检索结果-内蒙古大学图书馆

A distributed spectral-screening PCT algorithm

JOURNAL OF PARALLEL AND distributed COMPUTING 2003年第3期63卷 373-384页

作者： Achalakul, T Taylor, S King Mongkuts Univ Technol Dept Comp Engn Bangkok 10140 Thailand Dartmouth Coll Thayer Sch Engn Hanover NH 03755 USA

This paper describes a novel distributed algorithm for use in remote-sensing, medical image analysis, and surveillance applications. The algorithm combines spectra I-screening classification with the principal component transform, and human-centered mapping. It fuses a multi- or hyper-spectral image set into a single color-composite image that maximizes the impact of spectral variation on the human visual system. The algorithm operates on distributed collections of shared-memory multiprocessors that are connected through high-performance networking. Scenes taken from a standard 210 frame remote-sensing data set, collected with the hyper-spectral digital imagery collection experiment airborne imaging spectrometer, are used to assess the algorithms image quality, performance, and scaling. The algorithm is supported with a predictive analytical model that allows its performance to be assessed for a wide variety of typical variations in use. For example, changes to the number of spectra, image resolution, processor speed, memory size, network bandwidth/latency, and granularity of decomposition. The motivation in building a performance model is to assess the impact of changes in technology and problem size associated with different applications, allowing cost-performance tradeoffs to be assessed. (C) 2003 Elsevier Science (USA). All rights reserved.

关键词： principal component transform spectral angle classification distributed algorithm performance prediction

来源：评论

学校读者我要写书评

暂无评论

Protocol for dynamic ad-hoc networks using distributed spanning trees

引用

WIRELESS NETWORKS 2003年第6期9卷 673-686页

作者： Radhakrishnan, S Racherla, G Sekharan, CN Rao, NSV Batsell, SG Univ Oklahoma Sch Comp Sci Norman OK 73019 USA Loyola Univ Dept Comp Sci Chicago IL 60626 USA Oak Ridge Natl Lab Networking Lab Oak Ridge TN 37831 USA

A dynamic ad-hoc network consists of a collection of mobile hosts with frequently changing network topology. We propose a distributed algorithm that adapts to the topology by utilizing spanning trees in the regions where the topology is stable, and resorting to an intelligent flooding-like approach in highly dynamic regions of the network. Routing is performed using the spanning trees based a hold-and-forward or shuttling mechanisms. We introduce the notion of connectivity-through-time and the parameter holding-time as new fundamental concepts that can be used by ad-hoc routing algorithms. For various network connectivity scenarios we evaluate the impact of these concepts on the performance of ad-hoc routing algorithms. Using simulation, we study the throughput, reachability and message-reachability ratio of the proposed schemes under various connection/disconnection rates and holding times.

关键词： ad-hoc network routing spanning tree distributed algorithm simulation

来源：评论

学校读者我要写书评

暂无评论

distributed multiple target tracking and data association in ad hoc sensor networks

Distributed multiple target tracking and data association in...

引用

6th International Conference on Information Fusion

作者： Chu, M Mitter, S Zhao, F Palo Alto Res Ctr Palo Alto CA 94303 USA

ISBN: (纸本)0972184449

We introduce an efficient distributed algorithm for tracking multiple targets in an ad hoc sensor network. The key idea is to explicitly model an intermediate representation, which we refer to as individual track contributions, so that the effect of measurements observed by a node of the sensor network can be incorporated locally. Furthermore, since targets affect the observations of a local neighborhood of sensor nodes, communications are limited to local regions around currently known targets. A particularly important problem in multiple target tracking is the problem of data association. Since a sensor network is capable of measuring heterogeneous data, we divide the possible resolutions of ambiguity in data association into three categories. Discriminatory information is: (1) immediately available to resolve the ambiguity in data association, (2) delayed to resolve the ambiguity, and (3) unavailable. In this paper, we demonstrate the incorporation of target identity information when discriminatory information is available and a factored representation of tracks when discriminatory information is unavailable. We build efficiency into the tracking algorithm by triggering the extraction of discriminatory information and triggering the use of such information during tracking only when it is deemed necessary.

