本文選題：網(wǎng)絡(luò)流量分類 + 不平衡分類��； 參考：《東南大學(xué)》2015年碩士論文

【摘要】：網(wǎng)絡(luò)流量分類不僅可以幫助互聯(lián)網(wǎng)服務(wù)提供商提供服務(wù)質(zhì)量保障,而且可以對網(wǎng)絡(luò)進(jìn)行有效的監(jiān)督管理,確保網(wǎng)絡(luò)安全。隨著互聯(lián)網(wǎng)的迅猛發(fā)展,新興業(yè)務(wù)層出不窮,私有協(xié)議和加密應(yīng)用的廣泛使用,使得DPI分類方法的適用范圍越來越小。DFI方法主要通過流的統(tǒng)計(jì)特征來識別流量,無需解析應(yīng)用層負(fù)載,處理速度快,對加密報(bào)文和隱私協(xié)議仍然有效,并且無需額外的設(shè)備開銷。目前,基于DFI的機(jī)器學(xué)習(xí)流量分類方法具有良好的應(yīng)用前景。但是,該方法通常以獲得高的總體分類準(zhǔn)確率為優(yōu)化目標(biāo),而忽略網(wǎng)絡(luò)流量數(shù)據(jù)所具有的多類不平衡特性,使得分類性能往往偏向大類,而忽視小類。在網(wǎng)絡(luò)流量中,有些小類屬于重量級應(yīng)用,占有大量的字節(jié),其分類性能關(guān)乎網(wǎng)絡(luò)規(guī)劃及帶寬資源分配；有些小類應(yīng)用屬于命令流,實(shí)時(shí)通信流等,其分類性能關(guān)乎通信的可靠性及服務(wù)質(zhì)量。此外,由于網(wǎng)絡(luò)流量特征隨著時(shí)間和環(huán)境的變化而發(fā)生改變,現(xiàn)有的分類方法很難保持穩(wěn)定的分類性能,如何有效應(yīng)對網(wǎng)絡(luò)流量的概念漂移問題也是目前研究的熱點(diǎn)。本文的研究工作圍繞以上目標(biāo)展開,研究基于深度流檢測(Deep Flow Inspection, DFI)的流量分類方法。論文主要內(nèi)容如下：1.特征選擇算法對網(wǎng)絡(luò)流量分類的影響：在目前基于DFI檢測的網(wǎng)絡(luò)流量識別中,測度屬性的選取尤其重要。由于測度屬性中包含冗余與不相關(guān)特征,使得流量分類具有很高的計(jì)算復(fù)雜度與空間復(fù)雜度。而特征選擇算法能依據(jù)一定的評估策略選擇出更能區(qū)分流量類別的屬性,通過降低屬性的維度來降低計(jì)算復(fù)雜度和空間復(fù)雜度,并提高分類和識別的準(zhǔn)確率。本文提出基于選擇性集成和改進(jìn)序列向前搜索的混合特征選擇算法,并且與傳統(tǒng)的基于相關(guān)性的FCBF,信息增益InfoGain, GainRatio,基于統(tǒng)計(jì)的Chi-square以及基于一致性Consisitency進(jìn)行比較,實(shí)驗(yàn)結(jié)果表明該特征選擇算法可以更好的區(qū)分流行為特征屬性和類屬性之間的相關(guān)性。2.基于代價(jià)敏感的算法模型：由于網(wǎng)絡(luò)流數(shù)據(jù)存在類不平衡特性,且目前的流分類算法多偏向大類,忽視小類。為了提高小類的分類性能,本文提出了一種基于重采樣的代價(jià)敏感模型。首先對不平衡網(wǎng)絡(luò)流量數(shù)據(jù)進(jìn)行SMOTE重采樣,改善大類與小類的不平衡特性,然后采用AdaCost算法分類流量數(shù)據(jù),其中AdaCost中代價(jià)矩陣采用基于權(quán)重的錯(cuò)分代價(jià)矩陣。并且與傳統(tǒng)的C4.5分類算法進(jìn)行比較,實(shí)驗(yàn)結(jié)果表明該算法模型可以提高小類的流準(zhǔn)確率和字節(jié)準(zhǔn)確率。3.基于代價(jià)敏感的多分類器的算法模型：由于網(wǎng)絡(luò)流量特征隨著時(shí)間和環(huán)境的變化而發(fā)生改變,機(jī)器學(xué)習(xí)分類方法很難保持穩(wěn)定的分類性能。為了提高分類器的自適應(yīng)能力,本文提出一種基于精度權(quán)重的流量分類方法,實(shí)驗(yàn)結(jié)果表明該算法在處理流量的概念漂移問題上表現(xiàn)出較好的分類性能和泛化能力。為了進(jìn)一步提高動態(tài)環(huán)境下小類的分類性能,本文在基于精度權(quán)重的集成學(xué)習(xí)分類方法的基礎(chǔ)上提出了一種基于代價(jià)敏感的集成學(xué)習(xí)模型,模型由兩部分構(gòu)成：第一部分是混合特征選擇,獲取穩(wěn)定的最優(yōu)特征子集,第二部分將基于精度權(quán)重的分類方法與基于權(quán)重的AdaCost方法相結(jié)合。實(shí)驗(yàn)結(jié)果表明該方法能夠有效提高概念漂移環(huán)境下小類的流準(zhǔn)確率與字節(jié)準(zhǔn)確率。
[Abstract]:Network traffic classification can not only help the Internet service providers to provide quality assurance, but also can effectively supervise and manage the network to ensure network security. With the rapid development of the Internet, the emerging services emerge in endlessly, and the wide use of private protocols and encryption applications makes the application of the DPI classification method more and more applicable. The small.DFI method is mainly used to identify traffic through the statistical features of the stream. It does not need to parse the load of the application layer and is fast in processing speed. It is still valid for encrypted messages and privacy protocols, and without additional equipment overhead. At present, the machine learning flow classification method based on DFI has a good application prospect. However, this method usually obtains high total. The classification accuracy is the goal of optimization, while ignoring the multi class unbalance characteristic of network traffic data, the classification performance tends to be biased to the large class, but neglects the small class. In the network traffic, some small classes belong to heavy applications and occupy a large number of bytes, and their classification performance is related to network planning and bandwidth allocation; some small classes are applied. It belongs to the command stream, the real-time communication flow and so on. Its classification