检索结果-内蒙古大学图书馆

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Sandor Kocsardi Zoltan Nagy Arpad Csik Peter Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary Cellular Sensory and Wave Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Department of Mathematics and Computational Sciences Sźechenyi István University Gyor Hungary Faculty of Information Technology Pázmány Péter Catholic University Budapest Hungary

In the area of mechanical, aerospace, chemical and civil engineering the solution of partial differential equations (PDEs) has been one of the most important problems of mathematics for a long time. In this field, one of the most exciting areas is the simulation of fluid flow, which involves for example problems of air, sea and land vehicle motion. In this paper a CNN-UM based solver of 2D inviscid, adiabatic, compressible fluids will be presented. The governing equations are solved by using first- and second-order numerical methods. Unfortunately the necessity the coupled multi-layered computational structure with non-linear, space-variant templates does not make it possible to utilize the huge computing power of the analog CNN-UM chips. To improve the performance of our solution emulated digital CNN-UM implemented on FPGA has been used. Properties of the implemented specialized architecture is examined in terms of area, speed and accuracy.

关键词： Mathematical model Equations Computer architecture Microprocessors Field programmable gate arrays Computational modeling Magnetic cores

来源：评论

学校读者我要写书评

暂无评论

Experimental Result on Supersonic Flow Simulation on Emulated Digital CNN-UM

Experimental Result on Supersonic Flow Simulation on Emulate...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Sandor Kocsardi Zoltan Nagy Arpad Csik Peter Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary Cellular Sensory and Wave Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Department of Mathematics and Computational Sciences Széchenyi István University Gyor Hungary Faculty of Information Technology Pázmány Péter Catholic University Budapest Hungary

关键词： Mathematical model Fluids Computer architecture Computational modeling Equations Arrays Atmospheric modeling

来源：评论

学校读者我要写书评

暂无评论

Reducing the foreground aperture problem in mixture of Gaussians based motion detection

Reducing the foreground aperture problem in mixture of Gauss...

引用

14th International Conference on Systems Signals and image processing, IWSSIP 2007 and 6th EURASIP Conference Focused on Speech and image processing, Multimedia Communications and Services, EC-SIPMCS 2007

作者： Utasi, Á. Czúni, L. Department of Image Processing and Neurocomputing University of Pannonia Egyetem u. 10 Veszprém H-8200 Hungary

ISBN: (纸本)9789612480295

Separating the moving image parts from the static background is an important phase in video surveillance applications. The method based on Mixture of Gaussians (MOG) is an often used and robust approach to learn the background automatically and adaptively. Known MOG methods often suffer from the phenomena called the foreground aperture problem, when parts of large moving homogenous regions become part of the background instead of being selected as moving pixels. This article introduces a new method to eliminate this problem.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Strengthening Passwords by Keystroke Dynamics

Strengthening Passwords by Keystroke Dynamics

引用

IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications

作者： Attila Meszaros Zoltan Banko Laszlo Czuni Department of Image Processing and Neurocomputing University of Pannonia Hungary

This document presents the application of biometrics to strength conventional passwords. We show methods to analyze and compare users' keystroke patterns to be able to verify their identity when entering the password into a computer system. The problem's difficulty arises from the fact that only a very limited amount data is available and that new users can come and others may leave the system meantime. That is we are not allowed to re-evaluate all users' data during the application. We show test results based on 2400 records collected from 25 users of different typing ability.

关键词： Biometrics Authentication Fingerprint recognition Application software Humans Filtering Pattern matching Open systems Conferences Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Reducing the Foreground Aperture Problem in Mixture of Gaussians Based Motion Detection

Reducing the Foreground Aperture Problem in Mixture of Gauss...

引用

International Conference on Systems, Signals and image processing, IWSSIP

作者： A. Utasi L. Czuni Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary

Separating the moving image parts from the static background is an important phase in video surveillance applications. The method based on mixture of Gaussians (MOG) is an often used and robust approach to learn the background automatically and adaptively. Known MOG methods often suffer from the phenomena called the foreground aperture problem, when parts of large moving homogenous regions become part of the background instead of being selected as moving pixels. This article introduces a new method to eliminate this problem.

关键词： Apertures Gaussian processes Motion detection Gaussian distribution Pixel image processing Video surveillance Robustness Application software Process design

来源：评论

学校读者我要写书评

暂无评论

Emulated digital CNN solution for two dimensional compressible flows

Emulated digital CNN solution for two dimensional compressib...

