检索结果-内蒙古大学图书馆

Euromicro Conference on Parallel, distributed and Network-Based Processing

作者： Daniel Strigl Klaus Kofler Stefan Podlipnig Distributed and Parallel Systems Group Institute of Computer Science University of Innsbruck Innsbruck Austria

In this paper we present the implementation of a framework for accelerating training and classification of arbitrary Convolutional Neural Networks (CNNs) on the GPU. CNNs are a derivative of standard Multilayer Perceptron (MLP) neural networks optimized for two-dimensional pattern recognition problems such as Optical Character Recognition (OCR) or face detection. We describe the basic parts of a CNN and demonstrate the performance and scalability improvement that can be achieved by shifting the computation-intensive tasks of a CNN to the GPU. Depending on the network topology training and classification on the GPU performs 2 to 24 times faster than on the CPU. Furthermore, the GPU version scales much better than the CPU implementation with respect to the network size.

关键词： Scalability Neural networks Cellular neural networks Optical character recognition software Acceleration Multilayer perceptrons Multi-layer neural network Pattern recognition Optical computing Optical fiber networks

来源：评论

学校读者我要写书评

暂无评论

Wide area distributed file systems-A scalability and performance survey

引用

Scalable Computing 2010年第3期11卷 305-326页

作者： Ponnavaikko, Kovendhan Dharanipragada, Janakiram Distributed and Object Systems Lab Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai India

Recent decades have witnessed an explosive growth in the amounts of digital data in various fields of arts, science and engineering. Such data is generally of interest to a large number of people spread over wide geographical areas. Over the years, several distributed File systems (DFS) have, to varying degrees, addressed this requirement of sharing large amounts of data, stored in the form of files, among several users and applications. Scalability and performance are two important measures that determine the suitability of a file system for the applications executing over them. We perform a detailed comparative analysis of popular distributed file systems in terms of these measures in our survey. © 2010 SCPE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Extending the Strand Space Method with Timestamps: Part II Application to Kerberos V

引用

Journal of Information Security 2010年第2期1卷 56-67页

作者： Yongjian Li Jun Pang Chinese Academy of Sciences Institute of Software Laboratory of Computer Science The State Key Laboratory of Information Security University of Oldenburg Department of Computer Science Safety-critical Embedded Systems

In this paper, we show how to use the novel extended strand space method to verify Kerberos V. First, we formally model novel semantical features in Kerberos V such as timestamps and protocol mixture in this new framework. Second, we apply unsolicited authentication test to prove its secrecy and authentication goals of Kerberos V. Our formalization and proof in this case study have been mechanized using Isabelle/HOL.

关键词： Strand Space Kerberos V Theorem Proving Verification Isabelle/HOL

来源：评论

学校读者我要写书评

暂无评论

Towards more realistic simulations of Ad-hoc Networks - Challenges and opportunities

Towards more realistic simulations of Ad-hoc Networks - Chal...

引用

International Symposium on Performance Evaluation of computer & Telecommunication systems SPECTS

作者： Steffen Moser Frank Slomka Institute of Embedded Systems/Real-Time Systems Faculty of Engineering and Computer Science Ulm University Ulm Germany

Vehicular Ad-hoc Networks are a very interesting self-organizing communication system that can make the traffic on our roads much safer. A lot of aspects of the behavior of these systems are studied using network simulation frameworks. While the upper communication layers of Vehicular Ad-hoc Networks are mainly simulated according to their specifications, in this paper we will highlight weak points in these simulations. They occur due the fact that the layers below the link layer are considered very rarely and are also almost neglected by the commonly used network simulation frameworks. This can potentially lead to inaccurate simulation results which can be fatal when studying safety relevant applications or application with real-time constraints. In this work in progress paper we are going to propose an approach to get this under control.

关键词： Computational modeling Physical layer Ad hoc networks Receivers Data models Protocols Channel models

来源：评论

学校读者我要写书评

暂无评论

Extending the Strand Space Method with Timestamps: Part I the Theory

引用

Journal of Information Security 2010年第2期1卷 45-55页

In this paper, we present two extensions of the strand space method to model Kerberos V. First, we include time and timestamps to model security protocols with timestamps: we relate a key to a crack time and combine it with timestamps in order to define a notion of recency. Therefore, we can check replay attacks in this new framework. Second, we extend the classic strand space theory to model protocol mixture. The main idea is to introduce a new relation to model the causal relation between one primary protocol session and one of its following secondary protocol session. Accordingly, we also extend the definition of unsolicited authentication test.

关键词： Strand Space Kerberos V Theorem Proving Verification Isabelle/HOL

来源：评论

学校读者我要写书评

暂无评论

Deferring CAPEX Investments in Multi-Layer Networks through IP Traffic-Dependent Expansion Stages

Deferring CAPEX Investments in Multi-Layer Networks through ...

引用

2010 ITG Symposium on Photonic Networks

作者： Michael Duelli Anke Endler Michael Menth University of Würzburg Institute of Computer Science Chair of Distributed Systems Am Hubland 97074 Germany

Network design is performed for a traffic load in the future. This traffic load is far greater than traffic loads observed at intermediate stages. In this paper, we propose to plan a multi-layer network for such a future traffic load, but instead of provisioning the full network equipment at once, we suggest to defer the deployment of expensive IP interfaces and other enabling equipment only to stages when they are really needed to carry traffic. We develop an algorithm that concentrates IP traffic at an intermediate stage on a subset of those IP interfaces that are required to carry the full load in the future. This reduces the set of used IP interfaces which need to be installed at intermediate stages, and CAPEX investments for the other equipment can be deferred to the future.

