本文選題：態(tài)勢感知　切入點(diǎn)：態(tài)勢提取　出處：《福州大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：本文以網(wǎng)絡(luò)安全態(tài)勢感知為應(yīng)用背景,主要從智能計(jì)算技術(shù)入手,綜合引用粒子群優(yōu)化算法(Particle Swarm Optimization, PSO)、Logistic回歸算法、鄰域粗糙集技術(shù)以及MapReduce分布式框架,建立智能化網(wǎng)絡(luò)安全態(tài)勢要素獲取模型及計(jì)算方法,以提升網(wǎng)絡(luò)安全態(tài)勢要素獲取的精確性,更好的輔助網(wǎng)絡(luò)管理員對網(wǎng)絡(luò)的安全態(tài)勢進(jìn)行詳細(xì)深入分析,有助于其做出更優(yōu)的主動防范決策。主要工作包括以下幾個(gè)部分：(1)提出一種采用改進(jìn)的粒子群優(yōu)化算法(Improved Particle Swarm Optimization,IPSO)和邏輯斯蒂回歸算法(Logistic Regression, LR)的態(tài)勢要素提取模型(LR-IPSO),從大量網(wǎng)絡(luò)安全狀態(tài)數(shù)據(jù)中獲取態(tài)勢要素。網(wǎng)絡(luò)安全態(tài)勢感知中態(tài)勢要素獲取的問題可轉(zhuǎn)化為海量數(shù)據(jù)的識別分類問題,針對此類問題,采用Logistic回歸模型進(jìn)行求解。在Logistic回歸模型中,利用改進(jìn)的粒子群優(yōu)化算法的內(nèi)在隱并行性和很好的全局尋優(yōu)能力對Logistic回歸模型的參數(shù)進(jìn)行估算,優(yōu)化Logistic回歸模型的學(xué)習(xí)能力,從而改善對大量網(wǎng)絡(luò)安全狀態(tài)數(shù)據(jù)態(tài)勢要素獲取的正確率。(2)引入特征提取技術(shù),提出一種基于能直接處理連續(xù)型數(shù)據(jù)的鄰域粗糙集模型和Logistic回歸算法的態(tài)勢要素獲取模型。特征選擇可用于處理海量數(shù)據(jù)。同時(shí),鄰域粗糙集模型能夠直接處理連續(xù)型數(shù)據(jù),規(guī)避了一些重要信息在大量的預(yù)處理和離散化過程中丟失,從而導(dǎo)致分類精度下降。鄰域粗糙集模型處理之后,保留了特征集合中的最優(yōu)子集。在此基礎(chǔ)上,利用LR-IPSO模型對大量網(wǎng)絡(luò)安全狀態(tài)數(shù)據(jù)的態(tài)勢要素進(jìn)行獲取,可以很好的提高態(tài)勢要素獲取能力。(3)為了進(jìn)一步提高Logistic回歸算法的綜合性能,我們綜合考慮了網(wǎng)絡(luò)狀態(tài)數(shù)據(jù)的海量性和單機(jī)的處理能力,在上述算法和模型的基礎(chǔ)上,采用MapReduce框架,提出了一種改進(jìn)的基于Logistic回歸和鄰域約簡模型的網(wǎng)絡(luò)安全態(tài)勢要素獲取模型,即：利用MapReduce框架對Logistic回歸算法進(jìn)行改寫,實(shí)現(xiàn)并行Logistic回歸算法,可以一次性處理所有日志數(shù)據(jù),避免了抽取一部分原始數(shù)據(jù)過程中丟失一些重要的信息,進(jìn)一步提高了網(wǎng)絡(luò)安全態(tài)勢要素獲取的精度,同時(shí)縮短了整個(gè)獲取過程所需的時(shí)間。
[Abstract]:In this paper, based on the application background of network security situation awareness, the particle swarm optimization algorithm (PSO) Swarm optimization, PSOO logistic regression algorithm, neighborhood rough set technology and MapReduce distributed framework are introduced. In order to improve the accuracy of the acquisition of network security situation elements and assist the network administrator to analyze the network security situation in detail, the intelligent network security situation element acquisition model and the calculation method are established to improve the accuracy of the network security situation element acquisition. The main work includes the following parts: 1) this paper proposes a situation factor extraction model using improved Particle Swarm optimization algorithm (IPSO) and logistic regression algorithm (LRR), which is based on improved particle swarm optimization (PSO) and logistic regression algorithm (LRR). LR-IPSO, which obtains the situation elements from a large number of network security state data. The problem of obtaining the situation elements in the network security situation awareness can be transformed into the recognition and classification problem of the massive data. In the Logistic regression model, the parameters of the Logistic regression model are estimated by using the inherent implicit parallelism and good global optimization ability of the improved particle swarm optimization algorithm. The learning ability of Logistic regression model is optimized to improve the correct rate of acquiring a large number of network security state data situation elements. This paper presents a situation element acquisition model based on neighborhood rough set model and Logistic regression algorithm, which can directly process continuous data. Feature selection can be used to deal with mass data. At the same time, neighborhood rough set model can deal with continuous data directly. Some important information is lost in the process of preprocessing and discretization, which leads to the decline of classification accuracy. After the processing of neighborhood rough set model, the optimal subset of feature set is retained. In order to further improve the comprehensive performance of Logistic regression algorithm, the LR-IPSO model is used to obtain the situation elements of a large number of network security state data, which can improve the acquisition ability of the situation elements. Considering the magnanimity of network state data and the processing ability of single computer, we adopt MapReduce framework on the basis of the above algorithms and models. An improved network security situation element acquisition model based on Logistic regression and neighborhood reduction model is proposed, that is, the Logistic regression algorithm is rewritten by using the MapReduce framework, and the parallel Logistic regression algorithm is realized, which can process all the log data at one time. It avoids the loss of some important information in the process of extracting some raw data, further improves the precision of obtaining network security situation elements, and shortens the time required for the whole acquisition process.
【學(xué)位授予單位】：福州大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP393.08