引用

European Conference on Circuit Theory and Design, ECCTD

作者： Sandor Kocsardi Zoltan Nagy Peter Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In the area of mechanical, aerospace, chemical and civil engineering the solution of partial differential equations (PDEs) has been one of the most important problems of mathematics for a long time. Inside that one of the most exciting fields is the simulation of fluid flow, which involves for example problems of air, sea and land vehicle motion. In this paper a CNN-UM based solver of 2D inviscid, isothermal, compressible fluids will be presented. Unfortunately the necessity of the coupled multi-layered computational structure with non-linear, space-variant templates does not make it possible to utilize the huge computing power of the analog CNN-UM chips. To improve the performance of our solution an emulated digital CNN-UM has been used.

关键词： Cellular neural networks Analog computers Aerospace engineering Chemical engineering Civil engineering Partial differential equations Mathematics Computational modeling Fluid flow Land vehicles

来源：评论

学校读者我要写书评

暂无评论

CNN model on cell multiprocessor array

CNN model on cell multiprocessor array

引用

European Conference on Circuit Theory and Design, ECCTD

作者： Zoltan Nagy Laszlo Kek Zoltan Kincses Peter Szolgay Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Department Information Technology Pázmány Péter Catholic University Budapest Hungary Department Image Processing and Neurocomputing University of Pannonia Veszprem Hungary

Array computers can be useful in the solution of numerical spatio-temporal problems such as the state equation of the CNN or partial differential equations (PDE). IBM has recently introduced the cell broadband engine (Cell BE) Architecture which contains 8 identical vector processors in an array structure. In the paper the implementation of CNN simulation kernel on the Cell BE is described. The simulation kernel is optimized, according to the special requirements of the Cell BE and can use linear and also nonlinear (piecewise linear) templates. The area/speed/power tradeoffs of our solution and different hardware implementations are also compared.

关键词： Cellular neural networks Computer architecture Concurrent computing Partial differential equations Engines Kernel Hardware Signal processing Distributed computing Blades

来源：评论

学校读者我要写书评

暂无评论

Comment 1 on 'Evidence for response contraction bias in side-by-side matching tests' by SA Fotios and C Cheal

引用

Lighting Research and Technology 2007年第2期39卷 167-168页

作者： Houser, K.W. Schanda, J. Department of Architectural Engineering Durham School of Architectural Engineering and Construction University of Nebraska-Lincoln 1110 South 67th Street Omaha NE 68182-0681 United States Department of Image Processing and NeuroComputing University of Pannonia Egyetem u 10 Veszprém 8200 Hungary

来源：评论

学校读者我要写书评

暂无评论

Colour memory

Colour memory

引用

作者： Bodrogi, Peter Department of Image Processing and Neurocomputing Faculty of Information Technology Pannon University 10 Egyetem St. H-8200 Veszprém Hungary

ISBN: (纸本)0892082623

The aim of this study is to give an overview about the phenomenon of human colour memory: the related concepts, methodology, experimental findings and their interpretation. The concept of "cognitive colour" is defined. The characteristics of short-term and long-term colour memory are discussed, including memory colour shifts. Psycho-physical experimental methods to quantify colour memory are described and some typical memory colour results are briefly presented and interpreted.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Implementation of Nonlinear Template Runner Emulated Digital CNN-UM on FPGA

Implementation of Nonlinear Template Runner Emulated Digital...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Z. Kincses Z. Nagy P. Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprém Hungary Analogic and Neural Computing Laboratory Computer and Automation Institute of HAS Budapest Hungary

In the original CNN paradigm template values are defined as constants but several complex tasks can be efficiently solved by using nonlinear weights between the CNN cells. Unfortunately programmable nonlinear weights can not be implemented by using present day analog VLSI technology. In this paper a new emulated digital CNN-UM architecture will be presented which makes it possible to use zero and first order nonlinear templates during emulation. The new architecture is based on the Falcon emulated digital CNN-UM architecture and implemented on FPGAs. The computing precision of the architecture is configurable and the area/speed/accuracy tradeoffs are investigated

关键词： Field programmable gate arrays Cellular neural networks Gray-scale Very large scale integration Computer architecture image processing Detectors Emulation Hamming distance Application software

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：