检索结果-内蒙古大学图书馆

Improved functional imaging through network based parallel processing 2nd

2nd International Workshop on Communication, Architecture, and Applications for Network-Based parallel Computing (CANPC 98)

作者： Munz, F Stephan, T Maier, U Ludwig, T Bode, A Ziegler, S Nekolla, S Bartenstein, P Schwaiger, M Tech Univ Munich Klinikum Rechts Isar Nukl Med Klin & Poliklin D-8000 Munich Germany Tech Univ Munich Lehrstuhl Rechnertech & Rechnerorg D-8000 Munich Germany

ISBN: (纸本)3540641408

This paper deals with currently used algorithms for the reconstruction of functional images which run up to 60 hours or more on a single workstation and deal with hundreds of megabyte of data. A parallel implementation with high efficiency and almost linear speedup of a sophisticated iterative algorithm is given and its applicability to other reconstruction methods is shown. Whereas running this application on a high performance parallel computer is straightforward, there are more issues under production conditions as they are enforced by daily routine in a clinic. We adress the topic of fault tolerant parallelizing and batch queuing of programs which are typically written in a high level language like IDL or MATLAB and show how load balancing can preserve the ownership of workstations in a network of workstations (NOW) which is used for distributed computing during office hours.

关键词： functional imaging parallel image reconstruction load balancing batch queing network of workstations

来源：评论

学校读者我要写书评

暂无评论

Automatic feature selection for biological shape classification in ΣYNERGOS

Automatic feature selection for biological shape classificat...

引用

International Symposium on Computer Graphics, image processing, and Vision (SIBGRAPI 98)

作者： Bruno, OM Junior, RMC Consularo, LA Costa, LD Univ Sao Paulo Cybernet Vis Res Grp GII IFSC BR-13560970 Sao Carlos SP Brazil

ISBN: (纸本)0818692162

This work reports the development of a versatile framework allowing the characterization and analysis of computer vision techniques as well as their applications to biological shapes, with attention focused on neural cells. The proposed framework has been implemented within the Sigma ynergos system, a powerful imaging laboratory that includes, among other features, tools for performance assessment of computer vision techniques, image databases, real-time processing by using distributed systems and interface with the Internet. The motivations for the development of such a framework: (i) the importance of biological shape analysis;(ii) its potential as an effective tool for the systematic assessment of image processing and analysis techniques;and (iii) the possibility of conducting extensive characterizations of biological shapes. The paper describes an experiment to assess multiscale shape features for complexity characterization, which have been adopted for the classification of two types of ganglion neural cells (cat), namely alpha and beta. This experiment involves: (1) a training stage where the k-means clustering algorithm learns the prototypes of each class from the database;(2) the neurons in the database are classified;(3) the classification results are compared to the original classes;and (4) the number of misclassifications is determined. The genetic algorithm is used as a means of effectively investigating the N-dimensional spaces defined by the parameter configurations.

关键词： biological shape analysis multiscale methods neuromorphometry genetic algorithms image databases performance assessment

来源：评论

学校读者我要写书评

暂无评论

Method execution on a distributed image processing back-end

Method execution on a distributed image processing back-end

引用

Euromicro Workshop on parallel and distributed processing

作者： F. Niederl A. Goller Computer Graphics and Vision Graz University of Technology Graz Austria

The rapid grow of both, the size of remote sensing data and the number of users in this field requires systems which are easy to use, platform independent and mighty. Currently, many users are not able to process or even access data the way they would like to. Utilizing upcoming technologies like WWW, Java and CORBA, we propose a distributed system that connects users, data bases and method bases. Latter ones help users to find an appropriate sequence of methods for processing, and incorporating a broker they schedule execution onto fast remote processing units (backends). We discuss design considerations concerning the interaction of the back-end with other system components, and strategies for effective job distribution.

