Ontologies play a pivotal role in the Semantic Web by providing metadata for distributed and automated information processing. the standard ontology language OWL does not apply Unique Name Assumption. this lack leads ...
详细信息
Ontologies play a pivotal role in the Semantic Web by providing metadata for distributed and automated information processing. the standard ontology language OWL does not apply Unique Name Assumption. this lack leads to misunderstandings among users and complicates databases and software modeling. the paper presents ways to overcome it without increasing both computational and conceptual complexities of the standard formats. Weaker forms of name assumptions are also proposed which are more appropriate for the Semantic Web.
Article describes model of computation with feedforward multilayer neural network implemented in the network of workstations with cubic topology. Presented computation model is based on parallel error backpropagation ...
详细信息
Article describes model of computation with feedforward multilayer neural network implemented in the network of workstations with cubic topology. Presented computation model is based on parallel error backpropagation algorithm with regard to characteristics of simulations implementation architecture. Effectivity of parallel implementation of feedforward multilayer neural network is represented trough the cost of computation in parallel environment of workstations. Designed computation model allows formally describe components of parallel implementation of neural network. Model provides mathematical instrument for verification of performance, used in simulation of feedforward multilayer neural network on specified hardware platform.
In this paper, we present a distributed arithmetic (DA) formulation of the computation of discrete wavelet transform (DWT) using 9/7 filters, and mapped that into bit-parallel and bit-serial architectures for high-thr...
详细信息
In this paper, we present a distributed arithmetic (DA) formulation of the computation of discrete wavelet transform (DWT) using 9/7 filters, and mapped that into bit-parallel and bit-serial architectures for high-throughput and low-hardware implementations, respectively. the bit-serial structure processes the bit-slices of input vector in serial manner for low-hardware solution, while the bit-parallel structure processes all the bit-slices in parallel for high-throughput computation. the bit-parallel structure has 100% hardware utilization efficiency. Compared withthe existing multiplierless structures, the proposed structures offer significantly higher throughput rate and involve less area-delay product.
CCGrid' 2007, the 7th IEEE internationalsymposium on Cluster computing and the Grid was held in Rio de Janeiro, Brazil, on May 14 17, 2007. CCGrid has become a premium conference of truly international coverage, ...
详细信息
CCGrid' 2007, the 7th IEEE internationalsymposium on Cluster computing and the Grid was held in Rio de Janeiro, Brazil, on May 14 17, 2007. CCGrid has become a premium conference of truly international coverage, bringing together researchers and practitioners, enabling them to share their insight, results, and experience in the multi-faceted areas of Grid and cluster computing. the whole conference experience consisted of more than its strong technical program and also included three keynote speeches by scholars. there were seven workshops on emerging topics like the IEEE Technical Committee on Scalable computing Doctoral symposium, Agent-based Grid computing and Context-Awareness and Mobility in Grid computing. the paper by K. EL Maghraoui focused on adaptability for iterative MPI applications as adaptability enables a parallel application's execution system to split or merge processes, thereby modifying the executed program's granularity.
作者：
Mendes, Mário J.G.C.Santos, Bruno M.S.Da Costa, José SáIDMEC/ISEL
Instituto Superior de Engenharia de Lisboa Rua Conselheiro Emídio Navarro 1 1959-007 Lisboa Portugal Bluecape
Lda - CAE Solutions Alameda dos Oceanos 3.14.04H Esc. C Parque das Nações 1990-196 Lisboa Portugal IDMEC/IST
TULisbon Av. Rovisco Pais 1 1049-001 Lisboa Portugal
A general concern in industrial world is related to process maintenance, safety and availability problems in the presence of faults. Most industrial processes are very large or/and complex. Because of size and complex...
详细信息
In computer networks data flows can often reach transfer rates of several Gigabits per second. On the other hand most embedded systems have additional criteria - power consumption, size, low cost, generated heat - whi...
