Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jianmin Yang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Topology-Generalizable Reinforcement Learning for Adaptive Routing in IoUT Networks

    by Jianmin Yang, Yonghui Zhong, Yue Ma, Muzi Cui, Zhuoqian Wu, Pengyu Du, Guangjie Han

  • End-to-End Delay Estimation Under Multi-Hop Recurrence in Dynamic Integrated Networks

    by Jiahui Pei, Quansheng Guan, Hongbin Chen, Jianmin Yang, Chuanlin Liu

    The increasing scale of modern networks, particularly dynamic integrated networks spanning space, air, ground, and sea, introduces substantial challenges to end-to-end delay estimation due to strong node heterogeneity and volatile link conditions. These dynamics impair the accuracy and generalizability of traditional delay estimation methods, especially under diverse Quality of Service (QoS) requirements. To address this issue, we propose a stochastic particles and variational Bayesian estimation (SPAVE) scheme. The method first adopts stochastic network calculus (SNC) to model the arrival and service processes, and derives a recurrence relation for downstream delay as a function of upstream delay and local load. This recurrence relation is reformulated as a conditional distribution that characterizes the downstream delay at each hop, enabling hop-by-hop delay estimation through local parameter optimization and structured propagation across multi-hop nodes. By reducing the effective parameter dimensionality via stochastic particle sampling and rapidly refining the selected high probability particles through variational Bayesian inference, enabling SPAVE to adapt to dynamic integrated networks. Simulation results show that SPAVE achieves a mean absolute error below 10$^{-3}$.

  • Top Cited Papers

    Intelligent Reinforcement-Learning Routing Protocol With Integrated Power Control for Underwater Acoustic Sensor Networks

    by Jianmin Yang, Ying Huang, Jiahui Wang, Jiajing Chen, Tongwei Zhang, Guangjie Han

    Underwater acoustic sensor networks (UWASNs) play a vital role in ocean exploration, environmental monitoring, and disaster prevention by enabling precise and efficient data collection in underwater environments. However, designing efficient UWASNs routing protocols is a complex challenge because of energy limitations as well as link instability within underwater environments. For the purpose of improving network dependability and to maximize network transmission efficiency, an intelligent reinforcement-learning routing protocol with integrated Power-Control (IR2P) is proposed. In IR2P, we define a reward function within reinforcement learning (RL) that combines energy, distance to the sink, and link quality to determine the most suitable next hop node in routing decisions. Furthermore, IR2P employs a convex optimization-based power allocation strategy that achieves optimal cross-band distribution, ensuring fairness across frequency bands while avoiding overload on any single frequency. This approach reduces interference, improves energy efficiency, and enhances link reliability under complex acoustic conditions. Based on MATLAB simulation results, IR2P exhibits good performance in the underwater dynamic network environment in terms of packet loss rate, energy consumption, end-to-end delay, deviation factor, and other aspects, compared with the two representative underwater routing protocols (VBF and HH-VBF).


  • K -Means++-Based Secure and Efficient Routing Protocol Design for Underwater Sensor Networks

    by Jianmin Yang, Zhuoqian Wu, Ying Huang, Ming Gong, Xiaojun Zhang, Yue Ma, Guangjie Han

    The energy expenditure of underwater sensor nodes significantly exceeds the expenditure of terrestrial sensor nodes due to the challenging conditions of underwater acoustic communication channels. Maintaining and recharging sensor node equipment in underwater wireless sensor networks is particularly difficult due to the complexity of the underwater environment, thereby rendering energy consumption a pivotal concern. Clustering algorithms are regarded as a promising solution to address this challenge. By employing a K-means++-based clustering algorithm for more stable clustering of sensor nodes and taking into account pertinent factors involving node location, residual energy, and node degree in selecting the cluster’s head node, this study targets minimizing network energy consumption over the cluster establishment stage. During the data transfer stage, we prioritize network security and transmission efficiency by implementing a routing strategy that combines single-hop and double-hop propagation paths based on trust security models to mitigate risks from network attacks and black hole nodes. We also introduce a lightweight learning layer for per-link delivery and CH ranking, plus an unsupervised anomaly gate to down-weight suspicious nodes; both fuse with trust and fairness while leaving the physical and energy models unchanged. Simultaneously, AUVs are utilized to anchor sink nodes and directly transmit collected information from CHs. The results of the simulation in MATLAB indicate that the suggested routing protocol KSERP successfully balances and lessens the total energy consumption of the network while offering protection from malicious node attacks.


