Data-intensive document clustering on graphics processing unit (GPU) clusters

Document clustering is a central method to mine massive amounts of data. Due to the explosion of raw documents generated on the Internet and the necessity to analyze them efficiently in various intelligent information systems, clustering techniques have reached their limitations on single processors. Instead of single processors, general-purpose multi-core chips are increasingly deployed in response to diminishing returns in single-processor speedup due to the frequency wall, but multi-core benefits only provide linear speedups while the number of documents in the Internet is growing exponentially. Accelerating hardware devices represent a novel promise for improving the performance for data-intensive problems such as document clustering. They offer more radical designs with a higher level of parallelism but adaptation to novel programming environments.In this paper, we assess the benefits of exploiting the computational power of graphics processing units (GPUs) to study two fundamental problems in document mining, namely to calculate the term frequency-inverse document frequency (TF-IDF) and cluster a large set of documents. We transform traditional algorithms into accelerated parallel counterparts that can be efficiently executed on many-core GPU architectures. We assess our implementations on various platforms, ranging from stand-alone GPU desktops to Beowulf-like clusters equipped with contemporary GPU cards. We observe at least one order of magnitude speedups over CPU-only desktops and clusters. This demonstrates the potential of exploiting GPU clusters to efficiently solve massive document mining problems. Such speedups combined with the scalability potential and accelerator-based parallelization are unique in the domain of document-based data mining, to the best of our knowledge.     

面向用户柔点的设计模型

为了提高软件适应需求变化的能力,设计出具有良好柔性的软件,提出了一种基于面向用户柔点的设计模型.给出面向用户柔点的概念和特征,指出柔点与需求变化的密切联系.在此基础上,通过归纳需求变化的分类,抽象出柔点的分类.利用MVC(模型-视图-控制器)框架和软件设计模式给出通用的柔点设计模型,根据柔点的分类将模型细化.通过一个网...     

基于奇异值加权的图像复制粘贴伪造盲检测

提出了一种基于小波变换和奇异值分解的盲检测算法来识别图像的复制粘贴伪造。该算法用小波变换降低计算量,用奇异值表示图像特征。图像经过小波变换,提取出低频分量和高频分量。因低频部分保留图像的纹理信息,高频部分保留图像的轮廓信息,该算法分别从低频部分和高频部分提取图像奇异值,并把提取出的奇异值进行加权处理,以加权值作为图像块的特征。图像块之间做两两比较,根据图像块的特征相似度,判断是否存在图像复制粘贴伪造区域。在丰富层次和清晰细节轮廓的图像中,该算法能达到比较理想的检测效果,准确率较高。     

用可分负载理论分析无线传感器网络任务调度

针对无线传感器网络的任务如何在最短时间内完成且充分利用网络资源的问题,提出了一种基于可分负载理论的无线传感器网络任务调度算法（WDTA）.该算法根据网络中各个节点的处理能力和节点间的通信能力,将总任务从SINK节点下发至网络中.通过去除节点间的通信干扰来提高资源利用率和减少总任务完成时间.算法在两种分群结构的异构网络环境下进行了分析,得到了在各个节点上最合理的任务分配方案,以及最短的任务完成所需时间.理论分析了基于可分负载理论的无线传感器网络任务调度的极限情况.实验结果表明WDTA算法能够通过合理分配任务,而减少任务完成时间及节点能耗.该方案可以作为设计大规模无线传感器网络的原则.     

一种新型本征倏逝波型光纤传感器的研究

研究开发了一种新型本征型光纤倏逝波传感器.采用有机玻璃板和大半圆弧高抛光PVC管构成光纤支架,将60/125 μm阶跃多模光纤隔一定距离剥除等长度涂覆层后缠绕于光纤支架上,其无涂覆层部分位于上下两PVC管之间,经化学腐蚀后获得裸芯总长度大于0.5m的新型高灵敏本征型光纤倏逝波传感器.实验结果表明:该传感器对亚甲基蓝的探...     

基于IGBT的100kHz逆变电源控制的CPLD实现

采用CPLD实现一种脉冲均匀密度的功率调节(PSM)的100kHz串联谐振逆变电源,其具有控制电路简单,可靠性高等优点.介绍了脉冲均匀调制的原理及其CPLD的设计实现,给出了CPLD程序模块图以及仿真波形和试验结果.证明了其可行性.     

提高测厚仪系统安全性和控制精度

为了提高钢板的头部精度,从测量原理、组成等方面,介绍了安钢炉卷生产线X射线测厚仪系统安全性和控制精度的提高.     

NSFC1系列永磁式交流接触器在石化企业中的应用

介绍一种值得在石化企业中推广采用的新型电控设备--NCSF1系列永磁式交流接触器.     

UV surface exposure for low temperature hydrophilic silicon direct bonding

The ultraviolet (UV) surface exposure is applied in hydrophilic silicon direct bonding as an additional treatment following the traditional wet chemical activation processes. Infrared inspection and tensile strength test are then performed. It is found that improvement in bond-rate, interface uniformity as well as high tensile strength is obtained. The mechanism of UV exposure including surface cleaning and surface modification is discussed in detail. Mixed spectrum emitted from the UV source comprising 254 and 185 nm wavelength efficiently removes the resided organic contaminations on silicon surface by photosensitization and oxidation effects. Besides, considerable hydroxyl incorporations are generated by UV reacting with surface water molecular and silicon dioxide. Thus, appropriate UV exposure will render the silicon surface more hydrophilic and improve bondability. It is concluded that as an additional cleaning and modification treatment, UV exposure is effective and promising to enhanced bond quality in low temperature hydrophilic silicon direct bonding.     

CBERS-02星CCD数据土地利用分类方法研究——以江苏省宜兴地区为例

以江苏省宜兴地区为试验区,首先进行了CBERS-02星CCD数据的图像预处理,然后利用ERDASI-MAGINE和Definiens7.0等软件,采用非监督分类、监督分类、混合监督分类、面向对象四种分类方法进行了土地利用分类,并将影像分类结果进行了精度评价分析。结果表明：在一级地类的提取中,面向对象的最邻近分类器的分类精度最低,混合监督分类的精度最高;在二级地类的提取中,面向对象的特征阈值法得到的分类结果较好,能够轻松提取传统分类方法难于提取的地类。