Modern Information Infrastructure in the Support of Distributed Collective Practice in Transport

Transport is one of the oldest and most important forms of distributed collective practice. This paper traces the role of information and communication technologies in the transformation of transport-based distributed collective practice, focusing on the evolution of technologies that place control of the transport infrastructure in the hands of end users. Examples of this shift are provided, including an analysis of the events of September 11, 2001 as forms of distributed collective action.     

分布数据缓存体系

讨论了一种在分布信息访问环境下提高数据利用率和减少通信流量的分布缓存体系.缓存节点能缓存多个数据源的信息,使多个用户相互重用数据缓存,从而提高缓存的命中率.该缓存体系采用了多种不同的方法来解决数据缓存的一致性问题.最后提出了一种虚缓存节点的概念,用于扩展原来的体系.虚节点可以减少全局缓存访问优化计算的成本.     

一种数据并行中的群通信优化策略

群通信是影响大规模数据并行系统效率的关键因素,其主要发生在程序不同阶段间的数组重分布与循环划分后的数组重映射这两种情况.在一次通信中显著影响群通信效率常被忽视的因素是消息冲突和消息长度的不一致.因为它们会导致进程间大量的空闲等待时间.然而以前的研究要么不能完全避免消息冲突,要么针对某些特殊情况.对此,提出了在数组分布为Block_Cyclic(k)情况下的一种更具有普遍适用性的通信调度策略CSS.通过证明表明该策略能使一个通信步内的消息互不冲突且消息长度尽量相等.从而最小化通信调度生成时间和实际通信时间.最后的测试结果也表明,与传统的通信优化算法和MPI_Alltoallv实现相比,CSS策略使得通信效率得以明显提高.     

分布式系统一致性研究与案例分析

数据一致性是分布式系统研究领域的经典问题,大数据时代数据来源和业务需求的多样性及复杂性又为一致性研究带来了诸多新的挑战,同时也推动着这方面研究不断前进。目前关于分布式系统一致性的综述文章大多集中于介绍各种一致性模型的概念、定义,忽视了对模型在实际应用中的分析。论文在阐述现有一致性模型的基础上,结合实际系统进行案例分析,总结不同模型的适用范围;同时针对目前大数据技术的发展趋势,归纳一致性问题未来研究的发展方向,为读者进行一致性方面的研究提供一定的借鉴意义。     

基于支持向量数据描述的分布式数据流挖掘

针对传统分布式数据流挖掘算法的通信开销较大、分类精度较低的问题,提出一种基于支持向量数据描述的分布式数据流挖掘算法。利用局部站点快速更新数据流信息,采用支持向量机算法学习元级数据并传递到中心站点。中心站点负责接收及合并元级数据,形成全局分类结果。实验结果表明,该算法能在降低局部站点和中心站点网络通信量的同时,获得较高精度的全局分类结果。     

A Binding Procedure for Distributed Binary Data Representations

Problems (inherent in compound hierarchical representations) of preserving information on the structure of coded data and methods of solving them by “binding” of information substructures are discussed. A type of distributed representations is considered in which data are coded by multidimensional binary sparse vectors. The constraints imposed on a binding procedure are formulated and its implementation is provided. Some examples of representation of structured data are considered. __________ Translated from Kibernetika i Sistemnyi Analiz, No. 3, pp. 3–18, May–June 2005.     

Computational Collective Intelligence with Big Data: Challenges and Opportunities

Collective intelligence has been an important research topic in many AI communities. With The big data phenomenon, we have been facing on many research problems on how to integrate the big data with collective intelligence. This special issue has selected 9 high quality papers covering various research issues.     

分布式数据收集流程的改进及分析

对Platform公司分布式数据收集系统PERF进行研究,针对传统分布式数据收集流程中存在的容易导致数据收集过程中信息丢失、带宽浪费等问题,提出缩减中转环节等一系列方法,对数据的收集流程进行改进。通过分析客户应用该系统后的反馈信息,证明改进措施的有效性。     

Distributed Mining of Maximal Frequent Itemsets on a Data Grid System

In this paper, we propose a new algorithm, named Grid-based Distributed Max-Miner (GridDMM), for mining maximal frequent itemsets from databases on a Data Grid. A frequent itemset is maximal if none of its supersets is frequent. GridDMM is specifically suitable for use in Grid environments due to low communication and synchronization overhead. GridDMM consists of a local mining phase and a global mining phase. During the local mining phase, each node mines the local database to discover the local maximal frequent itemsets, then they form a set of maximal candidate itemsets for the top-down search in the subsequent global mining phase. A new prefix-tree data structure is developed to facilitate the storage and counting of the global candidate itemsets of different sizes. We built a Data Grid system on a cluster of workstations using the open-source Globus Toolkit, and evaluated the GridDMM algorithm in terms of performance, scalability, and the overhead of communication and synchronization. GridDMM demonstrates better performance than other sequential and parallel algorithms, and its performance is scalable in terms of the database size and the number of nodes. This research was supported in part by LexisNexis, NCR and AFRL/Wright Brothers Institute (WBI).     

