检索结果-内蒙古大学图书馆

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zengwei Huo Xu Yang Chao Xing Ying Zhou Peng Hou Jiaqi Lv Xin Geng Key Lab of Computer Network and Information Integration (Ministry of Education) Southeast University Nanjing China

Apparent age estimation has attracted more and more researchers since its potential applications in the real world. Apparent age estimation differs from chronological age estimation that in apparent age estimation each facial image is labelled by multiple individuals, the mean age is the ground truth age and the uncertainty is introduced by the standard deviation. In this paper, we propose a novel method called Deep Age Distribution Learning(DADL) to deal with such situation. According to the given mean age and the standard deviation, we generate a Gaussian age distribution for each facial image as the training target instead of the single age. DADL first detects the facial region in image and aligns the facial image. Then, it uses deep Convolutional Neural network(CNN) pre-trained based on the VGGFace and fine-tuned on the age dataset to extract the predicted age distribution. Finally it uses ensemble method to get the result. Our DADL method got a good performance in ChaLearn Looking at People 2016-Track 1: Age Estimation and ranked the 2nd place among 105 registered participants.

关键词： Estimation Training Standards Face Predictive models Uncertainty Correlation

来源：评论

学校读者我要写书评

暂无评论

Logistic Boosting Regression for Label Distribution Learning

Logistic Boosting Regression for Label Distribution Learning

引用

IEEE Conference on computer Vision and Pattern Recognition

作者： Chao Xing Xin Geng Hui Xue Key Lab of Computer Network and Information Integration (Ministry of Education) School of Computer Science and Engineering Southeast University

ISBN: (纸本)9781467388528

Label Distribution Learning (LDL) is a general learning framework which includes both single label and multi-label learning as its special cases. One of the main assumptions made in traditional LDL algorithms is the derivation of the parametric model as the maximum entropy model. While it is a reasonable assumption without additional information, there is no particular evidence supporting it in the problem of LDL. Alternatively, using a general LDL model family to approximate this parametric model can avoid the potential influence of the specific model. In order to learn this general model family, this paper uses a method called Logistic Boosting Regression (LogitBoost) which can be seen as an additive weighted function regression from the statistical viewpoint. For each step, we can fit individual weighted regression function (base learner) to realize the optimization gradually. The base learners are chosen as weighted regression tree and vector tree, which constitute two algorithms named LDLogitBoost and AOSO-LDLogitBoost in this paper. Experiments on facial expression recognition, crowd opinion prediction on movies and apparent age estimation show that LDLogitBoost and AOSO-LDLogitBoost can achieve better performance than traditional LDL algorithms as well as other LogitBoost algorithms.

关键词： Low-Density Lipoproteins Maximum entropy Regression (Psychology) Accelerated aging Cinema Boost Parametric statistics derivation extra message

来源：评论

学校读者我要写书评

暂无评论

Highly Compact Virtual Counters for Per-Flow Traffic Measurement through Register Sharing

Highly Compact Virtual Counters for Per-Flow Traffic Measure...

引用

IEEE Global Communications Conference

作者： You Zhou Yian Zhou Min Chen Qingjun Xiao Shigang Chen Department of Computer & Information Science & Engineering University of Florida Key Lab of Computer Network and Information Integration Southeast University Ministry of Education

ISBN: (纸本)9781509013296

Per-flow traffic measurement is a fundamental problem in the era of big network data, providing critical information for many practical applications including capacity planning, traffic engineering, data accounting, resource management, and scan/intrusion detection in modern computer networks. It is challenging to design highly compact data structures for approximate per-flow measurements. In this paper, we show that a highly compact virtual counter architecture can achieve fast processing speed (slightly more than 1 memory access per packet) and provide accurate measurement results under tight memory allocation. Extensive experiments based on real network trace data demonstrate its superior performance over the best existing work.