【相似文獻(xiàn)】

相關(guān)期刊論文 前6條

1 張艷莉;;基于Logistic回歸算法的企業(yè)顧客抱怨管理機(jī)制的構(gòu)建[J];科技通報(bào);2014年05期

2 龐天賜;;逐步logistic回歸的一種算法[J];中國衛(wèi)生統(tǒng)計(jì);1992年05期

3 耿金花;高齊圣;任敬喜;張嗣瀛;;基于Logistic回歸的社區(qū)滿意度模型[J];控制與決策;2007年11期

4 何欽成,黃亞明,何苗;神經(jīng)網(wǎng)絡(luò)與Logistic回歸在基礎(chǔ)研究成果綜合評價(jià)中的應(yīng)用比較[J];科技進(jìn)步與對策;2005年09期

5 楊俊英 ,楊海濤;應(yīng)用stata軟件實(shí)現(xiàn)logistic回歸的共線性診斷[J];中國衛(wèi)生統(tǒng)計(jì);2005年03期

6 ;[J];;年期

相關(guān)會議論文 前4條

1 李萬慶;閔捷;田野;蔣文翰;;隨機(jī)效應(yīng)logistic回歸在非獨(dú)立數(shù)據(jù)判別分析中的應(yīng)用[A];2011年中國衛(wèi)生統(tǒng)計(jì)學(xué)年會會議論文集[C];2011年

2 于長春;曾昭成;金鑫玲;宋明媚;孫志偉;卜翠萍;王靜;姜舒亞;施科;;Logistic回歸與ROC曲線在巨細(xì)胞病毒性肺炎臨床篩查中的應(yīng)用[A];2012年江浙滬兒科學(xué)術(shù)年會暨浙江省醫(yī)學(xué)會兒科學(xué)分會學(xué)術(shù)年會、兒內(nèi)科疾病診治新進(jìn)展國家級學(xué)習(xí)班論文匯編[C];2012年

3 鐘曉妮;周燕榮;王潤華;田考聰;賈慶良;汪洋;李勤;孫安龍;;主成分Logistic回歸在篩選乳腺癌監(jiān)測因素中的應(yīng)用[A];2000全國腫瘤學(xué)術(shù)大會論文集[C];2000年

4 夏慶梅;高巖;楊帆;步懷恩;王弘午;;天津市大學(xué)生痤瘡發(fā)病因素相關(guān)性及心理因素調(diào)查與分析[A];中華中醫(yī)藥學(xué)會中醫(yī)美容分會學(xué)術(shù)年會論文集[C];2009年

相關(guān)碩士學(xué)位論文 前8條

1 張印鵬;收入對我國老年人自評健康的影響[D];南京財(cái)經(jīng)大學(xué);2015年

2 李冬銀;基于Logistic回歸的網(wǎng)絡(luò)安全態(tài)勢要素獲取研究[D];福州大學(xué);2014年

3 徐剛;決策樹與Logistic回歸結(jié)合在新型農(nóng)村合作醫(yī)療制度實(shí)施效果研究中的應(yīng)用[D];南昌大學(xué);2007年

4 周菲;Logistic回歸多重共線性的診斷與改進(jìn)及其在醫(yī)學(xué)中的應(yīng)用[D];蘭州大學(xué);2011年

5 駱常好;懲罰logistic回歸與多因子降維法交互作用分析及其應(yīng)用[D];山西醫(yī)科大學(xué);2009年

6 孫曉煒;彩色多普勒超聲結(jié)合多變量Logistic回歸法對附件區(qū)惡性腫瘤的臨床預(yù)測價(jià)值[D];吉林大學(xué);2004年

7 鄒菊;Logistic回歸在乳腺癌綜合分析診斷中的應(yīng)用[D];南華大學(xué);2012年

8 王旭初;Logistic回歸和對數(shù)線性模型在高血壓現(xiàn)況研究中的應(yīng)用[D];浙江大學(xué);2008年

，

本文編號：1627122