一种多分支网络的行人重识别方法研究

行人重识别(ReID)是视频监控中的一项重要任务,由于复杂的背景杂波,变化的照明条件以及无法控制的相机设置,使其成为一项具有挑战性的任务.提出一种结合全局特征和局部特征的深度学习网络作为解决方案.该深度学习网络具有各种粒度的区分性信息,是一种多分支深度网络体系结构.其中一个分支用于全局特征表示,负责整张图片的全局信息提...     

一种基于协议的互联网音视频识别方法

长文探讨了如何有效地对互联网音视频节目进行识别，并提出了一种基于协议的互联网音视频识别方法。     

一种基于卷积神经网络特征表征的语音情感识别方法

为提高智能语音情感识别系统的准确性，提出了一种基于卷积神经网络CNN(Convolution Neural Network)特征表征的语音情感识别模型，该卷积模型以 Lenet-5模型为基础，增加了一层卷积层和池化层，并将二维卷积核改为一维卷积核，将一维特征预处理后，输送进该模型中，对特征变换表征。最后利用SoftMax分类器实现情感分类，CASIA与 EMO-DB开数据库上的识别结果显示:与Lenet-5网络相比，所设计网络模型的准确率分别提升了1.3％与2％，与SoftMax分类器相比，准确率分别提升了3.8％与6.1％，仿真结果验证了网络模型的有效性。     

一种级联式神经网络框架的路标识别方法研究

为了提升无人驾驶汽车对于外界环境感知的能力, 本文提出了一种级联式神经网络框架对虚拟环境中的路标进行检测与分类。该框架将添加了 辅助结构的全卷积神经网络与改进后的经典LeNet-5网络进行 组合,在处理所提取出的路标区域边缘不平整以及产生杂项问题上使用传统的腐蚀膨胀开运 算图像处理算 子进行优化和解决,实现虚拟道路图像中雨雪等多种情况下的多类路标进行定位与识别。通 过与经典的不 变矩特征、ORB全局特征提取方法,以及YOLO,SSD人工智能方法对比试验表明,本文所提出 方法具备检测准确度高,运算速度快的优势。     

一种实时数字视频内容识别方法

提出了一种在数字电视和流媒体播出过程中进行实时视频内容识别的算法模型,讨论了该模型的几个性质,同时给出一种融合不同视觉特征模型的视频匹配方法,并针对数字电视TS流进行了算法测试,得到了准确实时的内容检测效果.     

一种基于交点特征的印刷体数字识别方法

为了进一步提高印刷体的数字识别准确率,提出了一种基于交点特征和径向基函数神经网络的数字识别方法。首先利用交点特征对数字进行特征提取,即提取某一数字的划水平线得到的交点数作为水平特征分量,提取划垂直线得到的交点数作为垂直特征分量,将水平特征向量与垂直特征向量组合成数字的交点特征向量;然后利用径向基函数神经网络学习不同模式类别中的学习样本,学习过程完成后,利用此网络对样本进行识别。实验结果表明,该数字识别方法在印刷体数字识别中正确率可达到100%,处理效果良好。     

网络流量识别方法研究

随着P2P和多媒体流量的发展,原有的流量识别方法越来越显现出其不足.为识别这些流量,需要识别效率更高的识别方法.文中提出了一种混合流量识别方法,此方法将特征识别和会话行为映射方法相结合,进行精确的流量识别.接着给出了这种识别过程的流程图,对识别过程进行了说明.对包的识别是基于优先级的特征识别,以提高识别效率.通过实验,选取四种应用Monkey3,eDonkey2000,MSN messenger,BitTorrent流量,将这些单个流量和混合流量的识别结果进行了比较.由实验结果可得出该方法对混合流量识别率比单个流量识别率高.     

基于主体行为的多方安全协议会话识别方法

针对分布在多个相关流中的多方安全协议会话问题,提出了多方安全协议会话的3个启发式的主体行为特征——邻接主机行为、主体角色行为以及主机消息行为,给出了主体行为特征检测原理,提出了多方安全协议会话识别方法。针对3个典型的多方安全协议,分别在3种会话运行场景下进行实验,结果表明该方法识别率在90%以上,误报率和漏报率在6%以下,能够有效地识别协议会话。     

一种新的雷达辐射源识别方法

提出一种用于雷达辐射源识别的新方法。根据小波包特征（WPT）和脉冲重复间隔（PRI）的特点,将八维WPT中的第六、七个分量（Wpt6、Wpt7）以及PRI的均值和方差（mpRI、σ^2PRI）四个特征参数作为雷达辐射源的识别依据,设计了径向基概率神经网络（RBPNN）分类器。通过计算机仿真验证了新方法的可行性,与常规方法相比,不仅提高了识别准确率,识别速度也有所提高。     

一种基于显著性深度特征的视觉场景识别方法

视觉场景识别是自主导航平台和定位模块中一项基本且极具挑战性的任务。现有的视觉场景识别方法通常对视觉外观变化表现敏感且计算开销大,文章提出了一种无需训练的基于显著性深度特征的视觉场景识别框架。首先,基于预训练的CNN模型对图像提取特征,然后运用聚类等无监督方法和特征剪枝筛选筛选出显著性区域,显著性区域的选取可以显著降低计...     

