Scientists often have constraints from their experiments such as deadlines and budgets. For that reason, Job scheduling problem in Grid environments is not only important but also a challenging task. Both requirements...
详细信息
When learners access web-based educational systems, they often take advantage of what current web browsers offer: multiple tabs with different pages. Whether they are solving an exercise or learning a whole new topic,...
详细信息
ISBN:
(纸本)9781467351225;9781467351201
When learners access web-based educational systems, they often take advantage of what current web browsers offer: multiple tabs with different pages. Whether they are solving an exercise or learning a whole new topic, they can concurrently browse other relevant objects in the educational system or even resources outside the system, on the "wild" Web. this behavior goes unnoticed or it is only estimated in the traditional web usage mining, where it is supposed that the user opens only one page at a time. However, if we could record the parallel browsing behavior, we could better understand the user's activity, goals and improve learner model employed for personalization. the paths through resources (including spawning new tabs and switching between them) of many learners also express relevance between these resources and this can be leveraged in applications such as recommendation to other learners browsing similar learning objects. In this paper, we introduce a model for parallel browsing behavior based on events tracked with client-side scripting. We realized the proposed model in the ALEF educational system, which we use in several courses and evaluate learner behavior in the system.
the Random Access, Visualization and Exploration Network (RAVEN) aims to allow for the storage, analysis and visualisation of peta-bytes of scientific data in (near) real-time. In essence, RAVEN is a huge distributed ...
详细信息
ISBN:
(纸本)9783642281440
the Random Access, Visualization and Exploration Network (RAVEN) aims to allow for the storage, analysis and visualisation of peta-bytes of scientific data in (near) real-time. In essence, RAVEN is a huge distributed and parallel system. While testing of distributed systems, such as huge telecommunication systems, is well understood and performed systematically, testing of parallel systems, in particular high-performance computing, is currently lagging behind and is mainly based on ad-hoc approaches. this paper surveys the state of the art of software testing and investigates challenges of testing a distributed and parallel high-performance RAVEN system. While using the standardised Testing and Test Control Notation (TTCN-3) looks promising for testing networking and communication aspects of RAVEN, testing the visualisation and analysis aspects of RAVEN may open new frontiers.
Scalable analysis of massive graphs has become a challenging issue in high performance computing environments. ScaleGraph is an X10 library aimed for large scale graph analysis scenarios. this paper evaluates scalabil...
详细信息
ISBN:
(纸本)9781467323703;9781467323727
Scalable analysis of massive graphs has become a challenging issue in high performance computing environments. ScaleGraph is an X10 library aimed for large scale graph analysis scenarios. this paper evaluates scalability of ScaleGraph library for degree distribution calculation, betweeness centrality, and spectral clustering algorithms. We make scalability evaluation by analyzing a synthetic Kronecker graph with 40.3 million edges (for all the three algorithms), and a real social network with 69 million edges (for degree distribution calculation) on Tsubame 2.0 distributed memory environment.
the paper discusses implementation issues of a distributed program design tool based on monitoring of application global states. It is shown how the experience from the PS-GRADE parallel program design tool with contr...
详细信息
ISBN:
(纸本)9783642281501
the paper discusses implementation issues of a distributed program design tool based on monitoring of application global states. It is shown how the experience from the PS-GRADE parallel program design tool with controlling distributed programs at the process level, based on the extensive use of signals, can be transferred at the level of threads. A programming technique is proposed to combine the use of process level communication libraries like MPI or sockets withthe use of thread level libraries like OpenMP or pthreads. It enables designing a graphical parallel program development framework which uses signals at the level of distributedthreads executed in multiple cores of processors. Viable implementation of global state monitoring and involved control data transmissions at the level of threads are discussed.
the proceedings contain 77 papers. the topics discussed include: on aggressive early deflation in parallel variants of the QR algorithm;a model for efficient onboard actualization of an instrumental cyclogram for the ...
ISBN:
(纸本)9783642281440
the proceedings contain 77 papers. the topics discussed include: on aggressive early deflation in parallel variants of the QR algorithm;a model for efficient onboard actualization of an instrumental cyclogram for the mars MetNet mission on a public cloud infrastructure;distributed Java programs initial mapping based on extremal optimization;global asynchronous parallel program control for multicore processors;streaming model computation of the FDTD problem;numerical investigation of the cumulant expansion for Fourier path integrals;simulated annealing with coarse graining and distributedcomputing;high performance computing techniques for scaling image analysis workflows;parallel computation of bivariate polynomial resultants on graphics processing units;an interval version of the Crank-Nicolson method - the first approach;and an interval finite difference method of Crank-Nicolson type for solving the one-dimensional heat conduction equation with mixed boundary conditions.
the proceedings contain 77 papers. the topics discussed include: on aggressive early deflation in parallel variants of the QR algorithm;a model for efficient onboard actualization of an instrumental cyclogram for the ...
ISBN:
(纸本)9783642281501
the proceedings contain 77 papers. the topics discussed include: on aggressive early deflation in parallel variants of the QR algorithm;a model for efficient onboard actualization of an instrumental cyclogram for the mars MetNet mission on a public cloud infrastructure;distributed Java programs initial mapping based on extremal optimization;global asynchronous parallel program control for multicore processors;streaming model computation of the FDTD problem;numerical investigation of the cumulant expansion for Fourier path integrals;simulated annealing with coarse graining and distributedcomputing;high performance computing techniques for scaling image analysis workflows;parallel computation of bivariate polynomial resultants on graphics processing units;an interval version of the Crank-Nicolson method - the first approach;and an interval finite difference method of Crank-Nicolson type for solving the one-dimensional heat conduction equation with mixed boundary conditions.
Location-based applications such as Facebook Places, Foursquare, or Loopt attract millions of users by implementing point of interest finders, friend finders, geosocial networking, etc. Typically, these applications a...
详细信息
ISBN:
(纸本)9781467302586
Location-based applications such as Facebook Places, Foursquare, or Loopt attract millions of users by implementing point of interest finders, friend finders, geosocial networking, etc. Typically, these applications act as clients to a location service such as Google Latitude or Yahoo Fire Eagle, which manage mobile object positions and ensure the scalability to provide various clients with mobile object positions. However, exposing precise user positions raises user privacy concerns, especially if location service providers are not fully trusted, and private position information could be "lost", leaked, stolen, etc. To enable the secure management of private user positions on non-trusted location servers (LSs), we present novel position sharing approaches based on the concept of multi-secret sharing. Our approaches split up a precise user position into position shares, which are distributed to different LSs of different providers such that a compromised provider only reveals user positions with degraded precision. On the other hand, clients can combine several shares queried from different LSs to increase their provided precision without the need to store precise information at a single LS. We propose two position sharing approaches: PShare-SLM is the first position sharing approach presented so far for symbolic location models. For geometric location models, we present PShare-GLM, which improves existing geometric position sharing approaches [ 1] by considering continuous position updates and by increasing the robustness against various attacks.
Withthe development of WSN applications, there is increasing concern for the research of WSN. the routing algorithm is one of the important supporting technologies of WSN. However, the current studies of routing algo...
详细信息
this paper presents an overview of the new developments carried out to offer a reliable and efficient support for different computing infrastructures in the Kepler workflow orchestration system. the aim of the work is...
详细信息
暂无评论