基于改进模糊C均值算法的网络入侵检测研究  

Research on Fuzzy C-means Algorithm in Network Intrusion Detection of Big Data Platform

作　　者：郑美容[1] ZHENG Meirong(Fujian Chuanzheng Communications College,Fuzhou Fujian 350007,China)

机构地区：[1]福建船政交通职业学院,福建福州350007

出　　处：《信息与电脑》2021年第22期72-74,共3页Information & Computer

摘　　要：近年来,随着大数据技术的快速发展,大数据处理平台迅速兴起。大数据处理平台具有高吞吐量、网络协议多、端口多、数据量大、高并发等特征,借助传统入侵检测技术很难实时监控网络危险。为提高网络入侵检测的准确率和实时性,笔者提出一种改进模糊C均值算法,对分类后的数据集进行训练,使用Kafka技术处理采集的数据,通过Spark Streaming读取网络实时传输的数据流,并对检测到的入侵数据进行实时检测。In recent years,with the rapid development of big data technology,big data processing platform has sprung up rapidly.The big data processing platform has the characteristics of high throughput,many network protocols,many ports,large amount of data and high concurrency.It is difficult to monitor the network risk in real time with the help of traditional intrusion detection technology.In order to improve the accuracy and real-time of network intrusion detection,the author proposes an improved fuzzy C-means algorithm to train the classified data set,use Kafka technology to process the collected data,read the network real-time data stream through Spark Streaming,and detect the detected intrusion data in real time.

关 键 词：大数据处理平台 模糊C均值算法 Kafka Spark Streaming 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]