检索结果-内蒙古大学图书馆

Multiple-Goal Objective Functions For Optimization of Task Assignment in Complex computer systems

IFAC Proceedings Volumes 1994年第6期27卷 55-60页

作者： T.J. Marlowe A.D. Stoyenko P.A. Laplante R.S. Daita C.C. Amaro C.M. Nguyen S.L. Howell Department of Mathematics and Computer Science Seton Hall University South Orange NJ 07079 USA Real- Time Computing Laboratory New Jersey Institute of Technology Newark NJ 07102 USA Real-Time Computing Laboratory NJIT Newark NJ 07102 USA Department of Mathematics and Computer Science Fairleigh Dickinson University Madison NJ 07940 USA Naval Surface Warfare Center Dahlgren Division Code B40 10901 New Hampshire Ave. Silver Spring MD 20903-5640 USA

Complex systems are large applications, typically running on distributed, heterogeneous networks, driven by a number of distinct constraints and desiderata on goals such as performance, real-time behavior, and fault tolerance. These requirements frequently conflict, and satisfaction of these design objectives interacts strongly with assignment of system tasks to processors. The NSWC design framework DESTINATION provides an assignment module which can be used to optimize the system, as measured by the value of a weighted combination of objective cost functions. For even modest-sized systems and networks, assignment space is too large to search exhaustively. We have implemented algorithms which generate heuristically good assignments. However, compile-time evaluation of many interesting design factors, even those clearly related to assignment, is impossible without some estimate of the schedule. We therefore provide approaches for determining a reasonable “pseudo-schedule” for a given system, network, and assignment, and use this to simulate execution in evaluating cost functions.

关键词： Complex real-time systems allocation scheduling heuristics assignment

来源：评论

学校读者我要写书评

暂无评论

Deblurring of images by cellular neural networks with applications to microscopy

Deblurring of images by cellular neural networks with applic...

引用

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

作者： J.P. Miller T. Roska T. Sziranyi K.R. Crounse L.O. Chua L. Nemes Division Neurobiology Department of Molecular & Cell Biology University of California Berkeley CA USA Analogic and Neural Computing Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Electronics Research Laboratory Department of Electrical Engineering and Computer Science University of California Berkeley CA USA

In this paper it is shown how the Cellular Neural Network (CNN) can be used to perform image and volume deblurring, with particular emphases on applications to microscopy. We discuss the basic linear theory of the CNN including issues of stability and template size. It is observed that a CNN with a small template can be used to implement an Infinite Impulse Response filter. It is then shown how general deblurring problems can be addressed with a CNN when the blurring operator is known. The proposed application is to solve the basic 3-D confocal image reconstruction task about the form of the blurring operator, confocal behavior in microscope images can be obtained with only 3-5 acquired image planes. In addition, the stored program capability of the CNN Universal Machine would provide integration of several image processing and detection tasks in the same architecture.< >

关键词： Cellular neural networks Microscopy Application software Biology computing computer networks Laboratories Stability Optical devices Optical distortion Image resolution

来源：评论

学校读者我要写书评

暂无评论

Transparent load sharing in distributed systems: decentralized design alternatives based on the Condor package

Transparent load sharing in distributed systems: decentraliz...

引用

Reliable Distributed systems

作者： Chao-Ju Hou K.G. Shin T.K. Tsukada Computer Engineering Division Department of Elect. and Comp. Eng University of Wisconsin Madison WI USA Real-Time Computing Laboratory Department of Elect. Engineering and Comp. Science University of Michigan Ann Arbor MI USA

In recent years a number of load sharing (LS) mechanisms have been proposed or implemented to fully utilize system resources. We design and implement a decentralized LS mechanism based on the Condor package, and give in this paper a description of our design and implementation approaches. Two important features of the design are the use of region-change broadcasts in the information policy to provide each workstation with timely state information at the minimum communication cost, and the use of preferred list in the location policy to avoid task collisions. With these two features, we remove the central manager workstation in Condor, configure its functionalities into each participating workstation, and thus enhance the capability to tolerate single workstation failure and the reliability of Condor. We also discuss the experiments we conduct on the LS mechanism and the observations we obtained from empirical data.< >

关键词： Workstations Packaging Kernel Software packages Chaotic communication Design engineering Broadcasting Costs Availability Delay

来源：评论

学校读者我要写书评

暂无评论

An optimal algorithm for approximate nearest neighbor searching 94

An optimal algorithm for approximate nearest neighbor search...

