基于深度学习的交通标志检测

随着我国的汽车保有量速增长,自动驾驶的技术开始兴起,而交通标志检测是自动驾驶当中的一个重要的构成部分.交通标志的检测往往会受到光线变化、道路天气、摄像机角度等等因素的干扰,而且交通标志的数据集通常包含大量的小对象数据,这些问题已经成为交通标志检测领域中的难题.文章使用结合Darknet53的YOLOv3网络,增加对于小...     

高速低功耗深度报文检测方法

针对基于三态内容寻址存储器(TCAM,ternary content addressable memory)的深度报文检测(DPI,deep packet inspection)存在的高功耗问题,提出一种分级DPI方法BF-TCAM。第一级采用低功耗的并行布鲁姆过滤器(bloom fliter)排除无需检测的正常报文;第二级采用TCAM对真正需要检测的攻击报文和第一级的假阳性误判报文做进一步的检测。由于网络流量中大部分报文是正常报文,攻击报文在其中只占很少的部分,布鲁姆过滤器的假阴性(false negative)概率为0,可以保证不会产生漏检,假阳性概率很低,可以保证高速DPI检测的同时大大地降低功耗。     

红外热成像无损检测中缺陷深度检测新方法

文章在考虑缺陷大小对深度计算影响的基础上,通过对峰值时间与材料热特性参数、 缺陷深度以及缺陷大小(直径)的拟合,给出一个新的计算缺陷深度的公式,并通过实验验证了其可行性。     

基于深度学习目标检测算法的滑坡检测研究

针对目标检测算法在诸多图像识别领域应用效果突出,而在遥感图像滑坡检测中应用较少的现象,本文对同一少量低分辨率遥感数据集运用目前应用广泛的基于深度学习的目标检测算法Faster RCNN、YOLO、SSD进行遥感图像滑坡检测,并对实验结果进行了比较和分析,探讨三种目标检测算法的特点及其在遥感图像滑坡检测中适应的配置参数和应用范畴,以获得更有效的滑坡检测效果。     

基于深度学习的稠密人群检测

在针对稠密人群检测的试验中,传统来说,主要的方法有基于检测和基于回归两种方式。在人群密度较小样本量少的情况下,目标区域呈现出无遮挡,基于检测的方法效果较好。在人群密度较大样本量大的情况下,目标区域有目标遮挡,基于回归方法的效果较好。目前两种方法都得到了不同成程度的应用,然而,不论哪一种方式,要想精确检测出场景人数仍然是一个巨大的挑战。对于复杂场景下的稠密人群检测,本文系统性得总结出了几种最近的深度神经网络检测的方法,这些方法均是在稠密人群检测方面取得了较为理想的结果。     

离子束刻蚀深度检测技术的研究

将光学薄片用作敏感元件,利用激光干涉原理,将离子束刻蚀深度的信息转换为可测的激光干涉条纹的移动信息。这对微光学元件的离子束微细加工具有现实意义。对敏感元件与传感元件间的耦合进行了探讨,给出了振动误差的抑制措施。     

基于深度学习的实时车牌检测

车牌检测作为车牌识别的前序步骤,在交通管理等场景中占有举足轻重的地位。目前已经存在的车牌检测方法有的检测步骤过于繁琐,有的准确度较低、实时性较差。针对以上问题,文章提出了一种基于深度学习的车牌检测算法,该算法是一种流程简单的one-stage目标检测算法,同时还保证了较高的精度和较好的实时性,我们把这种算法称之为yolov3-mobilenetv2车牌检测算法。实验表明,该算法具有较高的研究和应用价值。     

基于深度学习的异常事件检测

面对复杂场景下异常事件检测的准确率偏低的情况,本文提出一种基于深度学习的异常事件检测方法,并将此方法扩展为异常事件分类方法.利用神经网络模型提取特征,将群体发散聚集事件,群体密集聚集事件,群体逃散事件和追赶事件这4种异常事件进行检测和分类.通过PKU-SVD-B测试集对训练出来的模型进行测试实验,并在UMN数据集上与几种方法做了对比实验,验证了本文提出的基于深度学习的异常事件检测算法,在适应多种不同场景的前提下,对多种异常事件检测的准确率很高,表明训练出来的模型对异常事件检测具有极强的泛化能力.     

