作者：
Nam, YYHwang, EJAjou Univ
Grad Sch Informat & Commun Suwon 441749 South Korea Korea Univ
Dept Elect & Comp Engn Seoul 136701 South Korea
As the market of mobile devices for video streaming is growing rapidly, it is necessary to convert a high bit rate MPEG stream into a low bit rate MPEG stream. However, it takes long time to transcode MPEG to another ...
详细信息
ISBN:
(纸本)3540240136
As the market of mobile devices for video streaming is growing rapidly, it is necessary to convert a high bit rate MPEG stream into a low bit rate MPEG stream. However, it takes long time to transcode MPEG to another steaming media format due to the huge amount of computation in a traditional single computing environment. Furthermore, real-time MPEG transcoding also demands high computational power. Fortunately, the algorithms compliant to the MPEG standard can be parallelized. In this paper, we propose several scheduling algorithms for real-time transcoding of MPEG video that can be used in heterogeneous distributedcomputing environments. In the experiment, we will compare their performance through an experimental evaluation.
Topology control is an effective mechanism to save energy for ad hoc networks. In this paper, we propose an energy-saving topology control algorithm for heterogeneous ad hoc networks with non-uniform transmission rang...
详细信息
ISBN:
(纸本)3540240136
Topology control is an effective mechanism to save energy for ad hoc networks. In this paper, we propose an energy-saving topology control algorithm for heterogeneous ad hoc networks with non-uniform transmission ranges: Minimum-power Ingress Neighbor Sub-network (MINS), which is fully distributed, asynchronous and localized. MINS not only preserves the network connectivity, but also has low communication overhead compared with other topology control algorithms. Simulation results show the effectiveness of our proposed algorithm.
Simulation is a powerful tool for the analysis of new system designs, retrofits to existing systems and proposed changes to operating rules. In this paper we limit our discussion to parallel and distributed simulation...
详细信息
ISBN:
(纸本)3540240136
Simulation is a powerful tool for the analysis of new system designs, retrofits to existing systems and proposed changes to operating rules. In this paper we limit our discussion to parallel and distributed simulation (PDS). In order to simulate large-scale complex systems with better consistency, further more as fast as possible, the universally adoptive approach of PDS is that make the execution of simulation programs on multiprocessor and distributedcomputing platforms. Time management algorithm is one of the key techniques in the parallel and distributed system simulation, which broadly fall into conservative and optimistic synchronization. A survey of boththe two algorithms is presented focusing on fundamental principles and mechanisms. the remainder of this paper is focused on one of the novel rollback algorithm;we call it as smart rollback algorithm. And then, we provide and describe the novel rollback algorithm in optimistic time management in detail, including scheduler's priority queue, rollback manager, cancellation strategies, and roll forward operation. Among this paper, central issues concern the synchronization of computations on different processors. Finally, we discuss how to get the relatively minimal rollback, and how to realize the dynamic allocation and reclamation.
In this paper, we propose a multi-dimensional category model (MDCM) for classifying multi-dimensional text collection. We can parallel and distribute the process of text classification in separately on each dimension....
详细信息
ISBN:
(纸本)3540240136
In this paper, we propose a multi-dimensional category model (MDCM) for classifying multi-dimensional text collection. We can parallel and distribute the process of text classification in separately on each dimension. Withthis model, performance of classifiers improves in both accuracy and time complexity. For classification accuracy, some benefits can be obtained. Classifiers learn from larger training documents with a small number of classes on each dimension. We can select the best classifier for each dimension and combine the results from them. For time complexity, the learning and classifying phases can be in parallel and distributed manner. the efficiency of MDCM is investigated on drug information data set which assigns topics in monographs in the first dimension and primary therapeutic classes in the second dimension. the experimental results show that parallel text classification on MDCM performs better than flat model in both accuracy and time complexity.
Today9;s cryptanalysis on symmetric key cryptography is encouraging the use of larger key sizes and complex algorithms to achieve an unbreakable state. However, this leads an increase in computational complexity. T...
详细信息
ISBN:
(纸本)3540240136
Today's cryptanalysis on symmetric key cryptography is encouraging the use of larger key sizes and complex algorithms to achieve an unbreakable state. However, this leads an increase in computational complexity. this has promoted many researchers to develop high-performance symmetric key cryptography schemes using approaches such as the use of high-end computing hardware. Peer-to-peer (P2P) or enterprise grids are proven as one of the approaches for developing cost-effective high-end computing systems. By utilizing them, one can improve the performance of symmetric key cryptography through parallel execution. this approach makes it attractive for adoption by businesses to secure their documents. In this paper we propose and develop an application for symmetric key cryptography using enterprise grid middleware called Alchemi. An analysis and comparison of its performance is presented along with pointers to future work.
this paper presents a proximity route selection scheme which is adaptive to the underlying network conditions. the proposed scheme repeatedly estimates and updates the total lookup latency based on the information fro...
详细信息
ISBN:
(纸本)3540240136
this paper presents a proximity route selection scheme which is adaptive to the underlying network conditions. the proposed scheme repeatedly estimates and updates the total lookup latency based on the information from the neighborhoods. the updated information is used to select the next peer dynamically to route the query, which results in reducing the overall lookup latency. We implemented the scheme using the Chord, one of the most popular DHT-based peer to peer systems, and compared the performance withthose of original Chord and the CFS' server selection scheme. the proposed scheme shows performance improvement over other schemes.
this paper addresses the possibility that IP, in the role of the common service, is not as general as is needed in order-to directly address application requirements, including scalable storage services, that go beyon...
详细信息
A wide range of planning applications are combinatorial in nature, making the design of general purpose planning algorithms a still very challenging endeavor. In order to cope withthis combinatorial complexity, some ...
详细信息
A wide range of planning applications are combinatorial in nature, making the design of general purpose planning algorithms a still very challenging endeavor. In order to cope withthis combinatorial complexity, some of the most recent work in artificial intelligence (AI) planning focuses on the use of sophisticated heuristics, domain search control knowledge, random search and efficient abstract state space encodings such as binary decision diagrams. the additional performance needed by complex planning applications can be provided by adopting massively parallelcomputing systems, such as networks of clusters. this paper describes a simple, general approach for turning backtrack search based planners into more powerful distributed systems that run on networks of clusters. Our approach consists in distributing backtrack search points to different processes on the network. We illustrate its potential using DSHOP, a distributed version of the SHOP planner.
In this paper the authors present the architecture and current status of implementation of a Grid-based environment for large scientific virtual organizations, with primary focus on the hydrometeorological community. ...
详细信息
the proceedings contain 26 papers. the special focus in this conference is on Static Analysis, distributed Systems, Real-Time Systems, Reflection and XML. the topics include: On the role of conceptual schemas in infor...
ISBN:
(纸本)3540220119
the proceedings contain 26 papers. the special focus in this conference is on Static Analysis, distributed Systems, Real-Time Systems, Reflection and XML. the topics include: On the role of conceptual schemas in information systems development;static deadlock detection in the Linux kernel;the chance for Ada to support distribution and real-time in embedded systems;a schizophrenic middleware to build versatile reliable distributedapplications;event language for real-time on-the-fly control according to the initial requirements;implementing execution-time clocks for the Ada ravenscar profile;extending the capabilities of real-time applications by combining MARTE-OS and Linux;supporting deadlines and EDF scheduling in Ada;a randomised test approach to testing safety critical Ada code;teaching real-time systems around a digital model railroad platform using Ada;high-integrity interfacing to programmable logic with Ada;implementing an application-defined scheduling framework for Ada tasking and a theory of persistent containers and its application to Ada.
暂无评论