Showing papers in "Journal of Parallel and Distributed Computing in 2004"

TL;DR: The task of classifying the types of moving vehicles in a distributed, wireless sensor network is investigated and a data set that consists of 820 MByte raw time series data, 70 MByte of preprocessed, extracted spectral feature vectors, and baseline classification results using the maximum likelihood classifier is compiled.

TL;DR: Lower bounds on the amount of communication that matrix multiplication algorithms must perform on a distributed-memory parallel computer are presented and it is shown that in any algorithm that uses O(n2/P2/3) words of memory per processor, at least one processor must send or receive Ω(n 2/P1/2) words.

TL;DR: In this article, the authors focus on fundamental networking challenges in sensor networks, such as supporting multi-hop communication while limiting radio operation to conserve power, data management, including frameworks that support attribute-based data naming, routing and in-network aggregation, geographic routing challenges in networks where nodes know their locations, and monitoring and maintenance of dynamic, resource-limited systems.

TL;DR: This work presents two algorithms for the efficient placement of sensors in a sensor field when the exact locations of the sensors are not known, aimed at optimizing the number of sensors and determining their placement to support distributed sensor networks.

TL;DR: A technique for predicting the run times of parallel applications based upon the run time of “similar” applications that have executed in the past is presented, which achieves predictions that are between 21 and 64 percent better than those achieved by other techniques.

TL;DR: It is shown that exact algorithms with proposed efficient implementations can effectively replace heuristics in the one-dimensional decomposition of nonuniform workload arrays with optimal load balancing.

TL;DR: This work proposes a hybrid GA that takes as input the current replica distribution and computes a new one using knowledge about the network attributes and the changes occurred, and evaluates these algorithms with respect to the storage capacity constraint of each site as well as variations in the popularity of objects.

TL;DR: A technical defnition of the term self-organization is discussed, one where a collection of units coordinate with each other to form a system that adapts to achieve a goal more efficiently.

TL;DR: It is proved that two extensions--partial and dynamic data regrouping--are NP-hard problems and the compiler implementation and experiments demonstrating that the new global strategy, on average, reduces memory traffic by over 40% and improves execution speed by over 60% on two high-end workstations.

TL;DR: The development of an energy-efficient, high-performance distributed computing paradigm to carry out Collaborative Signal and Information Processing (CSIP) in sensor networks using mobile agents is reported and a cluster-based hybrid computing is proposed to combine the advantages of these two paradigms.

TL;DR: The completion time of broadcast operations on static ad hoc wireless networks in presence of unpredictable and dynamical faults is studied and an Ω(Dn) lower bound is provided where n is the number of nodes and D is the source eccentricity in the fault-free part of the network.

TL;DR: This work gives a unique parametric algorithm labeling each regular tiling of the plane and to outerplanar graphs with maximum degree Δ, and improves the best known upper bounds from Δ + 9, Δ + 5 and Δ + 3 to Δ + 1 and Δ colors for the values of h equal to 2, 1 and 0, respectively.

TL;DR: A parallel algorithm for color constancy is devised that works for scenes where the illuminant changes smoothly over the image and is tested on several images of everyday objects.

TL;DR: This paper gives a polynomial time algorithm to find the optimal program partition for given program input data and uses an option-clustering approach to handle different program partitions for different program execution options.

TL;DR: Two new techniques that accommodate more tasks and/or tolerate faults effectively are proposed and are generic that they can be incorporated into many fault-tolerant non-preemptive scheduling algorithms.

TL;DR: A new algorithm is presented, which solves the problem of distributively finding a minimum diameter spanning tree of any (non-negatively) real-weighted graph G=(V, E, ω), and achieves O(|V|) time complexity and O( |V||E|) message complexity.

TL;DR: This work presents a distributed uniformization-based technique for obtaining response time densities from very large unstructured Markov models that utilizes hypergraph partitioning to minimize inter-processor communication while maintaining a good load balance.

TL;DR: A complete characterization of the relationship with the problems of leader election for vertices and edges of an anonymous ring of n processors is given, and a lower bound and a reasonably close upper bound on the message complexity valid for sorting and leader election are established.

TL;DR: This work concludes that parallel computing will be the key to afford high-resolution structure determination of cells, so that the location of molecular signatures in their native cellular context can be made a reality.

TL;DR: A context-sensitive middleware, called Reconfigurable Context-Sensitive Middleware (RCSM), is presented for addressing this dynamic integration problem, and results indicate that the integration process is lightweight and results in reasonably high performance in PDA-like devices and desktop PCs.

TL;DR: This paper presents the design and implementation of a new dynamic fuzzy-decision-based load balancing system incorporated in a distributed object computing environment using a fuzzy logic controller which informs a client object to use the most appropriate service such that load balancing among servers is achieved.

TL;DR: This paper describes a grid transfer algorithm suitable for massively parallel codes which use multiple grids that uses a rendezvous technique wherein a third decomposition is used to search for elements in one grid that contain nodal points of the other.

TL;DR: This paper extends the previous work by analyzing the ability of the distributed tracker to track multiple targets in a simulated environment and results from simulations and field tests of the approach are provided.

TL;DR: A number of aspects regarding the generalization of the diffusion algorithms for the case when the processors have different relative speeds and the communication parameters have different values are addressed.

TL;DR: A system-level diagnosis algorithm for hypercube multicomputer systems based on the PMC model that can isolate all faulty processors to within a set that contains at most one fault-free processor is described.

TL;DR: An analytical model of energy-constrained, reliable, data-centric information routing in sensor networks under all the above constraints is developed and a game-theoretic metric called path weakness to measure the qualitative performance of different routing mechanisms is developed.

TL;DR: This work presents a set of modifications to a traditional debugger that makes it capable of debugging applications running on thousands of processes, and shows that the debugger is scalable to thousands of processors.

TL;DR: This paper reports the design of a peer-to-peer storage network called Tornado, which is built on top of the virtual home concept, which designates each data item in Tornado to a virtual home instead of directly to a peer node.

TL;DR: It is argued that modularity and efficiency, in the form of overlapping communication latencies and processor idle times, can be achieved much more easily inmessage-driven execution than in message-passing SPMD style.

TL;DR: A new approach to easing the design of parallel prefix circuits is presented, and a depth-size optimum parallel prefix circuit, named WE4 with fan-out 4 is constructed, which has the smallest depth among all known depthsize optimal prefix circuits with bounded fan- out.