PDM:基于Hadoop的并行数据分析系统

提出了一款基于Hadoop的并行数据分析系统——PDM.该系统拥有大量以MapReduce为计算框架的并行数据分析算法,不仅包括传统的ETL、数据挖掘、数据统计和文本分析算法,还引入了基于图理论的SNA(社会网络分析)算法.详细阐述了并行多元线性回归算法和多源最短路径算法的原理和实现,其中,提出的消息传递模型能有效解决MapReduce难以处理邻接矩阵的问题;介绍了基于电信数据的典型应用,如采用并行k均值和决策树算法实现的套餐推荐,利用并行PageRank算法实现的营销关键点发现等;最后通过性能测试,说明该系统适合高效地处理大规模数据.     

Tracking Co-evolution of Behavior and Relationships with Mobile Phones

The co-evolution of social relationships and individual behavior in time and space has important implications,but is poorly understood because of the difficulty of closely tracking the everyday life of a complete community.We offer evidence that relationships and behavior co-evolve in a student dormitory,based on monthly surveys and location tracking through resident cellular phones over a period of nine months.We demonstrate that a Markov jump process could capture the co-evolution in terms of the rates at which residents visit places and friends.Our co-evolution model will be useful in bridging sensor networks data and organizational dynamics theories,simulating different ways to shape behavior and relationships,and turning mobile phone data into data products.     

基于异构网络环境中的接纳控制算法

接纳控制机制可以有效控制网络拥塞程度,为VoIP应用提供服务质量保证。RED算法可以为VoIP应用提供公平的队列管理机制,鉴于RED队列的优越性和普遍性,提出了RED队列的延迟分析计算方法,并基于该计算方法设计实现了基于RED的接纳控制算法,仿真结果表明该算法是有效的。     

面向服务的C4ISR系统能力需求分析与建模方法

面向服务计算（SOC）提供了一种满足C4ISR系统动态需求的新的集成架构,面向服务集成是未来C4ISR系统综合集成的必然趋势。为了解决C4ISR高层需求描述到系统设计的映射问题,将面向服务思想引入C4ISR系统的能力需求分析,提出了一种面向服务的C4ISR系统能力需求分析建模方法。该方法在3层多本体的基础上,由活动分析驱动服务建模,通过整合服务提供能力需求,为C4ISR系统分析设计和系统集成提供了一种更灵活的解决方案。最后,采用一个案例说明了方法的有效性和可用性。     

求解对流-扩散方程的一类显示交替分组方法

对求解对流-扩散方程初边值问题的第二类Saul’yev非对称格式以及古典显、隐格式进行组合,提出一种新的求解对流-扩散方程的显示交替分组方法,并对新方法进行稳定性分析和数值实验.新方法针对内点为偶数的情况,在节点两端点处用分组格式进行处理,所得解的精度高,稳定性好,容易在并行机上实现.     

现代网络打印解决方案

该文讨论网络计算环境下网络打印的概念、连接方式及其解决方案。     

教育经济贡献率的一种软计算方法

提出了一种新的教育经济贡献率的软计算方法,该算法由4个步骤组成:①按照科学技术水平对目标系统进行模糊软分类,得到最佳分类数,从而确定了最佳的规则数;②根据规则数确定模糊神经网络的结构,建立人力资本到经济增长的模糊映射,即“一次滤波”,得到人力资本对经济增长的贡献率αk;③建立教育到人力资本的模糊映射,即“二次滤波”,得到教育对人力资本的贡献率α′k;④计算教育对经济的贡献率ECFk=αk×α′k。最后,用该算法来计算我国教育对经济的贡献率。     

高等教育计算和信息技术学科面临的挑战

Despite the growth of the IT industry and the high demand for IT skills university departments seem unable to attract enough student to cater for the needs of the profession.There seems to be a misconception about the difference between IT user skills and the discipline of Computing.This article attempts to do three things:1)reinforce the view that a crisis of IT skills shortage is looming;2)reiterate the fact that computing science is an exciting discipline that is central to the knowledge economy and that career prospects in IT-related jobs are very good despite the fears surrounding outsourcing and 3)suggest that HE computing departments must be flexible enough to embrace a two-facetted challenge:a)the changing landscape of IT Skills and b)the high hopes and aspirations of the first generation of our digital-native student community.     

Study on High-Performance Computing for Simulation of End Milling Force

Milling Process Simulation is one of the important re search areas in manufacturing science. For the purpose of improving the prec ision of simulation and extending its usability, numerical algorithm is more and more used in the milling modeling areas. But simulative efficiency is decreasin g with increase of its complexity. As a result, application of the method is lim ited. Aimed at above question, high-efficient algorithm for milling process sim ulation is studied. It is important for milling process...     

基于SUSAN算子的边缘增强低比特率图像压缩

提出一种新的低比特率图像压缩算法,该算法首先利用SUSAN算子检测出输入图像的边缘信息,然后利用边缘增强方法对边缘信息进行增强,最后将增强后的边缘信息和解码后的输入图像相加形成最终的压缩图像.实验结果表明,和基于小波的传统编码方法相比,在低比特率下,该算法能减少图像的边缘模糊,提高压缩图像的识别度和峰值信噪比.