引用

Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms

作者： Sunil Arya David M. Mount Nathan S. Netanyahu Ruth Silverman Angela Wu Max-Planck-Institut für Informatik Im Stadtwald D-66123 Saarbrücken Germany Department of Computer Science and Institute for Advanced Computer Studies University of Maryland College Park Maryland Space Data and Computing Division NASA Goddard Space and Flight Center Greenbelt Maryland and Center for Automation Research University of Maryland College Park Maryland Department of Computer Science University of the District of Columbia Washington DC and Center for Automation Research University of Maryland College Park Maryland Department of Computer Science and Information Systems The American University Washington DC

来源：评论

学校读者我要写书评

暂无评论

A SIMPLE DISTRIBUTED LOOP-FREE ROUTING STRATEGY FOR computer-COMMUNICATION NETWORKS

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED systems 1993年第12期4卷 1308-1319页

作者： SHIN, KG CHOU, CC Real-Time Computing Laboratory Computer Science and Engineering Division Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA

The loops resulting from either component failures or Load changes in a computer communication network degrade the performance and the adaptability of conventional distributed adaptive routing strategies, such as ARPANET's previous routing strategy (APRS). In this paper, we develop a distributed loop-free routing strategy by adding only one additional piece of information-the total number of minimum-delay paths-to the commonly used routing messages and tables. Most conventional approaches to the looping problem suffer high overheads in time and space because each message must either include the first several nodes of its path or trace the entire path to detect a loop. By contrast, the proposed routing strategy requires only easily obtainable information, yet removes loops completely. It is far more efficient in both time and space than its conventional counterparts, especiallyTable Ifor sparse computer networks. The correctness of the proposed strategy is proved, and several illustrative e?xamples are given. The performance of this strategy is shown to be always better than, or at least as good as, that of APRS and any multiorder routing strategies, where the order of a routing strategy is determined by the amount of routing information carried in each routing message.

关键词： ARPANET computer COMMUNICATION NETWORKS DISTRIBUTED ADAPTIVE ROUTING LOOP-FREE OR FAULT-TOLERANT ROUTING NETWORK DELAY TABLES STRATEGY ROUTING MESSAGES

来源：评论

学校读者我要写书评

暂无评论

TASK DECOMPOSITION AND COMPETING EXPERT-SYSTEM - ARTIFICIAL NEURAL-NET OBJECTS FOR RELIABLE AND REAL-TIME INFERENCE

TASK DECOMPOSITION AND COMPETING EXPERT-SYSTEM - ARTIFICIAL ...

引用

1993 IEEE INTERNATIONAL CONF ON NEURAL NETWORKS / 2ND INTERNATIONAL CONF ON FUZZY systems

作者： KHOSLA, R DILLON, T Expert and Intelligent Systems Laboratory Applied Computing Research Institute Department of Computer Science and Computer Engineering La Trobe University Bundoora 3083 VIC Australia

ISBN: (纸本)0780309995

The properties of Artificial Neural Networks(ANNs) like massive parallelism, generalization make them amenable for application in various diagnostic/time-critical problem domains including alarm processing in power systems. However, enormous size of power systems haB inhibited real time use of ANNs. In this paper, we apply an integrated model for real time alarm processing in a real world terminal power station. The integrated model is a combination of a generic neuro-expert system model, object model, and unix operating system process(UOSP) model. We show how the massive parallelism and fast execution features of ANNs help us to cope with real-time system constraints like data variability and fast response time. For further enhancing reliability we propose a practical use of competing ES-ANN objects. © 1993 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of trace sampling for performance debugging tools 93

Effectiveness of trace sampling for performance debugging to...