A Neural Network Method for Traffic Dispersion

１ＩｎｔｒｏｄｕｃｔｉｏｎＴｒａｆｉｃｄｉｓｐｅｒｓｉｏｎ［１］，ｗｈｉｃｈｍｅａｎｓｔｈｅｔｒａｆｉｃｉｓｄｉｓｔｒｉｂｕｔｅｄｏｖｅｒｍｕｌｔｉｐｌｅｐａｔｈｓａｎｄｔｒａｎｓｍｉｔｅｄｉｎｐａｒａｌｅｌ，ｉｓｕｓｅｄｔｏｉｍｐｒｏｖｅｔｈｅｎｅ...     

基于抽样分组长度分布的加密流量应用识别

基于确定性抽样数据分组序列的位置、方向、分组长度和连续性、有序性等流统计特征和典型的分组长度统计签名,并结合带数据分组位置、方向约束和半流关联动作的提升型DPI,提出了一种基于假设检验的加密流量应用识别统计决策模型,包括分组长度统计签名决策模型和DFI决策模型,并给出了相应的分组长度统计签名匹配算法以及基于DPI和DFI混合方法的加密流量应用识别算法。实验结果表明,该方法能够成功捕获加密应用在流坐标空间中独特的统计流量行为,并同时具有极高的加密识别精确率、召回率、总体准确率和极低的加密识别误报率、总体误报率。     

基于蚁群的对等网路由协议的研究

综合考虑结构化协议和非结构化协议的优点,提出了一种基于蚁群的对等网路由协议.分析对等网路由协议的研究现状,对结构化路由协议和非结构化路由协议进行了介绍.对等网路由协议进行了总体设计,给出了对等网路由协议的描述和总体结构图.提出了对等网路由协议算法的数据结构,并对等网路由协议算法进行了详细设计.利用仿真实验对等网路由协议进行了验证,实验结果表明该对等网路由协议是有效的.     

采用云计算技术的网络流量检测

为了实现对现网大数据网络流量的实时、有效检测,提出了一种基于云计算的网络流量检测方案。该方案充分利用Hadoop平台Map/Reduce编程模型在海量数据处理方面的优势,采用分层化的设计思想,克服了传统检测方案在海量数据应用环境中效率低下、可扩展性与安全性不足的缺点。重庆移动DPI平台应用表明,该方案较为有效,流量检测效果良好,在大数据处理时效率较普通分布式处理有明显提高。     

FlowAntEater: network traffic automatic signature generator

In the areas of traffic classification, the payload signature-based classification method–deep packet inspection (DPI) shows the highest performance in terms of preciseness, reliability and practicality. The usual way, however, obtaining signatures for DPI is analyzing network traffic payload and find signatures by hand, which means inefficient and a heavy burden for researchers. Therefore, the research on network traffic automatic signatures generation (NTASG), which helps administrators and researcher find network signatures, becomes important. In this paper, a software framework on NTASG is proposed which uses the K-means cluster algorithm to purity the traffic flow and contains a systematic signatures management algorithm, sig-tree. Also, the feasibility of our design choices was proved via experimental evaluation on the campus traffic trace.     

全面深化流量经营部署方案探讨

流量经营的概念已经提出好多年,运营商也进行了大量试点,打造流量经营平台,从规模到价值全面深化推广流量经营势在必行.分析了流量经营的典型业务场景,提出了深化流量经营部署方案建议,该方案主要由流量价值增长解决方案、系统架构和实施步骤构成,并给出了方案的关键技术和流程.工程应用与实践结果表明,该方案能够有效刺激运营商流量价值的增长.     

A Comparison of Performance between Macro-mobility Protocol and Micro-mobility Protocol

1　IntroductionAlthoughthemobileIP protocol[1～3] workswellinthemacromobilitysituation ,someproblemsoccurinthemicromobilitysituation .Therearetwomainconcerns.First,theregistrationdelaycon tributestothehandoffdelay .Thedelayissignifi cantwhenanMNisfarawayfromhomeandcausessignificantpacketdropanddrasticreductionincom municationthroughput.Second ,frequentlocationupdatesincurextensiveoverheadforlocationcachemanagementinrouteoptimizationthatrequiresac curatelocationinformationinordertotunnelIPda…     