关键词： Radiation detectors Registers Estimation Memory management Time measurement Encoding

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Not So Cooperative Caching System

引用

China Communications 2015年第7期12卷 31-46页

作者： HU Xiaoyan GONG Jian CHENG Guang ZHANG Weiwei Ahmad Jakalan School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education

Not So Cooperative Caching(NSCC) considers a network comprised of selfish nodes; each is with caching capability and an objective of reducing its own access cost by fetching data from its local cache or from neighboring caches. These nodes would cooperate in caching and share cached content if and only if they each benefit. The challenges are to determine what objects to cache at each node and to implement the system in the context of information Centric networking(ICN). This work includes both a solution for the NSCC problem and a design and implementation of an NSCC system in Named Data networking(NDN), a large effort that exemplifies ICN. Our design applies NDN synchronization protocol to facilitate the information exchange among nodes, adopts group key encryption to control data access within the NSCC group, and offers an error checker to detect error events in the system. Our approach is validated by deploying the system we developed on Planet Lab.

关键词： named data networking content caching selfish caches synchronization group rekeying error checker game theory

来源：评论

学校读者我要写书评

暂无评论

network-Interconnection-Oriented: a Scalable Routing Service Model

Network-Interconnection-Oriented: a Scalable Routing Service...

引用

IEEE International Conference on High Performance Computing and Communications

作者： Yi Wan Jun Shen Tao Han Zu-Qin Ji MOE Key Laboratory of Computer Network and Information Integration School of Computer Science and Engineering Southeast University Nanjing 210096 China

ISBN: (纸本)9781509042982

Aimed at improving poor performance of current network routing service in the way of scalability, a new scalable routing service model (SRSM) is proposed based on the core of network interconnection and principles of modern packet switching. Three basic elements, which are addressing mode, routing table and routing algorithm, are abstracted to establish Meta model (SRSM) of routing service and realize typification of routing service models. Thus enhancing the abstraction level of routing service model can make it more flexible and scalable. Furthermore, the scalability of SRSM is resolving through contrasting routing service model instances of IP network, CDN (Content Delivery network) and NDN (Named Data networking). Finally, the related experiments of named routing service model instances and IP routing service model instances based on SRSM are provided to verify the feasibility and scalability of SRSM.

关键词： New network service model network routing service Scalability of service network interconnection network architecture

来源：评论

学校读者我要写书评

暂无评论

A Description Method for network Architecture

A Description Method for Network Architecture

引用

IEEE International Conference on High Performance Computing and Communications

作者： Jun Shen Zuqin Ji Wen Gao Yi Wan Key Laboratory of Computer Network & Information Integration of Ministry of Education School of Computer Science & Engineering Southeast University Nanjing 210096 China

ISBN: (纸本)9781509042982

Due to lack of desired model for traditional network architecture, services which are newly deployed can't be analyzed and verified quickly or efficiently. To address this problem, this paper puts forward a description method for network architectures which includes two parts: the modeling method and the formal model. First of all, we give a modeling method from the essence of the service interactions for network architecture;secondly, on the base of the modeling method, the formal model which is a description method for network architecture is provided;finally, we provide an application case with the description method. It is verified that the description method does well in the description of the network architectures and it can satisfy the need of analyzing the deploying of new services.

关键词： Architecture Modeling Formal Method network Architecture

来源：评论

学校读者我要写书评

暂无评论

Progress in Command and Control Server Finding Schemes of Botnet

Progress in Command and Control Server Finding Schemes of Bo...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Xiaojun Guo Guang Cheng Yifei Hu Mian Dai Southeast University Nanjing Jiangsu CN Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

ISBN: (纸本)9781509032068

Botnets have become one of the most serious threats to current Internet and future network security. Only finding and connecting command and control(C&C) servers can bots join and work for botnet, hence how to find C&C servers is critical to botnet management and running. In this paper, we preliminarily summarize and classify the currently typical C&C server finding schemes as three types: dedicated IP address, Internet infrastructure and third-party application/service from a new perspective. And we compare these three types on four aspects. It's seen that third type presents better than other two types on complexity, flexibility, traffic covertness and scale.