关键词： multiple target tracking classification data association sensor network distributed algorithm

来源：评论

学校读者我要写书评

暂无评论

A utility-based power-control scheme in wireless cellular systems

引用

IEEE-ACM TRANSACTIONS ON NETWORKING 2003年第2期11卷 210-221页

作者： Xiao, M Shroff, NB Chong, EKP Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

distributed power-control algorithms for systems with hard signal-to-interference ratio (SIR) constraints may diverge when infeasibility arises. In this paper, we present a power-control framework called utility-based power control (UBPC) by reformulating the problem using a softened SIR requirement (utility) and adding a penalty on power consumption (cost). Under this framework, the goal is to maximize the net utility, defined as utility minus cost. Although UBPC is still noncooperative and distributed in nature, some degree of cooperation emerges: a user will automatically decrease its target SIR (and may even turn off transmission) when it senses that traffic congestion is building up. This framework enables us to improve system convergence and to satisfy heterogeneous service requirements (such as delay and bit error rate) for integrated networks with both voice users and data users. Fairness, adaptiveness, and a high degree of flexibility can be achieved by properly tuning parameters in UBPC.

关键词： admission control cellular system distributed algorithm fairness Nash equilibrium Pareto optimal power control robustness signal-to-interference ratio (SIR) stability utility function wireless

来源：评论

学校读者我要写书评

暂无评论

Synchronization and handoff management schemes for wireless multimedia systems

引用

COMPUTER NETWORKS 2003年第3期41卷 347-362页

作者： Boukerche, A Hong, SB Jacob, T Univ N Texas Dept Comp Sci Denton TX 76203 USA

This paper presents handoff management schemes for synchronization algorithms for wireless multimedia systems. The synchronization and handoff management schemes allow mobile hosts to receive time-dependant multimedia streams without delivery interruption while moving from one cell to another. They also maintain the correct ordering of the media components, through the execution of the wireless multimedia application by a means of timestamped messages passed among mobile hosts, base stations and servers. The timestamp values are used to compute the delay for each multimedia unit for each server. Furthermore, the proposed schemes always search for a quasi-receiver among the base stations with which the mobile hosts can communicate to synchronize multimedia units. We discuss the algorithms and present a set of simulation experiments that evaluate the performance of our schemes, using message complexity and buffer usage at each frame arrival time. Our results indicate that. our schemes exhibit no underflow or overflow within the bounded delivery time. (C) 2002 Published by Elsevier Science B.V.

关键词： distributed algorithm synchronization mobile multimedia wireless communications end-to-end protocol

来源：评论

学校读者我要写书评

暂无评论

Asynchronous implementation of failure detectors

Asynchronous implementation of failure detectors

引用

International Conference on Dependable Systems and Networks

作者： Mostefaoui, A Mourgaya, E Raynal, M Univ Rennes 1 IRISA F-35042 Rennes France

ISBN: (纸本)0769519520

Unreliable failure detectors introduced by Chandra and Toueg are abstract mechanisms that provide information on process failures. On the one hand, failure detectors allow to state the minimal requirements on process failures that allow to solve problems that cannot be solved in purely asynchronous systems. But, on the other hand, they cannot be implemented in such. systems: their implementation requires that the underlying distributed system be enriched with additional assumptions. The usual failure detector implementations rely on additional synchrony assumptions (e.g., partial synchrony). This paper proposes a new look at the implementation of failure detectors and more specifically at Chandra-Toueg's failure detectors. The proposed approach does not rely on synchrony assumptions (e.g., it allows the communication delays to always increase). It is based on a query-response mechanism and assumes that the query/response messages exchanged obey a pattern where the responses from some processes to a query arrive among the (n - f) first ones (n being the total number of processes, f the maximum number of them that can crash, with 1 less than or equal to f < n). When we consider the particular case f = 1, and the implementation of a failure detector of the class denoted lozengeS (the weakest class that allows to solve the consensus problem), the additional assumption the underlying system has to satisfy boils down to a simple channel property, namely, there is eventually a pair of processes (p(i), p(j)) such that the channel connecting them is never the slowest among the channels connecting p(i) or p(j) to the other processes. A probabilistic analysis shows that this requirement is practically met in asynchronous distributed systems.