引用

1993 ACM SIGMETRICS Conference on Measurement and Modeling of computer systems, SIGMETRICS 1993

作者： Martonosi, Margaret Gupta, Anoop Anderson, Thomas Computer Systems Laboratory Stanford University CA94305 United States Computer Science Division Univ. of California BerkeleyCA94720 United States

ISBN: (纸本)0897915801

Recently there has been a surge of interest in developing performance debugging tools to help programmers tune their applications for better memory performance [2, 4, 10]. These tools vary both in the detail of feedback provided to the user, and in the runtime overhead of using them. MemSpy [10] is a simulation-based tool which gives programmers detailed statistics on the memory system behavior of applications. It provides information on the frequency and causes of cache misses, and presents it in terms of source-level data and code objects with which the programmer is familiar. However, using MemSpy increases a program's execution time by roughly 10 to 40 fold. This overhead is generally acceptable for applications with execution times of several minutes or less, but it can be inconvenient when tuning applications with very long execution times. This paper examines the use of trace sampling techniques to reduce the execution time overhead of tools like MemSpy. When simulating one tenth of the references, we find that MemSpy's execution time overhead is improved by a factor of 4 to 6. That is, the execution time when using MemSpy is generally within a factor of 3 to 8 times the normal execution time. With this improved performance, we observe only small errors in the performance statistics reported by MemSpy. On moderate sized caches of 16KB to 128KB, simulating as few as one tenth of the references (in samples of 0.5M references each) allows us to estimate the program's actual cache miss rate with an absolute error no greater than 0.3% on our five benchmarks. These errors are quite tolerable within the context of performance debugging. With larger caches we can also obtain good accuracy by using longer sample lengths. We conclude that, used with care, trace sampling is a powerful technique that makes possible performance debugging tools which provide both detailed memory statistics and low execution time overheads. © 1993 ACM.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

An asynchronous neural network model for the shortest path problem

An asynchronous neural network model for the shortest path p...

引用

IEEE International Conference on Neural Networks, ICNN 1993

作者： Zhao, Songhe Dillon, T.S. Expert and Intelligent Systems Laboratory Applied Computing Research Institute Department of Computer Science and Computer Engineering La Trobe University BundooraVIC3083 Australia Northern Jiao-tong University Beijing China

ISBN: (纸本)0780309995

Researchers have shown that the neural network models can be used to find solutions for many optimization problems. Most of these models are energy based models and there is no guarantee the network converges to a global optimal solution. In this paper, we propose a new neural shortest path network model which no special convergence procedure needs to be performed. The network can work in purely an asynchronous mode and guarantees to reach the global optimal solution. © 1993 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An algorithm for the generalized singular value decomposition on massively parallel computers

引用

Journal of Parallel and Distributed computing 1993年第4期17卷 267-276页

作者： Park, Haesun Ewerbring, L. Magnus Computer Science Department University of Minnesota Minneapolis MN 55455 United States Mathematics and Computer Science Division Argonne national laboratory Argonne IL 60439 9700 South Cass Avenue United States Ericsson Radio Systems S-16480 Stockholm Sweden

A new algorithm for computing the generalized singular value decomposition that diagonalizes two matrices is introduced. First, two existing algorithms are studied, one due to Paige and the other to Han and Veselic. The former requires only orthogonal plane transformations, resulting in two matrices with parallel rows. The latter employs nonsingular (not necessarily orthogonal) transformations to directly diagonalize the two data matrices. For many applications, it is preferable to be given both the diagonal matrices and the transformation matrices explicitly. Our algorithm has the advantages that the nonsingular transformation is readily available, computation of transformations is simple, and the convergence test is efficient in a parallel computing environment. We present implementation results, obtained on a Connection Machine 2, to compare our new algorithm with that of Paige. © 1993 Academic Press, Inc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protein Secondary Structure Prediction Using Two-level Case-based Reasoning

Protein Secondary Structure Prediction Using Two-level Case-...

引用

1st International Conference on Intelligent systems for Molecular Biology, ISMB 1993

作者： Leng, Bing Buchanan, Bruce G. Nicholas, Hugh B. Intelligent Systems Laboratory Department of Computer Science University of Pittsburgh PittsburghPA15260 United States Pittsburgh Supper Computing Center University of Pittsburgh PittsburghPA15260 United States

ISBN: (纸本)0929280474

We have developed a two-level case-based reasoning architecture for predicting protein secondary structure. The central idea is to break the problem into two levels: first, reasoning at the object (protein) level, and using the global information from this level to focus on a more restricted problem space;second, decomposing objects into pieces (segments), and reasoning at the internal structures level;finally, synthesizing the pieces back to the objects. The architecture has been implemented and tested on a commonly used data set with 69.3% predictive accuracy. It was then tested on a new data set with 67.3% accuracy. Additional experiments were conducted to determine the effects of using different similarity matrices. Copyright © 1993, AAAI (***). All rights reserved.

关键词： Case based reasoning

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：