  • Open Access

    WLQRP: A Weighting Link-Quality-Based Routing Protocol for Underwater Sensor Networks

    by Jianmin Yang, Jiahui Wang, Haitao Yu, Yexin Gao, Zhuoqian Wu, Zhihong Peng

    Due to challenges posed by long propagation distances, high mobility, limited bandwidth, multipath propagation, and Doppler effects in underwater acoustic sensor networks (UASNs), the design of routing protocols faces numerous complexities. To enhance reliability in sparse node regions and reduce network energy consumption, this paper proposes a dependable and energy-efficient routing protocol termed WLQRP for weighting link-quality-based routing protocol. WLQRP leverages link quality information between nodes for data forwarding. When computing the link quality between nodes, it considers not only the historical transmission success ratio between nodes and their immediate relay but also incorporates the link quality between the relay and the relay’s next-hop nodes. This approach effectively reduces the likelihood of encountering void regions. Moreover, the protocol judiciously selects the next-hop node to improve transmission success rates, thereby minimizing data packet retransmissions and reducing energy consumption. We conduct MATLAB simulations to evaluate the WLQRP protocol, comparing it against the VBF (vector-based forwarding) and the HH-VBF (hop-by-hop vector-based forwarding) underwater routing protocol. Experimental results demonstrate that WLQRP enhances network performance in terms of data transmission rate, energy consumption, and end-to-end delay. These findings validate the efficacy of the proposed protocol.


  • Open Access

    EERP: An energy-efficient and reliable routing protocol for underwater acoustic wireless networks

    by Jiahui Wang, Zhihong Peng, Zhuoqian Wu, Xiaojun Zhang, Junwei Gao, Jianmin Yang

    Underwater acoustic wireless sensor networks are crucial for underwater monitoring, underwater development and national defense applications. In order to solve the problems of long propagation, high mobility, limited bandwidth, multipath and Doppler effect in underwater acoustic sensor networks, this paper proposes an energy-efficient and reliable underwater routing protocol. This protocol leverages the link quality information of each node for data transmission. When selecting the optimal relay, it evaluates not only the transmission success rate between the node and the next-hop node but also considers the link quality of the next-hop node and its neighboring nodes. This approach effectively reduces the likelihood of nodes encountering communication gaps. Moreover, the protocol incorporates the concept of relay node persistence, significantly reducing the frequency of handshakes between nodes and conserving energy. Ultimately, the efficacy of EERP was verified through MATLAB simulation analysis.

  • Underwater Acoustic Communication

    by Lu Ma, Gang Qiao, Jianmin Yang

  • Underwater Acoustic Sensor Network

    by Jianmin Yang, Lu Ma, Gang Qiao

  • Open Access

    A graph-based narrowband matched-field source localization method

    by Peng Xiao, Jianmin Yang

    Matched field processing (MFP) has been regarded as one of the most successful acoustical methods for positioning underwater sources. In this paper, the narrowband MFP method is combined with a recently developed framework—the graph signal processing (GSP) method. Following the paradigm of GSP, a spatial adjacency matrix is constructed for the arbitrary distributed sensors based on the Green's function, then the source is located by utilizing the graph Fourier transform. The simulation results illustrate that the graph-based MFP outperforms the conventional MFP processors for its better accuracy and fewer requirements for sensor numbers.