ZLZhisheng Li

Zhisheng Li

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


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


Latest Publications

  • Open Access

    An Underwater Source Location Privacy Protection Scheme Based on Game Theory in a Multi-Attacker Cooperation Scenario

    by Beibei Wang, Xiufang Yue, Kun Hao, Yonglei Liu, Zhisheng Li, Xiaofang Zhao

    Ensuring source location privacy is crucial for the security of underwater acoustic sensor networks amid the growing use of marine environmental monitoring. However, the traditional source location privacy scheme overlooks multi-attacker cooperation strategies and also has the problem of high communication overhead. This paper addresses the aforementioned limitations by proposing an underwater source location privacy protection scheme based on game theory under the scenario of multiple cooperating attackers (SLP-MACGT). First, a transformation method of a virtual coordinate system is proposed to conceal the real position of nodes to a certain extent. Second, through using the relay node selection strategy, the diversity of transmission paths is increased, passive attacks by adversaries are resisted, and the privacy of source nodes is protected. Additionally, a secure data transmission technique utilizing fountain codes is employed to resist active attacks by adversaries, ensuring data integrity and enhancing data transmission stability. Finally, Nash equilibrium could be achieved after the multi-round evolutionary game theory of source node and multiple attackers adopting their respective strategies. Simulation experiments and performance evaluation verify the effectiveness and reliability of SLP-MACGT regarding aspects of the packet forwarding success rate, security time, delay and energy consumption: the packet delivery rate average increases by 30%, security time is extended by at least 85%, and the delay is reduced by at least 90% compared with SSLP, PP-LSPP, and MRGSLP.


  • Open Access

    A Dynamic Trust Model for Underwater Sensor Networks Fusing Deep Reinforcement Learning and Random Forest Algorithm

    by Beibei Wang, Xiufang Yue, Yonglei Liu, Kun Hao, Zhisheng Li, Xiaofang Zhao

    Underwater acoustic sensor networks (UASNs) are vital for applications like marine environmental monitoring, disaster prediction, and national defense security. Due to the prolonged exposure of underwater sensor nodes in unattended and potentially hostile environments, the application of UASNs is confronted with numerous security threats. Trust models are an important means to detect anomalous nodes in UASNs and ensure security. However, when confronted with intricate underwater surroundings, the assessment of trust is prone to disruption, and current trust models lack a flexible mechanism for updating trust. Consequently, this study introduces a dynamic evaluation trust model (DRFTM) for underwater acoustic sensor networks that integrate deep reinforcement learning and the random forest algorithm. First, the DRFTM comprehensively considers indicators including communication, data, energy, and environment to provide reliable trust evidence for the next evaluation; second, under the conditions of node mobility and dynamic updating of network topology, we propose a predictive model for assessing the trust status of sensor nodes based on random forest training; last, the utilization of deep reinforcement learning is instrumental in determining the most effective trust update strategy, leading to improved detection accuracy of the trust model. The simulation results demonstrate the effectiveness of the DRFTM in detecting malicious nodes, reducing false positives, and accurately assessing trust, achieving a remarkable 99% accuracy in identifying malicious nodes.


  • Open Access

    A Ship Detection Model Based on Dynamic Convolution and an Adaptive Fusion Network for Complex Maritime Conditions

    by Zhisheng Li, Zhihui Deng, Kun Hao, Xiaofang Zhao, Zhigang Jin

    Ship detection is vital for maritime safety and vessel monitoring, but challenges like false and missed detections persist, particularly in complex backgrounds, multiple scales, and adverse weather conditions. This paper presents YOLO-Vessel, a ship detection model built upon YOLOv7, which incorporates several innovations to improve its performance. First, we devised a novel backbone network structure called Efficient Layer Aggregation Networks and Omni-Dimensional Dynamic Convolution (ELAN-ODConv). This architecture effectively addresses the complex background interference commonly encountered in maritime ship images, thereby improving the model’s feature extraction capabilities. Additionally, we introduce the space-to-depth structure in the head network, which can solve the problem of small ship targets in images that are difficult to detect. Furthermore, we introduced ASFFPredict, a predictive network structure addressing scale variation among ship types, bolstering multiscale ship target detection. Experimental results demonstrate YOLO-Vessel’s effectiveness, achieving a 78.3% mean average precision (mAP), surpassing YOLOv7 by 2.3% and Faster R-CNN by 11.6%. It maintains real-time detection at 8.0 ms/frame, meeting real-time ship detection needs. Evaluation in adverse weather conditions confirms YOLO-Vessel’s superiority in ship detection, offering a robust solution to maritime challenges and enhancing marine safety and vessel monitoring.


  • Open Access

    CERRT: A Mobile Robot Path Planning Algorithm Based on RRT in Complex Environments

    by Kun Hao, Yang Yang, Zhisheng Li, Yonglei Liu, Xiaofang Zhao

    In complex environments, path planning for mobile robots faces challenges such as insensitivity to the environment, low efficiency, and poor path quality with the rapidly-exploring random tree (RRT) algorithm. We propose a novel algorithm, the complex environments rapidly-exploring random tree (CERRT), to address these issues. The CERRT algorithm builds upon the RRT approach and incorporates two key components: a pre-allocated extension node method and a vertex death mechanism. These enhancements aim to improve vertex utilization and overcome the problem of becoming trapped in concave regions, a limitation of traditional algorithms. Additionally, the CERRT algorithm integrates environment awareness at collision points, enabling rapid identification and navigation through narrow passages using local simple sampling techniques. We also introduce the bidirectional shrinking optimization strategy (BSOS) based on the pruning optimization strategy (POS) to further enhance the quality of path solutions. Extensive simulations demonstrate that the CERRT algorithm outperforms the RRT and RRV algorithms in various complex environments, such as mazes and narrow passages. It exhibits shorter running times and generates higher-quality paths, making it a promising approach for mobile robot path planning in challenging environments.


  • Top Cited Papers

    An Insulator Defect Detection Model in Aerial Images Based on Multiscale Feature Pyramid Network

    by Kun Hao, Guanke Chen, Lu Zhao, Zhisheng Li, Yonglei Liu, Chuanqi Wang

    The faults caused by insulator defects will seriously threaten the operational safety of the power grid. Therefore, insulator defect detection plays a crucial role in inspecting transmission lines. Compared with traditional methods, the network such as You Only Look Once (YOLO) family based on deep learning has high accuracy and strong robustness in insulator recognition and fault detection. However, the performance of these network is usually affected by the shooting conditions as well as aerial images with diverse types of insulators and complex backgrounds, resulting in poor detection result. In addition, the relatively small insulator fault (bunch-drop) area in aerial images will make detection difficult. To solve these problems, this article proposes an improved insulator defect detection model based on YOLOv4 (ID-YOLO). To create our model, we design a new backbone network structure, cross-stage partial and residual split attention network (CSP-ResNeSt), that can solve the interference problem of complex backgrounds in aerial images to enhance the network’s feature extraction capability. In addition, we adopt a new multiscale bidirectional feature pyramid network with simple attention module (Bi-SimAM-FPN), which can address the difficulty of identifying a small scale of insulator defects in an image for more efficient feature fusion. We experimentally demonstrate that the mean average precision (mAP) of the proposed model is 95.63%, which is 3.5% higher than that of the YOLOv4. Most importantly, the detection speed of this model can reach 63 frames/s, which meets the requirements of real-time detection of insulator bunch-drop faults.