基于大数据优化神经网络的船舶通信网络干扰信息识别  

Disturbance information identification of ship communication network based on big data optimization neural network

作　　者：谭韶生 夏旭[3] TAN Shao-sheng;XIA Xu(Central South University,Changsha 410007,China;Hunan Industry Polytechnic,Changsha 410208,China;Hunan Vocational Institute of Safety Technology,Changsha 410151,China)

机构地区：[1]中南大学,湖南长沙410007 [2]湖南工业职业技术学院,湖南长沙410208 [3]湖南安全技术职业学院,湖南长沙410151

出　　处：《舰船科学技术》2022年第14期133-136,共4页Ship Science and Technology

基　　金：湖南省社会科学成果评审委员会课题资助项目(XSP20YBC417);湖南省职业院校教育教学改革研究资助项目(ZJGB2019021);湖南省教育厅科学研究资助项目(18C1333)。

摘　　要：构建船舶通信网络干扰信息特征识别矩阵,选取干扰信息瞬时特征指标,提取特征信息。采用单极Sigmoid函数神经网络构建船舶通信网络干扰信息识别模型,将所提取瞬时特征作为模型输入,采用权值直接确定法确定隐层与输出层间的权值,输出大数据资源调度下船舶通信网络干扰信息识别结果。研究结果显示该方法有较好的识别效果,能够提升通信信息的安全性与传输效率。Construct the characteristic recognition matrix of ship communication network interference information,select the instantaneous characteristic index of interference information,and extract characteristic information.The unipolar Sigmoid function neural network is used to construct the ship communication network interference information identification model,and the extracted instantaneous features are used as the input of the model.The weights between the hidden layer and the output layer are determined by the direct weight determination method,and the results of ship communication network interference information identification under the scheduling of big data resources are output.The results show that this method has a good recognition effect and can improve the security and transmission efficiency of communication information.

关 键 词：数据资源调度 通信网络 干扰信息识别 特征识别矩阵 神经网络 SIGMOID函数 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]