV) in a sparsely deployed underwater sensor networks (UWSNs) is a fundamental key issue. This paper proposes an AUV data collection method based on 3D Dirichlet vertexes (DCDV). Firstly, the AUV data collection point set (V) is generated by Dirichlet graphics method. Secondly, a bisection graph is used to describe the dominating relationship of data collection points to nodes, and the communication radius of nodes is used to screen the effective dominance relationship between them. Then the set of AUV candidate data collection points () is minimized according to the paternal genetic criterion. Finally, the hybrid particle swarm search algorithm is used to obtain the optimal path (). Simulation results corroborate the effectiveness of the proposed methods.

  • Open Access

    IMF 2 O 2 : A Fully Connected Sensor Deployment Algorithm for Underwater Sensor Networks

    by Na Xia, Yin Wang, Bin Chen, Huazheng Du, Chaonong Xu, Rong Zheng

    To address the problems of node deployment schemes in existing underwater sensor networks that lack consideration of network connectivity and high deployment costs, this article constructs an optimization model that maximizes network coverage and minimizes deployment costs while ensuring full connectivity. For the NP-hard property of this optimization model, an improved moth flame optimization node deployment algorithm based on fuzzy operators (IMF 2 O 2 ) is proposed. First, comprehensively considering the two performance metrics of network coverage and network connectivity, a multi-objective selection mechanism based on fuzzy operators is proposed to improve network coverage while ensuring full connectivity. Second, a fixed number of nodes are used to monitor the target event points, transforming the node deployment of sensors into an optimal problem and proposing an improved moth flame optimization algorithm to solve this problem. Finally, the two metrics of coverage and deployment cost are measured and the fuzzy operator is used to select the optimal number of nodes to be deployed. Numerical results showed that the proposed algorithm improved network coverage rate by 10%, 22%, and 25%, and improved network connectivity rate by 12%, 20%, and 8% as compared to PSSD, RAWS, and VODA, respectively, while ensuring full connectivity.


  • Open Access

    Study on Gibbs Optimization-Based Resource Scheduling Algorithm in Data Aggregation Networks

    by Sheng Ding, Huazheng Du, Na Xia, Shaojie Li, Yongtang Yu

    In data aggregation networks (WSNs, ad hoc, mesh, etc.), it is key to schedule the network resources, such as channels and TDMA time slots, to minimize the communication conflict and optimize the network data-gathering performance. In this paper, the resources scheduling problem is formulated as a vertex coloring problem in graph theory. Then, a multi-channel TDMA scheduling algorithm based on the Gibbs optimization is proposed. By defining the Gibbs energy expression according to the objective function of the problem, the joint probability of channel and time slot can be computed for the optimized selection of channels and time slots. This algorithm is low-complexity and its convergence performance can be proven. Experiments with different network parameters demonstrate that the proposed algorithm can reduce the communication conflict, improve the network throughput, and effectively reduce the network transmission delay and scheduling length for the data aggregation networks.


  • Open Access

    A Navigation Satellites Selection Method Based on ACO With Polarized Feedback

    by Huazheng Du, Yunqing Hong, Na Xia, Guofu Zhang, Yongtang Yu, Jiwen Zhang

    Selecting the optimal satellite subset for positioning from all satellites in view can not only achieve positioning accuracy but also reduce the computational burden. In this paper, a navigation satellites selection method is proposed based on ant colony optimization with the improvement of polarized feedback (ACO-PF). Firstly, the satellite selection problem is described as a combinatorial optimization problem, and the noise weighted geometric dilution of precision (NWGDOP) is defined as the criterion for satellite selection. Then the ant colony optimization (ACO) is incorporated to solve the problem, and a polarized feedback mechanism is presented to improve the convergence speed of algorithm. Meanwhile, a perturbation operator is designed to improve the global searching ability of the algorithm. The numerical experimental results show that ACO-PF can select the superior satellites combination which provides highprecision positioning. And its convergence outperforms the related algorithms by up to 50%. Besides, the achieved NWGDOP of ACO-PF is usually 0.065 smaller than ACO. Therefore, the ACO-PF method can be considered as a promising candidate for satellite selecting in navigation applications.