关键词： Asynchronous distributed systems distributed algorithm Fault tolerance Process crash Unreliable failure detectors

来源：评论

学校读者我要写书评

暂无评论

Leader election in rings with nonunique labels

Leader election in rings with nonunique labels

引用

International Conference on Parallel and distributed Processing Techniques and Applications

作者： Dobrev, S Pelc, A Univ Ottawa SITE Ottawa ON K1N 6N5 Canada

ISBN: (纸本)1892512459

We consider the leader election problem in a ring whose nodes have possibly nonunique labels. Every node knows a priori its own label and two integers, m and M, which are, respectively, a lower and an upper bound on the (unknown) size n of the ring. The aim is to decide whether leader election is possible and to perform it, if so. We consider both the synchronous and the asynchronous version of the problem and we are interested in message complexity in both cases. For the synchronous version we present an algorithm using 0 (n log n) messages and working in time O(M). Moreover, our algorithm uses O(n) messages when all identifiers are distinct. For the asynchronous version we show an Omega(nM) lower bound on message complexity for this problem, and present an algorithm for it using Omega(nM) messages.

关键词： distributed algorithm leader election ring

来源：评论

学校读者我要写书评

暂无评论

A method for evaluating efficiency of protocols on the asynchronous shared-state model

引用

6th International Symposium on Self-Stabilizing Systems (SSS 2003)

作者： Nakaminami, Y Masuzawa, T Herman, T Osaka Univ Suita Osaka 565 Japan Univ Iowa Iowa City IA 52242 USA

ISBN: (纸本)3540404538

distributed systems are commonly modeled by asynchronous models where no assumption is made about process execution speed. The asynchronous model is preferable to the synchronous one because the model reflects the fact that a distributed system consists of computers with different processing speeds. However, the asynchrony of the system makes it difficult to evaluate efficiency (performance) of distributed protocols. This paper defines a class of distributed protocols called linear state-transition protocols, in the state-communication model, and shows that efficiency of such protocols in the asynchronous distributed model can be derived from analysis of their synchronous execution, where all processes are synchronized in the lock-step fashion. This provides an effective method for evaluating efficiency of the linear state-transition protocols in the asynchronous distributed model. The paper also demonstrates the effectiveness of the method by applying it to the self-stabilizing alternator.

关键词： distributed system distributed algorithm asynchronous model time complexity synchronous execution linear state-transition protocol

来源：评论

学校读者我要写书评

暂无评论

On the Load Balancing of a Parallel Switch with Input Queues

On the Load Balancing of a Parallel Switch with Input Queues

引用

The Fourth International Conference on Parallel and distributed Computing, Applications and Technologies

作者： Yuguo Dong Peng Yi Yunfei Guo Jiangxin Wu National Digital Switching System Engineering & Technological R&D Center National Digital Switching System Engineering & Technological R&D Center

ISBN: (纸本)0780378407

The parallel switch is an emerging switch technology,by which we can build a high capacity switching system,such as a terabit switch,from many small switch *** a parallel switch with input queues, the high-speed packets will queue in the input buffer for scheduling,which can highly reduce the control complexity and the internal *** this paper we refer to parallel switch with input queues as Buffered Parallel Switch(BPS). Since the switch fabrics in a BPS are working parallel and independently,we address the open issue of switch fabrics' load-balancing and propose a family of distributed scheduling *** also prove that such load-balancing algorithms can guarantee the delay time of the *** results show the validity and performance of our load-balancing *** considerations on implementing the scheduling algorithms are discussed.

关键词： Parallel switch load balancing buffer scheduling distributed algorithm

来源：评论

学校读者我要写书评

暂无评论

distributed State Space Minimization

引用

Electronic Notes in Theoretical Computer Science 2003年 80卷 109-123页

作者： Stefan Blom Simona Orzan CWI P.O.Box 94079 NL-1090 GB Amsterdam The Netherlands

In [5], we have given a straightforward distributed implementation of the Kanellakis-Smolka 'naive' algorithm for reducing labeled transition systems modulo strong bisimulation. The algorithm proceeds by partition refinement, that is by computing increasingly fine-grained partitions of the set of states. In this paper we present an optimized distributed implementation, in which the refinements are no longer entirely recomputed in every iteration, but they are computed incrementally. A second significant improvement is the overlap between communication and computation, that results in a better use of both memory and processing power. We discuss these optimizations and show experimental results.

关键词： state spaces strong bisimulation distributed algorithm

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：