基于卷积神经网络的无线传感器网络链路异常检测算法  

Link anomaly detection algorithm for wireless sensor networks based on convolutional neural networks

作　　者：特木尔朝鲁[1] 张亚萍 TEMUR Chao-lu;ZHANG Ya-ping(College of Arts and Sciences,Shanghai Maritime University,Shanghai 201306,China)

机构地区：[1]上海海事大学文理学院,上海201306

出　　处：《吉林大学学报（工学版）》2024年第8期2295-2300,共6页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(10461005).

摘　　要：为精准检测无线传感器网络异常链路,提出基于CNN的无线传感器网络链路异常检测算法。采用并发多线程技术设计网络链路异常检测功能,利用CNN建立网络链路异常检测训练模型。输入网络链路数据,卷积处理网络链路信息,提取网络链路特征向量,并通过下采函数处理,分析网络链路异常行为,使用向量映射方式表示异常部分向量,经过Softmax函数分类器完成分类检测。实验结果表明:本文方法能有效提升链路异常分类精度和检测精度,且用时较短。To accurately detect abnormal links in wireless sensor networks,a CNN based wireless sensor network link anomaly detection algorithm is proposed.Design network link anomaly detection function using concurrent multithreading technology,and establish a training model for network link anomaly detection using CNN.Input network link data,convolve network link information,extract network link feature vectors,and analyze network link abnormal behavior through down sampling function processing.Use vector mapping to represent the abnormal part vector,and complete classification detection through Softmax function classifier.The experimental results show that the proposed method can effectively improve the accuracy of link anomaly classification and detection,and it takes a short time.

关 键 词：无线传感器网络 卷积神经网络 卷积运算 激活函数 下采样层 链路特征 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]