分布式空间数据注册容器的设计与实现

分布式空间数据注册容器是国家地质空间信息网格(NGSIG)平台内一种重要的数据发现机制。该文介绍注册容器的重要特征及体系结构,描述其2个重要组成部分,即结点容器和应用门户容器。在NGSIG平台上实现空间数据注册容器,在空间数据整合中的应用表明,该容器运行效果良好。     

Five Steps to Construct a Model of Data Allocation for Distributed Database Systems

The allocation of data to nodes in a computer communications network is a critical issue in distributed database design, specially in wide area network where optimizing the distributed queries is the main objective. Numerous models of data allocation have been presented so far (Ceri and Pelagatti, 1986; Lee et al., 1994; Apers, 1988; Mahmood et al., 1994; Theel, 1994; Saha and Mukherjee, 1994; Walfson and Jajodia, 1995), but no optimal or universally accepted algorithm exists yet, and very few algorithms have been implemented to date (Rob and Cornonel, 1993). In this paper a method to construct a model of data allocation for distributed database system has been proposed. The adopted method for the construction of the data allocation model leads to an efficient model of its kind. The proposed model not only solves distributed database design problem, but also solves distributed database maintenance problem by covering initial allocation and post allocation of the data. The efficiency of proposed model has been proved by comparing proposed model with other relevant models.     

Distributed Data Acquisition and Control by Software Bus

Increasing global competition forces manufacturers of products fi‘om all technical fields to guarantee a high product quality for a long period of time. At the same time it is necessary to minimize production costs. In order to meet all these requirements, on-line data acquisition and processing ate of increasing importance in distributed automation systems. A software bus operating on industrial Ethemet has an ability to minimize operating costs by offering easy installation, scalability, high degree of reliability and remote monitoring and control.     

基于Rough集理论的分布式知识获取模型

分布式知识获取是当前数据挖掘研究领域的热点问题之一.为了利用Rough集理论荻取分布决策表中的知识,提出了一个基于Rough集理论的分布式知识获取模型,并讨论了数据在粗糙分布式环境下,运用信息抽取算子及知识生成算子获取全局决策规则的方法.这些理论与方法扩展了Rough集理论处理多数据源的知识获取问题.实例证明了这些方法的可行性.     

分布式数据库的复制和分片

该文通过对集中式数据库和分布式数据库进行比较,指出集中式数据库在存储能力,访问速度等方面存在的问题,对分布式数据库中的数据复制和分片的概念,原则,方法进行详细的论述,最后,对数据复制和分片要解决的关键问题进行分析。     

一个分布式数据采集系统的设计与研制

对现有的数据采集系统结构与性能进行研究后,设计了模块式数据采集盒和分布式数据采集系统结构.该系统利用网络技术,将采样、监控计算机和独立的数据采集盒连接起来,实现多现场、多通道实时数据的监控、采集与处理.给出了系统总体结构、数据采集盒原理与设计、系统软件功能设计和系统实现方案.采集频率达到每通道每秒1～30 次,可同时采样5 000通道、监控2 000通道,兼有模拟仿真与数据处理功能.     

分布式数据库的复制和分片

该文通过对集中式数据库和分布式数据库进行比较,指出集中式数据库在存储能力,访问速度等方面存在的问题,对分布式数据库中的数据复制和分片的概念,原则,方法进行详细的论述,最后,对数据复制和分片要解决的关键问题进行分析。     

e-Science应用中野外数据采集传输系统设计与实现

e-Science是近年新兴的研究热点,主要研究IT技术与各学科领域的结合与应用。野外数据的采集与传输是在涉及野外观测的学科领域中开展e-Science应用所面临的亟需解决的问题。提出了一种融合多种通讯方式的支持野外数据采集与传输的系统架构,以实现自动化、高效的数据采集与传输。提出的系统已经使用JAVA语言开发出了原型系统,经过测试有较好的实用效果。     

分布式VOD系统的视频数据存储

以降低视频服务损失率为目标研究分布式ＶＯＤ系统视频文件的存储策略,并给出了分布式视频服务器的视频文件存储方法。     

分布式数据监控系统的设计和实现

市场经济环境下,引入先进的信息技术可以加强宏观调控的科学性和提高宏观调控的效率,加大监控力度和监管效率.远程数据监控所获取的数据可以作为宏观调控的数据参考和依据,其具有数据容量大,监控现场环境复杂,原始数据来源多样化和异构化等特点.对此,提出了分布式监控系统功能结构和整体架构方案,分布式异构数据库设计方案,远程服务接口设计和实现方法.提出了客户端安全验证机制和远程服务调用的实现.     

分布式空间数据仓库的构建与OLAP服务实现

介绍基于分布式数据库技术、网络通信技术、地理信息系统技术的空间数据仓库的设计方法。以福建省沿海地区遗迹保护区为例,搭建了一个分布式的空间数据仓库。在此基础上实现以地区行政级别、类型划分及保护区一般信息为雏度的多粒度数据部署。并以本数据仓库为倒,根据不同的空间联机分析（OLAP）服务请求,动态创建数据立方体,完成OLAP服务并返回空间OLAP结果。