深度包检测中的模式匹配算法研究

计算机网络技术飞速发展给人们生活带来便利的同时,也带来了严重的网络安全问题,由于各种网络攻击行为的不断出现,深度包检测逐渐成为网络安全的必然要求,作为影响深度包检测技术性能的模式匹配算法,成为研究的关键技术。对深度包检测中常见的一些模式匹配算法进行了分析和总结,并提出了进一步的研究方向。     

Method of data cleaning for network traffic classification

Network traffic classification aims at identifying the application types of network packets. It is important for Internet service providers （ISPs） to manage bandwidth resources and ensure the quality of service for different network applications However, most classification techniques using machine learning only focus on high flow accuracy and ignore byte accuracy. The classifier would obtain low classification performance for elephant flows as the imbalance between elephant flows and mice flows on Internet. The elephant flows, however, consume much more bandwidth than mice flows. When the classifier is deployed for traffic policing, the network management system cannot penalize elephant flows and avoid network congestion effectively. This article explores the factors related to low byte accuracy, and secondly, it presents a new traffic classification method to improve byte accuracy at the aid of data cleaning. Experiments are carried out on three groups of real-world traffic datasets, and the method is compared with existing work on the performance of improving byte accuracy. Experiment shows that byte accuracy increased by about 22.31% on average. The method outperforms the existing one in most cases.     

基于NetFlow流记录的高速应用流量分类方法

针对目前应用流量分类算法效率不高的现状,提出一种以NetFlow统计的IP流记录信息作为输入的高速应用流量分类(FATC,fast application-level traffic classification)算法。该算法采用基于简单相关系数的测度选择算法衡量测度变量间的相关关系,删除对分类无用或相互冗余的测度,而后使用基于Bayes判别法的分类算法将网络流量分至误判损失最小的应用类别中。理论分析及实验表明,FATC算法在具有超过95%的分类准确率基础上,极大降低了当前应用流量分类方法在训练和分类过程的时空复杂度,满足实时准确分类当前10Gbit/s主干信道网络流量的需求。     

Research of the traffic characteristics for the real time online traffic classification

Aiming at the hysteretic characteristics of classification problem existed in current internet traffic identification field,this paper investigates the traffic characteristic suitable for the on-line traffic classification,such as quality of service (QoS).By the theoretical analysis and the experimental observation,two characteristics (the ACK-Len ab and ACK-Len ba) were obtained.They are the data volume which first be sent by the communication parties continuously.For these two characteristics only depend on data’s total length of the first few packets on the flow,network traffic can be classified in the early time when the flow arrived.The experiment based on decision tree C4.5 algorithm,with above 97% accuracy.The result indicated that the characteristics proposed can commendably reflect behavior patterns of the network application,although they are simple.     

Early recognition of internet traffic based on signature inspection

The accurate and efficient classification of Internet traffic is the first and key step to accurate traffic management, network security and traffic analysis. The classic ways to identify flows is either inaccu-rate or inefficient, which are not suitable to be applied to real-time online classification. In this paper, we originally presented an early recognition method named Early Recognition Based on Deep Packet Inspec-tion (ERBDPI) based on deep packet inspection, after analyzing the distribution of payload signature be-tween packets of a flow in detail. The basic concept of ERBDPI is classifying flows based on the payload signature of their first some packets, so that we can identify traffic at the beginning of a flow connection. We compared the performance of ERBDPI with that of traditional sampling methods both synthetically and using real-world traffic traces. The result shows that ERBDPI can get a higher classification accuracy with a lower packet sampling rate, which makes it suitable to be applied to accurate real-time classification in high-speed links.     