ZBP: A Zone-Based Broadcasting Protocol for Wireless Sensor Networks

Wireless Sensor Networks (WSNs) have been widely used in motoring and collecting interests of environment information. Packet flooding or broadcasting is an essential function for establishing a communication path from sink node to a region of sensor nodes. However, flooding operation consumes power and bandwidth resources and raises the packet collision and contention problems, which reduce the success rate of packet transmissions and consume energy. This article proposes an efficient broadcasting protocol to reduce the number of sensor nodes that forward the query request, hence improves the packet delivery rate and saves bandwidth and power consumptions. Sensor node that received the query request will dynamically transfers the coordinate system according to the zone-ID of source node and determines whether it would forward the request or not in a distributed manner. Compared with the CBM and traditional flooding operation, experimental results show that the proposed zone-based broadcasting protocol decreases the bandwidth and power consumptions, reduces the packet collisions, and achieves high success rate of packet broadcasting.Chih-Yung Chang received the Ph.D. degree in Computer Science and Information Engineering from National Central University, Taiwan, in 1995. He joined the faculty of the Department of Computer and Information Science at Aletheia University, Taiwan, as an Assistant Professor in 1997. He was the Chair of the Department of Computer and Information Science, Aletheia University, from August 2000 to July 2002. He is currently an Associate Professor of Department of Computer Science and Information Engineering at Tamkang University, Taiwan. Dr. Chang served as an Associate Guest Editor of Journal of Internet Technology (JIT), Special Issue on “Wireless Ad Hoc and Sensor Networks” (2004) and a member of Editorial Board of Tamsui Oxford Journal of Mathematical Sciences (2001–2005). He was an Area Chair of IEEE AINA′2005, Vice Chair of IEEE WisCom2005, Track Chair (Learning Technology in Education Track) of IEEE ITRE′2005, Program Co-Chair of MNSA′2005, Workshop Co-Chair of INA′2005, MSEAT′2003, MSEAT′2004, Publication Chair of MSEAT′2005, and the Program Committee Member of ICPP′2004, USW′2005, WASN′2005, and the 11th Mobile Computing Workshop. Dr. Chang is a member of the IEEE Computer Society and IEICE society. His current research interests include wireless sensor networks, mobile learning, Bluetooth radio systems, Ad Hoc wireless networks, and mobile computing.Kuei-Ping Shih received the B.S. degree in Mathematics from Fu-Jen Catholic University, Taiwan, Republic of China, in June 1991 and the Ph.D. degree in Computer Science and Information Engineering from National Central University, Taiwan, Republic of China, in June 1998. After two years of military obligation, he joined the faculty of the Department of Computer Science and Information Engineering, Tamkang University, Taiwan, Republic of China, as an assistant professor in 2000. Dr. Shih served as a Program Area Chair in the IEEE International Conference on Advanced Information Networking and Applications (AINA), 2005, and as a Technical Track Chair in the IEEE International Conference on Information Technology: Research and Education (ITRE), 2005. Dr. Shih’s current research interests include wireless networks, sensor networks, mobile computing, and network protocols design.Dr. Shih is a member of the IEEE Computer and Communication Societies and Phi Tau Phi Scholastic Honor Society.Shih-Chieh Lee received the B.S. degree in Computer Science and Information Engineering from Tamkang University, Taiwan, in 1997. Since 2003 he has been a Ph.D. Students in Department of Computer Science and Information Engineering, Tamkang University. His research interests are wireless sensor networks, Ad Hoc wireless networks, and mobile/wireless computing.     

UDP协议中分包与重组方法研究

针对多用户使用UDP协议实现大数据量的可靠传输需求,采用事件与多线程技术,提出了一种简单实用的分包与重组方法。根据UDP协议通信的性能和特点,分析了传输数据的分包与重组原理,对分包与重组的程序设计进行了研究。利用在应用层对报文进行重新封装技术,讨论了传输数据合理分包的原则,以及接收方对一系列无序到达的报文正确重组的方法。     

A network processor‐based architecture for multi‐gigabit traffic analysis

The wide availability of cheap and effective commodity PC hardware has driven the development of versatile traffic monitoring software such as protocol analyzers, traffic characterizers and intrusion detection systems. Most of them are designed to run on general purpose architectures and are based on the well‐known libpcap API, which has rapidly become a de facto standard. Although many improvements have been applied to packet capturing software, it still suffers from several performance flaws, mainly due to the underlying hardware bottlenecks. To overcome these issues, this paper proposes a system architecture, which combines the high performance of a Network Processor card with the flexibility of software‐based solutions. It allows for removing most part of the hardware limitations exhibited by a purely PC‐based architecture, while preserving the full compliance to any software applications based on libpcap. In addition, the proposed system enables the use of monitoring applications at the wire speed, with the possibility of on‐the‐fly data processing. The system performance has been thoroughly assessed: the results show that it clearly outperforms the previous PC‐based solutions in terms of packet capturing power, while the timestamping accuracy is as good as that achieved by DAG cards. Copyright © 2009 John Wiley & Sons, Ltd.