详细信息
In computer networks data flows can often reach transfer rates of several Gigabits per second. On the other hand most embedded systems have additional criteria - power consumption, size, low cost, generated heat - which usually means that even a flow rate of several Megabits per second is difficult to reach. this paper reports on the development of an automated embedded system for data transfers of up to 47 Mib/s using two customized embedded 68 k/Coldfire RISC microprocessors.
We discuss the application of Web 2.0 to support scientific research (e-Science) and related 'e-moreorlessanything' applications. Web 2.0 offers interesting technical approaches (protocols, message formats, an...
详细信息
We discuss the application of Web 2.0 to support scientific research (e-Science) and related 'e-moreorlessanything' applications. Web 2.0 offers interesting technical approaches (protocols, message formats, and programming tools) to build core e-infrastructure (cyberinfrastructure) as well as many interesting services (Facebook, YouTube, Amazon S3/EC2, and Google maps) that can add value to e-infrastructure projects. We discuss why some of the original Grid goals of linking the world's computer systems may not be so relevant today and that interoperability is needed at the data and not always at the infrastructure level. Web 2.0 may also support parallel Programming 2.0-a better parallelcomputing software environment motivated by the need to run commodity applications on multicore chips. A 'Grid on the chip' will be a common use of future chips with tens or hundreds of cores. Copyright (C) 2008 John Wiley & Sons, Ltd.
A system implemented in MATLAB is described, which may be deployed over a Campus Grid utilizing the Condor job management system. Our approach can re-distribute jobs as node availability changes. the architecture of t...
详细信息
A system implemented in MATLAB is described, which may be deployed over a Campus Grid utilizing the Condor job management system. Our approach can re-distribute jobs as node availability changes. the architecture of the system, its components, and their deployment across the Cardiff University Campus Grid (consisting of 2500 machines) are presented. Challenges in image processing applications that can be deployed over such infrastructure are presented, along with performance results that demonstrate the use of our system alongside a standard Condor deployment, demonstrating a significant increase in throughput using our approach(double dagger). Copyright (C) 2008 John Wiley & Sons, Ltd.
Resource selection on current brokers still presents challenges for achieving the best solution in the decision-making process, especially when considering many factors. We approach this problem considering user prefe...
详细信息
Resource selection on current brokers still presents challenges for achieving the best solution in the decision-making process, especially when considering many factors. We approach this problem considering user preference for specific resource selection objectives such as expected performance for an application execution, resource access restriction, execution application cost, and resource reliability. For each objective, we employ different techniques and combine them in a decision theory model. By considering performance in the selection process, we use the case-based reasoning technique based on similar past job executions to predict a new job time execution. Withthe resource access restriction as a selection factor, we develop a fine-grain policy-based model for distributed resource access verification. Unlike a global access policy, which applies to all resources in a virtual organization, a fine-grain policy establishes rules for specific resources and users. In this case, a previous access restriction verification prevents a resource selection, which may deny access to a requisition, resulting in an unsuccessful submission. the decision model uses the multi-attribute utility theory, which relates the important objectives above and allows different proportions of user preferences for each objective. the complete solution is distributed and implemented using a multi-agent system, acting as at resource broker. All models of this paper are analyzed in a real environment, presenting appropriate functional behaviors. Results, show that our prediction model is accurate and efficient in the prediction process and our distributed model runs faster than centralized approaches and considers access restriction heterogeneities. Copyright (C) 2008 John Wiley & Sons, Ltd.
A new parallel algorithm, based on the concept of antidiagonal wave pattern, for computing approximate inverses, is introduced for symmetric multiprocessor systems. the parallel normalized approximate inverses are use...
详细信息
ISBN:
(纸本)9780769534725
A new parallel algorithm, based on the concept of antidiagonal wave pattern, for computing approximate inverses, is introduced for symmetric multiprocessor systems. the parallel normalized approximate inverses are used in conjunction withparallel normalized preconditioned conjugate gradient-type schemes, for the efficient solution of sparse finite element linear systems. the parallel implementation issues of the new algorithm are discussed and the parallel performance is presented, using OpenMP.
暂无评论