performance is related to the reliability and the quality of the service. In addition, the current classification method is difficult to maintain a stable classification performance because of the change of network traffic characteristics along with the change of time and environment. How to deal with the concept drift problem of network traffic is also the hot research. The research work around the above aims to study the flow classification method based on Deep Flow Inspection (DFI). The main contents of this paper are as follows: 1. the influence of the feature selection algorithm on network traffic classification: in the current network traffic recognition based on DFI detection, the selection of measure attributes is especially important. The degree attribute contains redundancy and unrelated features, making the traffic classification with high computational complexity and space complexity. The feature selection algorithm can select the attributes that can distinguish the flow category more according to a certain evaluation strategy, and reduce the complexity and complexity by reducing the dimension of the attribute, and improve the classification and recognition. In this paper, a hybrid feature selection algorithm based on selective integration and improved sequence forward search is proposed, and compared with the traditional correlation based FCBF, information gain InfoGain, GainRatio, statistical Chi-square and consistency based Consisitency, the experimental results show that the feature selection algorithm can be better. .2. based on the cost sensitive algorithm model that distinguishes the correlation between the characteristic attributes and the class attributes: because the network flow data has the class imbalances, and the current flow classification algorithms tend to tend to large classes and ignore the small classes. In order to improve the classification performance of the small classes, a cost sensitive model based on resampling is proposed in this paper. The unbalanced network traffic data is resampling with SMOTE to improve the unbalance characteristics of large class and small class. Then AdaCost algorithm is used to classify traffic data, and the cost matrix in AdaCost is based on the weight based misdivision cost matrix. And compared with the traditional C4.5 classification algorithm, the experimental results show that the algorithm can improve the small class. Flow accuracy and byte accuracy.3. based on the cost sensitive multi classifier algorithm model: because the network traffic characteristics change with time and environment changes, the machine learning classification method is difficult to maintain the stable classification performance. In order to improve the adaptive energy of the classifier, a flow based on the precision weight is proposed in this paper. The experimental results show that the algorithm shows better classification performance and generalization ability to deal with the concept drift of traffic. In order to further improve the classification performance of small classes in dynamic environment, this paper proposes a cost sensitive integration based on the integrated learning classification method based on precision weight. The model is composed of two parts: the first part is the mixed feature selection to obtain the stable optimal feature subset. The second part combines the classification method based on the precision weight and the weight based AdaCost method. The experimental results show that the method can effectively improve the flow accuracy and byte accuracy of the small classes in the conceptual drift environment.

