智能计算机与应用
智能計算機與應用
지능계산궤여응용
Computer Study
2015年
2期
21-24
,共4页
流量识别%机器学习%早期特征%柔性神经树
流量識彆%機器學習%早期特徵%柔性神經樹
류량식별%궤기학습%조기특정%유성신경수
Traffic Identification%Machine Learning%Early Stage Features%Flexible Neural Trees
在互联网产生的早期阶段对其进行准确有效的识别,对于网络管理和网络安全来说都有着极其重要的意义。鉴于此,近年来越来越多的研究致力于仅仅基于流量早期的数个数据包,建立有效的机器学习模型对其进行识别。本文力图基于柔性神经树( FNT)构建有效的互联网流量早期识别模型。两个开放数据集和一个实验室采集的数据集用于实验研究,并将FNT与8种经典算法进行对比。实验结果表明,FNT在大多数情况下,其识别率和误报率指标优于其他算法,这说明FNT是一种有效的流量早期识别模型。
在互聯網產生的早期階段對其進行準確有效的識彆,對于網絡管理和網絡安全來說都有著極其重要的意義。鑒于此,近年來越來越多的研究緻力于僅僅基于流量早期的數箇數據包,建立有效的機器學習模型對其進行識彆。本文力圖基于柔性神經樹( FNT)構建有效的互聯網流量早期識彆模型。兩箇開放數據集和一箇實驗室採集的數據集用于實驗研究,併將FNT與8種經典算法進行對比。實驗結果錶明,FNT在大多數情況下,其識彆率和誤報率指標優于其他算法,這說明FNT是一種有效的流量早期識彆模型。
재호련망산생적조기계단대기진행준학유효적식별,대우망락관리화망락안전래설도유착겁기중요적의의。감우차,근년래월래월다적연구치력우부부기우류량조기적수개수거포,건립유효적궤기학습모형대기진행식별。본문력도기우유성신경수( FNT)구건유효적호련망류량조기식별모형。량개개방수거집화일개실험실채집적수거집용우실험연구,병장FNT여8충경전산법진행대비。실험결과표명,FNT재대다수정황하,기식별솔화오보솔지표우우기타산법,저설명FNT시일충유효적류량조기식별모형。
Identifying Internet traffic at their early stages accurately is very important for network management and security. Recent years,more and more studies have devoted to find effective machine learning models to identify traffics with the few packets at the early stage. This paper tries to build an effective early stage traffic identification model by applying flexible neural trees. Three network traffic data sets including two open data sets are used for the study. Eight classical classifiers are employed as the comparing methods in the identification experiments. FNT outperforms the other methods for most cases in the identification experiments,and it behaves very well for both of TPR and FPR. Thus,FNT is effective for early stage traffic identification.