面向轻载深包检测的应用负载特征自动挖掘(英文)

Automatic signature generation approaches have been widely applied in recent traffic classification.However,they are not suitable for LightWeight Deep Packet Inspection(LW_DPI) since their generated signatures are matched through a search of the entire application data.On the basis of LW_DPI schemes,we present two Hierarchical Clustering(HC) algorithms:HC_TCP and HC_UDP,which can generate byte signatures from TCP and UDP packet payloads respectively.In particular,HC_TCP and HC_ UDP can extract the positions of byte signatures in packet payloads.Further,in order to deal with the case in which byte signatures cannot be derived,we develop an algorithm for generating bit signatures.Compared with the LASER algorithm and Suffix Tree(ST)-based algorithm,the proposed algorithms are better in terms of both classification accuracy and speed.Moreover,the experimental results indicate that,as long as the application-protocol header exists,it is possible to automatically derive reliable and accurate signatures combined with their positions in packet payloads.     

A federated semi-supervised learning approach for network traffic classification

The classification of network traffic, which involves classifying and identifying the type of network traffic, is the most fundamental step to network service improvement and modern network management. Classic machine learning and deep learning methods have widely adopted in the field of network traffic classification. However, there are two major challenges in practice. One is the user privacy concern in cross-domain traffic data sharing for the purpose of training a global classification model, and the other is the difficulty to obtain large amount of labeled data for training. In this paper, we propose a novel approach using federated semi-supervised learning for network traffic classification, in which the federated server and clients from different domains work together to train a global classification model. Among them, unlabeled data are used on the client side, and labeled data are used on the server side. The experimental results derived from a public dataset show that the accuracy of the proposed approach can reach 97.81%, and the accuracy gap between the federated learning approach and the centralized training method is minimal.     

Studying cost-sensitive learning for multi-class imbalance in Internet traffic classification

Cost-sensitive learning has been applied to resolve the multi-class imbalance problem in Internet traffic classification and it has achieved considerable results.But the classification performance on the minority classes with a few bytes is still unhopeful because the existing research only focuses on the classes with a large amount of bytes.Therefore,the class-dependent misclassification cost is studied.Firstly,the flow rate based cost matrix(FCM) is investigated.Secondly,a new cost matrix named weighted cost matrix(WCM) is proposed,which calculates a reasonable weight for each cost of FCM by regarding the data imbalance degree and classification accuracy of each class.It is able to further improve the classification performance on the difficult minority class(the class with more flows but worse classification accuracy).Experimental results on twelve real traffic datasets show that FCM and WCM obtain more than 92% flow g-mean and 80% byte g-mean on average;on the test set collected one year later,WCM outperforms FCM in terms of stability.     

高速网络环境下的P2P流媒体业务分析和识别方法

The growing P2P streaming traffic brings a variety of problems and challenges to ISP networks and service providers.A P2P streaming traffic classification method based on sampling technology is presented in this paper.By analyzing traffic statistical features and network behavior of P2P streaming,a group of flow characteristics were found,which can make P2P streaming more recognizable among other applications.Attributes from Netflow and those proposed by us are compared in terms of classification accuracy,a...     

基于能耗的流量路由与NDN网路

Greening Internet is an important issue now, which studies the way to reduce the increasing energy expenditure. Our work focuses on the network infrastructure and considers its energy awareness in traffic routing. We formulate the model by traffic engineering to achieve link rate adaption, and also predict traffic matrices to preserve network stability. However, we realize that there is a tradeoff between network performance and energy efficiency, which is an obvious issue as Internet grows larger and larger. An essential cause is the huge traffic, and thus we try to find its solution from a novel architecture called Named Data Networking (NDN) which can flexibly cache content in edge routers and decrease the backbone traffic. We combine our methods with NDN, and finally improve both the network performance and the energy efficiency. Our work shows that it is effective, necessary and feasible to consider greening idea in the design of future Internet.     

基于SVM决策树的网络流量分类

提出一种用支持向量机(SVM)决策树来对网络流量进行分类的方法,利用SVM决策树在多类分类方面的优势,解决SVM在流量分类中存在的无法识别区域和训练时间较长的问题。对权威流量数据集进行了测试,实验结果表明,SVM决策树在流量分类中比普通的"一对一"和"一对多"SVM方法具有更短的训练时间和更好的分类性能,分类准确率可以达到98.8%。