【學(xué)位授予單位】：東南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TP393.06

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 卜華龍;夏靜;韓俊波;;特征選擇算法綜述及進(jìn)展研究[J];巢湖學(xué)院學(xué)報(bào);2008年06期

2 王博;賈焰;田李;;基于類標(biāo)號擴(kuò)展的半監(jiān)督特征選擇算法[J];計(jì)算機(jī)科學(xué);2009年10期

3 陳紅;郭躬德;;一種新的雙重融合的半監(jiān)督特征選擇算法[J];小型微型計(jì)算機(jī)系統(tǒng);2010年08期

4 張曉光;孫正;徐桂云;阮殿旭;;一種類內(nèi)方差與相關(guān)度結(jié)合的特征選擇算法[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2011年03期

5 陳建華;王治和;蔣蕓;許虎寅;樊東輝;;一種改進(jìn)的文本分類特征選擇算法[J];微電子學(xué)與計(jì)算機(jī);2011年12期

6 郭磊;王亞弟;陳庶樵;朱珂;伊鵬;;一種改進(jìn)的動態(tài)流特征選擇算法[J];計(jì)算機(jī)工程與應(yīng)用;2012年18期

7 代琨;于宏毅;馬學(xué)剛;李青;;基于支持向量機(jī)的特征選擇算法綜述[J];信息工程大學(xué)學(xué)報(bào);2014年01期

8 毛勇;周曉波;夏錚;尹征;孫優(yōu)賢;;特征選擇算法研究綜述[J];模式識別與人工智能;2007年02期

9 任雙橋;傅耀文;黎湘;莊釗文;;基于分類間隔的特征選擇算法[J];軟件學(xué)報(bào);2008年04期

10 李勇明;張素娟;曾孝平;覃劍;韓亮;;輪詢式多準(zhǔn)則特征選擇算法的研究[J];系統(tǒng)仿真學(xué)報(bào);2009年07期

相關(guān)會議論文 前5條

1 甄超;鄭濤;許潔萍;;音樂流派分類中特征選擇算法研究[A];第18屆全國多媒體學(xué)術(shù)會議（NCMT2009）、第5屆全國人機(jī)交互學(xué)術(shù)會議（CHCI2009）、第5屆全國普適計(jì)算學(xué)術(shù)會議（PCC2009）論文集[C];2009年

2 張仰森;曹元大;;最大熵建模方法中一種改進(jìn)的特征選擇算法[A];NCIRCS2004第一屆全國信息檢索與內(nèi)容安全學(xué)術(shù)會議論文集[C];2004年

3 張錚;胡社教;江萍;;基于EP模式的特征選擇算法[A];2011中國儀器儀表與測控技術(shù)大會論文集[C];2011年

4 周炎濤;唐劍波;王家琴;;基于信息熵的改進(jìn)TFIDF特征選擇算法[A];第二十六屆中國控制會議論文集[C];2007年

5 李文法;段m#毅;劉悅;孫春來;;一種面向流分類的特征選擇算法[A];第四屆全國信息檢索與內(nèi)容安全學(xué)術(shù)會議論文集（上）[C];2008年

相關(guān)博士學(xué)位論文 前6條

1 王劍橋;基于局部特性的毫米波距離像識別方法研究[D];南京理工大學(xué);2014年

2 李云;特征選擇算法及其在基于內(nèi)容圖像檢索中的應(yīng)用研究[D];重慶大學(xué);2005年

3 劉華文;基于信息熵的特征選擇算法研究[D];吉林大學(xué);2010年

4 張靖;面向高維小樣本數(shù)據(jù)的分類特征選擇算法研究[D];合肥工業(yè)大學(xué);2014年

5 潘巍巍;故障嚴(yán)重程度識別的有序分類特征分析方法[D];哈爾濱工業(yè)大學(xué);2013年

6 張嘉偉;心電圖形態(tài)特征的識別及其在分類中的作用研究[D];華東師范大學(xué);2011年

相關(guān)碩士學(xué)位論文 前10條

1 徐嬌;基于Hadoop的文本特征選擇算法的研究[D];蘭州大學(xué);2015年

2 朱艷玲;基于聚類的多層特征選擇算法的研究與應(yīng)用[D];鄭州輕工業(yè)學(xué)院;2015年

3 周p，

本文編號：1845973