关键词： image processing Java Computer graphics Remote sensing Job design Web sites World Wide Web Internet distributed processing distributed computing

来源：评论

学校读者我要写书评

暂无评论

NOW based parallel reconstruction of functional images

NOW based parallel reconstruction of functional images

引用

International Symposium on parallel processing

作者： F. Munz T. Stephan U. Maier T. Ludwig A. Bode S. Ziegler S. Nekolla P. Bartenstein M. Schwaiger Nuklearmedizinische Klinik und Poliklinik des Klinikums rechts der Isar Technische Universität München Munchen Germany Lehrstuhl für Rechnertechnik und Rechnerorganisation Technische Universität München Munchen Germany

This paper deals with the parallel implementation of reconstruction algorithms for functional imaging on a network of workstations (NOW). Algorithms which provide the best image quality are not used in clinical routine, because they have a runtime of up to 60 hours with real clinical data sets of several hundred megabytes. After giving an overview of currently used image reconstruction algorithms, we describe a general parallel implementation of these algorithms with almost linear speedup and high efficiency which cuts down the runtime to a feasible limit. The high load which is caused by the parallel application conflicts with the predominantly interactive usage of clinical workstations, therefore we address load balancing with an application oriented, adaptive mechanism in order to preserve the ownership of workstations. Furthermore we explain how the integration of MATLAB and IDL based applications with a conventional distributed queuing system (DQS) can be achieved and why this significantly improves usage in clinical routine.

关键词： image reconstruction Positron emission tomography Workstations Runtime Detectors Scattering Iterative methods image quality Load management MATLAB

来源：评论

学校读者我要写书评

暂无评论

Architecture and the software environment of parallel computer Cenju-4

引用

NEC RESEARCH & DEVELOPMENT 1998年第4期39卷 385-390页

作者： Nakata, T Kanoh, Y Tatsukawa, K Yanagida, S Nishi, N Takayama, H NEC Corp Ltd C&C Media Res Labs Tokyo Japan NEC Corp Ltd Informatec Syst Tokyo Japan NEC Corp Ltd Comp Div Tokyo Japan

This paper describes the architecture and operating system, and gives an evaluation of NEC's new parallel computer Cenju-4 Major features of Cenju-4 are: a) parallel memory architecture which encompasses distributed shared memory and user-level inter-processor communication. b) Scalable system from 8 nodes to 1,024 nodes. Using the powerful RISC processor VR10000 (200 MHz) from MIPS ii Technologies, Inc., Cenju-4 system can be configured from 8 nodes to 1,024 nodes, flexibly extending the system as the demand arises. c) Utilization of a flexible micro-kernel operating system. Since the system adopts a micro-kernel based operating system (MACH), it can be configured into several software environments such as UNIX double dagger server systems and, single system image systems. The key components of the system are two 1 M gate arrays which implement memory control, inter processor communication control and network communication controls. The programming environment provided are de-facto standard libraries, high-level programming languages such as MPI (Message Passing Interface), PVM (parallel Virtual Machine) and HPF (High Performance Fortran). The operating system and the inter-processor communication libraries fully exploit the functionality of the hardware to realize an inter-processor communication latency of 4.5 mu s and the throughput of 169 MB/s at user program level.

关键词： high performance computing (HPC) parallel processing distributed memory architecture distributed shared memory (DSM)

来源：评论

学校读者我要写书评

暂无评论

An enhanced Co-scheduling method using reduced MS-state diagrams

An enhanced Co-scheduling method using reduced MS-state diag...

引用

International Symposium on parallel processing

作者： R. Govindarajan N.S.S. Narasimha Rao E.R. Altman G.R. Gao Computer Science & AutomationSupercomputer Edn. & Research Centre Indian Institute of Science Bangalore India Novell Software Development India Limited Bangalore India Yorktown Heights IBM Thomas J. Watson Research Center USA Electrical & Computer Engg. University of Delaware Newark USA

Instruction scheduling methods based on the construction of state diagrams (or automata) have been used for architectures involving deeply pipelined function units. However, the size of the state diagram is prohibitively large, resulting in high execution time and space requirement. We present a simple method for reducing the size of the state diagram by recognizing unique paths of a state diagram. Our experiments show that the number of paths in the reduced state diagram is significantly lower-by 1 to 3 orders of magnitude-compared to the number of paths in the original state diagram. Using the reduced MS-state diagrams, we develop an efficient software pipelining method. The proposed software pipelining algorithm produced efficient schedules and performed better than R.A. Huff's (1993) Slack Scheduling method, and the original Co-scheduling method, in terms of both the initiation interval (ii) and the time taken to construct the schedule.

