基于关系型数据库的网络流数据预处理方法  

A PREPROCESS APPROACH OF NETWORK TRAFFIC BASED ON RELATIONAL DATABASE

作　　者：王盛 朱金奇[1] 花季伟[1] 乔增顺 Wang Sheng;Zhu Jinqi;Hua Jiwei;Qiao Zengshun(College of Computer and Information Engineering,Tianjin Normal University,Tianjin 300387,China)

机构地区：[1]天津师范大学计算机与信息工程学院,天津300387

出　　处：《计算机应用与软件》2021年第5期137-144,224,共9页Computer Applications and Software

基　　金：天津市自然科学基金项目(17JCYBJC16400,18JCYBJC85900,18JCQNJC70200)。

摘　　要：网络设备分类的前提是要对流量数据进行正确的预处理。现有预处理方法大多利用编程语言开发出小型工具类软件,应用范围较窄不具有推广性,无法满足一些特定的处理需求且源码不公开。对此,提出一种通用性的网络流量数据集构造方法,可以快速完成特征提取。并提出一种特征提取库的模块化方法,能够不断完善统计特征。通过在公开的pcap数据集上的实验,证明了该方法能有效解决pcap网络流统计特征的提取,具有很好的实用性和处理效率。The premise of network device classification is to preprocess traffic data properly.Most of the existing preprocessing methods use programming language to develop small tool software,which has narrow application scopes and not is not suitable for popularization.They cannot meet some specific processing requirements and the source code is not public.Thus,a general network traffic data set construction method is presented,which can quickly complete feature extraction.A modular method of feature extraction library is proposed,and it can continuously improve statistical features.The experiment on the published pcap dataset proves that the method can effectively solve the statistical feature extraction of pcap network flow and has good practicability and processing efficiency.

关 键 词：预处理 网络流分类 数据库 PCAP 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]