关键词： IP networks Topology Network topology Optical switches Multiprotocol label switching Optical fiber networks Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Automating the mean-field method for large dynamic gossip networks

Automating the mean-field method for large dynamic gossip ne...

引用

International Conference on Quantitative Evaluation of systems

作者： Bakhshi, Rena Endrullis, Jörg Endrullis, Stefan Fokkink, Wan Haverkort, Boudewijn Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Universität Leipzig Institut für Informatik Leipzig Germany Centre for Telematics and Information Technology University of Twente Enschede Netherlands Embedded Systems Institute Eindhoven Netherlands

ISBN: (纸本)9780769541884

We investigate an abstraction method, called meanfield method, for the performance evaluation of dynamic networks with pairwise communication between nodes. It allows us to evaluate systems with very large numbers of nodes, that is, systems of a size where traditional performance evaluation methods fall short. While the mean-field analysis is well-established in epidemics and for chemical reaction systems, it is rarely used for communication networks because a mean-field model tends to abstract away the underlying topology. To represent topological information, however, we extend the mean-field analysis with the concept of classes of states. At the abstraction level of classes we define the network topology by means of connectivity between nodes. This enables us to encode physical node positions and model dynamic networks by allowing nodes to change their class membership whenever they make a local state transition. Based on these extensions, we derive and implement algorithms for automating a mean-field based performance evaluation. © 2010 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Towards marine bloom trajectory prediction for AUV mission planning

Towards marine bloom trajectory prediction for AUV mission p...

引用

2010 IEEE International Conference on Robotics and Automation, ICRA 2010

作者： Das, Jnaneshwar Rajan, Kanna Frolov, Sergey Py, Frederic Ryan, John Caron, David A. Sukhatme, Gaurav S. Robotic Embedded Systems Laboratory Department of Computer Science University of Southern California United States Monterey Bay Aquarium Research Institute Moss Landing CA United States Dept. of Biological Sciences University of Southern California United States

ISBN: (纸本)9781424450381

This paper presents an oceanographic toolchain that can be used to generate multi-vehicle robotic surveys for large-scale dynamic features in the coastal ocean. Our science application targets Harmful Algal Blooms (HABs) which have significant societal impact to coastal communities yet are poorly understood ecologically. Bloom patches can be large spatially (in kms) and unpredictable in their extent. To understand their ecology, we need to be able to bring back water samples from the 'right' places and times for lab analysis. In doing so, we target hotspots representative of intense biogeochemical activity for such sampling. Our approach uses remote sensing data to detect such hotspots using ocean color as a proxy, and advectively projects these patches spatio-temporally using surface current data from HF Radar stations. Experiments with satellite and Radar data sets are promising for large, coherent blooms. We show how these predictions can be used to select an appropriate sampling trajectory for an AUV. ©2010 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Situational method engineering applied for the enactment of development processes - An agent based approach

Situational method engineering applied for the enactment of ...

引用

作者： Seemueller, Holger Voos, Holger Honke, Benjamin Bauer, Bernhard Mobile Robotics and Mechatronics Lab. University of Applied Sciences Ravensburg-Weingarten D-88241 Weingarten Germany Programming Distributed Systems Lab. Institute of Computer Science University of Augsburg D-86135 Augsburg Germany

ISBN: (纸本)9789898425065

Interdisciplinary product development is faced with the collaboration of diverse roles and a multitude of interrelated artifacts. Traditional and sequential process models cannot deal with the long-lasting and dynamic behavior of the development processes of today. Moreover, development processes have to be tailored to the needs of the projects, which are usually distributed today. Thus, keeping these projects on track from a methodology point of view is difficult. In order to deal with these challenges, this paper will present a novel method engineering and enactment approach. It combines the ideas of workflow technologies and product line engineering for method engineering as well as agent technology for the development process enactment.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Fruit Detection, Tracking, and 3D Reconstruction for Crop Mapping and Yield Estimation

Fruit Detection, Tracking, and 3D Reconstruction for Crop Ma...

引用

International Conference on Control, Automation, Robotics and Vision

作者： Jednipat Moonrinta Supawadee Chaivivatrakul Matthew N. Dailey Mongkol Ekpanyapong Computer Science and Imformation Management Asian Institute of Technology Pathumthani THAILAND Microelectronics and Embedded Systems Asian Institute of Technology Pathumthani THAILAND

ISBN: (纸本)9781424478149

Through automated agricultural inspection, farmers can potentially achieve better productivity and accurately predict yields and crop quality. A variety of sensors can be used for agricultural inspection, but the cheapest and most information-rich is the video camera. We collect data in the field from a monocular camera fixed to a mobile inspection platform. For purposes of pineapple crop mapping and yield prediction, we propose an image processing framework for in-field fruit detection, tracking, and 3D reconstruction. We perform a series of experiments on feature point extraction using Harris, SIFT, and SURF features, feature point description using SIFT and SURF descriptors, feature point classification using SVMs, fruit region tracking using blob tracking, and 3D reconstruction using structure from motion and robust ellipsoid estimation techniques. We find that SURF feature points and descriptors provide the best tradeoff between processing time and classification accuracy and that the method is sufficiently accurate for fruit region detection. Our preliminary results for fruit region tracking and 3D fruit reconstruction are promising. We plan further work towards development of a useful aid to help farmers manage their farms.

关键词： Object detection Object tracking Keypoint detection Keypoint descriptors Keypoint classification Image segmentation Structure from motion 3D reconstruction El-lipsoid estimation Pineapple Mobile field robot Agricultural automation

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：