关键词： Pipeline processing Hazards Processor scheduling Software maintenance Delay Supercomputers Computer science Automation Software algorithms Scheduling algorithm

来源：评论

学校读者我要写书评

暂无评论

New Chinese remainder theorems

New Chinese remainder theorems

引用

Asilomar Conference on Signals, Systems & Computers

作者： Yuke Wang Department of Electrical and Computer Engineering Concordia University Montreal QUE Canada

ISBN: (纸本)0780351487

The residue-to-binary conversion is the crucial step for residue arithmetic. The traditional methods are the Chinese remainder theorem (CRT) and the mixed radix conversion. This paper presents new Chinese remainder theorems I, ii, and Ill for the residue-to-binary conversion, with the following detailed results. (1) The big weights in the original CRT are reduced to a matrix of numbers less than the moduli P/sub i/. (2) The new Chinese remainder theorem I is a parallel algorithm in mixed radix format. The delay is reduced from O(n) to O(logn). (3) The new Chinese remainder theorem ii reduces the modulo operation from the size M to a size less than /spl radic/M. (4) The new Chinese remainder theorem ii can be easily extended to the new Chinese remainder theorem iiI for non-prime moduli sets. (5) A summary of a long list of references on residue-to-binary conversion is also presented.

关键词： Cathode ray tubes Delay image converters Digital arithmetic parallel algorithms Digital signal processing Fast Fourier transforms Digital filters Filtering image processing

来源：评论

学校读者我要写书评

暂无评论

Task division for parallel implementation of object identification system based on alternating hypothesize-verify-extend strategy

引用

Concurrency and Computation: Practice and Experience 1998年第9期9卷

作者： Weisi Lin Institute of Microelectronics 11 Science Park Road Singapore Science Park II Singapore 117685

parallelism has been perceived as the way for a computer vision system to achieve the required speedup in practice with existing algorithms and computing resources. It is known that methods of task division in such systems are algorithm-dependent. This paper investigates the parallel implementation of an object identification system based on an alternating hypothesize-verify-extend strategy with a transputer mesh network. This non-deterministic task is firstly divided on the hypothesis level and then within the processing for each hypothesis. It has been demonstrated that an object with modest complexity can be recognized and located from a cluttering image in a fraction of a second. © 1997 John Wiley & Sons, Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Software platform for parallel image processing and computer vision

Software platform for parallel image processing and computer...

引用

Conference on parallel and distributed methods for image processing

作者： Taniguchi, R Makiyama, Y Tsuruta, N Yonemoto, S Arita, D Kyushu Univ. (Japan)

ISBN: (纸本)0819425885

We describe a general purpose environment for the development of parallel image processing/computer vision algorithms: PRIME (parallel image Media processing Environment). ''General purpose'' here means that the environment is designed so as to be used on a variety of multi-processor systems ranging from tightly-coupled computers to loosely-coupled computers. The key point of the system is that it provides an architecture-independent programming environment for image processing and computer vision. We show the outline of PRIME, its implementation, and its preliminary performance evaluation.

关键词： parallel programming image processing computer vision architecture-independence MPI

来源：评论

学校读者我要写书评

暂无评论

parallel image processing using a Pentium based shared-memory multiprocessor-system

Parallel image processing using a Pentium based shared-memor...

引用

Conference on parallel and distributed methods for image processing

作者： Rothlubbers, C Orglmeister, R Technical Univ. of Berlin (Germany)

ISBN: (纸本)0819425885

This paper describes two different parallel computing approaches for image processing problems on a Pentium based multiprocessor-system. These multiprocessor computers are often used as network servers. We demonstrate the utilization of one of these machines, equipped with four Intel Pentium processors, far a parallel image processing task. A parallel computation of motion vector-fields based on correlation techniques is discussed to show the possible acceleration. The computational results show that a high efficiency can be reached, even a linear speedup is possible under certain conditions. Besides the mentioned correlation technique there are various image processing problems that can easily be evaluated in parallel. Although massively parallel systems and special purpose systems are much faster, off-line image processing can be accelerated by using these broadly available low-cost machines.

关键词： parallel computing multiprocessor-system image processing correlation technique motion vector-field

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：