入侵檢測(cè)異常數(shù)據(jù)的分類與可視化研究
[Abstract]:With the development of network technology, the security problem becomes more and more prominent. In the face of network security problems, the traditional intrusion detection technology has many defects such as low detection rate and low detection efficiency in multi-classification of abnormal data. In order to solve the problem of low detection rate, this paper improves the binary tree support vector machine algorithm based on clustering algorithm, and the detection rate is improved. In order to solve the problem of low detection efficiency, this paper improves the detection efficiency by using MapReduce technology on the basis of the improved algorithm. In this paper, an intrusion detection anomaly data classification and visualization system based on improved algorithm is designed and implemented. The system consists of four modules: intrusion detection data acquisition module, intrusion detection anomaly data statistical analysis module, intrusion detection data visualization module and system management module. The intrusion detection data acquisition module is mainly responsible for the acquisition of intrusion data, and the intrusion detection anomaly data statistical analysis module mainly uses the improved multi-classification algorithm to classify the abnormal data. Intrusion detection data visualization module is mainly used for data collation, query, statistics and graphic display. The system management module is mainly used for the configuration of alarm rules, alarm configuration and user authority management. The purpose of this paper is to collect the intrusion detection data together, through the automatic processing of the statistical analysis module, and finally to use Highcharts technology to display the data on the visual interface, which provides the judgment basis for preventing and reducing the network intrusion behavior.
【學(xué)位授予單位】:華北電力大學(xué)(北京)
【學(xué)位級(jí)別】:碩士
【學(xué)位授予年份】:2017
【分類號(hào)】:TP393.08
【參考文獻(xiàn)】
中國博士學(xué)位論文全文數(shù)據(jù)庫 前5條
1 李紅;流程挖掘算法研究[D];云南大學(xué);2015年
2 劉積芬;網(wǎng)絡(luò)入侵檢測(cè)關(guān)鍵技術(shù)研究[D];東華大學(xué);2013年
3 袁嵩;樹突狀細(xì)胞算法研究及在監(jiān)控系統(tǒng)入侵檢測(cè)中的應(yīng)用[D];武漢大學(xué);2013年
4 李雁妮;深網(wǎng)數(shù)據(jù)集成與挖掘關(guān)鍵問題的建模及算法研究[D];西安電子科技大學(xué);2013年
5 鄔書躍;基于支持向量機(jī)和貝葉斯分析技術(shù)的入侵檢測(cè)方法研究[D];中南大學(xué);2012年
中國碩士學(xué)位論文全文數(shù)據(jù)庫 前10條
1 王偉;企業(yè)移動(dòng)辦公綜合應(yīng)用系統(tǒng)設(shè)計(jì)[D];長春工業(yè)大學(xué);2016年
2 王照清;大數(shù)據(jù)環(huán)境下數(shù)據(jù)查詢優(yōu)化技術(shù)應(yīng)用研究[D];北方工業(yè)大學(xué);2016年
3 張馨允;基于Spark的Web文本挖掘系統(tǒng)的研究與實(shí)現(xiàn)[D];吉林大學(xué);2016年
4 程文露;中國互聯(lián)網(wǎng)企業(yè)空間分布的數(shù)據(jù)挖掘—一種大數(shù)據(jù)分析模式[D];華東師范大學(xué);2016年
5 王姍;基于Hadoop平臺(tái)的一種Apriori算法改進(jìn)方法[D];吉林大學(xué);2016年
6 林川;基于SNMP/IPMI的數(shù)據(jù)采集框架的設(shè)計(jì)與實(shí)現(xiàn)[D];中國科學(xué)院研究生院(沈陽計(jì)算技術(shù)研究所);2016年
7 吳恩英;基于支持向量機(jī)的高校課堂教學(xué)質(zhì)量評(píng)價(jià)研究[D];重慶師范大學(xué);2016年
8 邢穎;銀行管理系統(tǒng)的研究與實(shí)現(xiàn)[D];遼寧科技大學(xué);2016年
9 張之宣;云計(jì)算環(huán)境下實(shí)時(shí)日志分析系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];浙江大學(xué);2016年
10 張彬;基于Spark大數(shù)據(jù)平臺(tái)日志審計(jì)系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];山東大學(xué);2015年
,本文編號(hào):2341130
本文鏈接:http://sikaile.net/guanlilunwen/ydhl/2341130.html