物联网学报2025，Vol.9Issue(1)：89-102,14.DOI:10.11959/j.issn.2096-3750.2025.00454
基于深度强化学习模型融合的海洋气象传感器网络入侵检测方法
Intrusion detection based on deep reinforcement learning model fusion for maritime meteorological sensor networks
摘要
Abstract
Maritime meteorological sensor networks(MMSN)differ from traditional land-based networks,presenting new challenges for intrusion detection tasks.A satellite-based detection method for maritime meteorological sensor net-works was designed using satellite communication technology.The network structure and characteristics of maritime me-teorological sensor networks were analyzed in this method.Research was conducted on improving the detection perfor-mance of intrusion detection systems(IDS)from the perspectives of algorithms and loss functions.A maritime meteoro-logical sensor network intrusion detection method based on the fusion of deep reinforcement learning models was pro-posed.Firstly,light gradient boosting machine(LightGBM),1D conventional neural network(1D-CNN),and 2D conven-tional neural network(2D-CNN)classifiers with improved loss functions were established to comprehensively extract the temporal and spatial features of the intrusion detection data in maritime meteorological sensor networks.Secondly,a model fusion method was designed based on the stacking and averaging principles of model fusion technology.This method leveraged the strengths of the base classifiers and mitigated their weaknesses,thereby enhancing the overall sys-tem detection performance.Finally,simulation experiment results demonstrate that the proposed intrusion detection method can effectively improve the detection performance for a few types of attack data and enhance the robustness of the system.关键词
海洋气象传感器网络/入侵检测系统/模型融合/焦点损失函数Key words
MMSN/IDS/model fusion/focal loss function分类
电子信息工程引用本文复制引用
张文潇,苏新,顾依凌..基于深度强化学习模型融合的海洋气象传感器网络入侵检测方法[J].物联网学报,2025,9(1):89-102,14.基金项目
国家自然科学基金资助项目(No.62371181) （No.62371181）
常州市政策引导类计划国际科技合作/港澳台科技合作项目(No.CZ20230029)The National Natural Science Foundation of China(No.62371181),The Changzhou Science and Technology In-ternational Cooperation Program(No.CZ20230029) （No.CZ20230029）