关键词： Servers IP networks Internet Complexity theory Malware Feature extraction Mobile communication

来源：评论

学校读者我要写书评

暂无评论

Temporal inactivation enhances robustness in an evolving system

arXiv

引用

arXiv 2018年

作者： Ogushi, Fumiko Kertész, János Kaski, Kimmo Shimada, Takashi Kyoto University Institute for Advanced Study Kyoto University Yoshida Ushinomiya-cho Sakyo-ku Kyoto606-8501 Japan Center for Materials research by Information Integration National Institute for Materials Science 1-2-1 Sengen Tsukuba Ibaraki305-0047 Japan Department of Network and Data Science Central European University Budapest1051 Hungary Institute of Physics Budapest University of Technology and Economics Budapest1111 Hungary Department of Computer Science Aalto University School of Science P.O. Box 15500 Espoo Finland Alan Turing Institute British Library 96 Euston Road LondonNW1 2DB United Kingdom Mathematics and Informatics Center University of Tokyo Department of Systems Innovation Graduate School of Engineering University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan

We study the robustness of an evolving system that is driven by successive inclusions of new elements or constituents with m random interactions to older ones. Each constitutive element in the model stays either active or is temporarily inactivated depending upon the influence of the other active elements. If the time spent by an element in the inactivated state reaches TW, it gets extinct. The phase diagram of this dynamic model as a function of m and TW is investigated by numerical and analytical methods and as a result both growing (robust) as well as non-growing (volatile) phases are identified. It is also found that larger time limit TW enhances the system's robustness against the inclusion of new elements, mainly due to the system's increased ability to reject "falling-together" type attacks. Our results suggest that the ability of an element to survive in an unfavorable situation for a while, either as a minority or in a dormant state, could improve the robustness of the entire system. Copyright © 2018, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Flow Scheduling Strategies for Minimizing Flow Completion Times in information-agnostic Data Center networks

Flow Scheduling Strategies for Minimizing Flow Completion Ti...

引用

作者： Peiyi Yu Chao Hu Bo Liu Changyou Xing College of Command Information Systems PLA University of Science and Technology Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education

Minimizing the flow completion time（FCT） is widely considered as an important optimization goal in designing data center networks. However, existing schemes either rely on the precondition that the size and deadline of each flow is known in advance, or require modifying the switch hardware, which is hard to implement in practice. In this paper, we present MCPF, a flexible and dynamic flow scheduling strategy to reduce the FCT. This strategy is based on the estimated probabilities of each flow to finish the transmission in a period time, and these flows which have higher completion probabilities are assigned with higher priority. Meanwhile, switches perform flow scheduling according to these priorities. We employ a queueing theory based mathematical model to analyze the average FCT of MCPF, and compare it with other two flow scheduling strategies. We also introduce the challenges and the solutions to implement MCPF in realistic networks. Finally, we evaluate the performance of MCPF in Mininet. The analysis and experimental results show that MCPF could effectively reduce the FCT.

关键词： completion time scheduling strategy data center networks information agnostic

来源：评论

学校读者我要写书评

暂无评论

引用

International Journal of Communications, network and System Sciences 2016年第5期9卷 168-176页

作者： Yongdong Hu Guoxin Wu School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China College of Information Science and Technology Nanjing Forestry University Nanjing China

Modelling WiMAX network traffic based on the self-similarity character is better than the traditional model based on the Poisson process, because the former can provide more accurate calculation for effective bandwidth. In this paper we propose a WiMAX network traffic model based on M/Pareto model to describe its self-similarity character. Then we deduce the average transmission rate and the variance coefficient for the FBM traffic model by the M/Pareto model, and get the Hurst parameter of the FBM traffic model by statistical analysis method. By the FBM traffic model we get a formula for calculating the effective bandwidth. Accordingly, we propose a modified self-similar call admission control algorithm (SS-CAC). SS-CAC can avoid measuring the parameter values of FBM traffic flow to do call admission control. Simulation results show that SS-CAC greatly reduces the call blocking rate and improves the bandwidth utilization.

关键词： WiMAX CAC Self-Similar Effective Bandwidth QoS

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：