Effective naive Bayes nearest neighbor based image classification on GPU

Non-parametric classifier, Naive Bayes nearest neighbor, is designed with no training phase, and its performance outperforms many well-trained learning-based image classifiers. Unfortunately, despite its high accuracy, it suffers from great computational pressure from distance computations in space of local feature. This paper explores accelerating strategies from perspectives of both algorithm design and software development. Our approach integrates space decomposition capability of Product quantization (PQ) and parallel accelerating capability of underlying computational platform, Graphics processing unit (GPU). PQ is exploited to compress the indexed local features and prune the search space. GPU is used to ease most of computational pressure by processing the tasks in parallel. To achieve good parallel efficiency, a new sequential classification process is first designed and decomposed into independent components with high parallelism. Effective parallelization techniques are then presented to make use of computational resources. Parallel heap array is built to accelerate the process of feature quantization. Distance table lookup is built to speed up the process of feature search. Comparative experiments on UIUC-Sport dataset demonstrate that our integrated solution outperforms other implementations significantly on Core-quad Intel Core i7 950 CPU and GPU of NVIDIA Geforce GTX460. Scalability experiment on 80 million tiny images database shows that our approach still performs well when large-scale image database is explored.     

A GPU-based parallel method for evolutionary tree construction

Evolutionary trees are widely applied in various applications to show the inferred evolutionary relationships among species or entities. Neighbor-Joining is one solution for data-intensive and time-consuming evolutionary tree construction, with polynomial time complexity. However, its performance becomes poorer with the growth of massive datasets. Graphics Processing Units (GPUs) have brought about new opportunities for these time-consuming applications. Based on its high efficiency, a GPU-based parallel Neighbor-Joining method is proposed, and two efficient parallel mechanisms, data segmentation with asynchronous processing and the minimal chain model with bitonic sort, are put forward to speed up the processing. The experimental results show that an average speedup of 25.1 is achieved and even approximately 30 can be obtained with a sequence dataset ranging from 16,000 to 25,000. Moreover, the proposed parallel mechanisms can be effectively exploited in some other high performance applications.     

矿用多协议嵌入式网关设计

针对目前煤矿中异构网络之间通信困难、信息融合不便、监测监控信息不能及时传送等问题,本文设计实现了一种矿井多协议嵌入式网关。该网关基于uC/OS-Ⅱ嵌入式操作系统,移植LwIP网络协议实现RS232、RS485、CAN和以太网之间的协议转换;硬件核心采用ST公司STM32F107,该芯片以ARM Cortex-M3内核,集成各种高性能工业标准接口,更适应于高性能、低成本、低功耗的嵌入式应用。     

Dynamic equivalent method of interconnected power systems with consideration of motor loads

The existing equivalent methods usually only deal with static load models and neglect the dynamic characteristics of loads such as induction motors.This paper presents a dynamic equivalent method which considers motor dynamics.At first,the clustering criterion of motor loads is given.The motors with similar dynamic characteristics are classified into one group.Then,reduction of motors in the same group is carried out.Finally,parameters of the equivalent motor are calculated and the equivalent system is thus...     

发电系统短期可靠性评估的等效机组法

本文提出了等效机组的概念,有效地解决了发电系统短期可靠性评估中的“状态爆炸”难题该方法不仅提高了短期可靠性评估的速度和精度,而且极大地压缩了计算存贮量,使发电系统短期可靠性评估更趋于实用化.通过对示例发电系统进行短期可靠性评估,其结果证明了该方法的正确性和有效性.     

基于微分方程数值分析的机械臂运动参数挖掘模型

在目前的运动参数挖掘模型中,通常采用差异化运动原理对运动过程进行分析,缺乏实际的公式支持,在进行参数挖掘时影响性能。因此,提出基于微分方程数值分析的机械臂运动参数挖掘模型研究。首先利用微分方程数值分析的方式来对机械臂的运动过程进行模拟,列举出其中的动态特性参数。依据动态特征参数,利用神经元网络对其中的运动参数属性进行特征提取。获得运动特征后,使用贝叶斯原理进行深入的运动参数挖掘。为了验证设计的运动参数模型性能,设计仿真实验,设定模拟机械臂,并使用设计模型与文献[3]、文献[5]、文献[13]中的参数挖掘模型进行运动参数挖掘,并对比性能的优劣性。实验结果证明,设计的运动参数挖掘模型具有较高的运算速度、实时性以及准确率,证明设计的运动参数挖掘模型具有较高的性能,满足设计初衷。     

基于跨语言神经主题模型的汉越新闻话题发现方法

针对汉越跨语言新闻话题发现任务中汉越平行语料稀缺,训练高质量的双语词嵌入较为困难,而且新闻文本一般较长导致双语词嵌入的方法难以很好地表征文本的问题,提出一种基于跨语言神经主题模型（CL-NTM）的汉越新闻话题发现方法,利用新闻的主题信息对新闻文本进行表征,将双语语义对齐转化为双语主题对齐任务。首先,针对汉语和越南语分别训练基于变分自编码器的神经主题模型,从而得到单语的主题抽象表征;然后,利用小规模的平行语料将双语主题映射到同一语义空间;最后,使用K-means方法对双语主题表征进行聚类,从而发现新闻事件簇的话题。实验结果表明,所提方法相较于面向中英文的隐狄利克雷分配主题改进模型（ICE-LDA）在Macro-F1值与主题一致性上分别提升了4个百分点与7个百分点,可见所提方法可有效提升新闻话题的聚类效果与话题可解释性。     

多平台数据容灾系统的研究与设计*

基于对Windows和Linux平台卷管理系统的特性分析,提出一种基于卷复制的数据容灾系统模型,并论述了其系统结构、工作原理以及关键技术.该系统的主要特点是采用模块嵌入技术实现系统与平台的有机结合,同时支持多种复制模式以保证数据的一致性,通过加密、压缩传输以提高数据安全性并降低带宽要求,另外提供灾难恢复机制,保证了主数据系统在遭受灾难的情况下可以方便地迁移和回迁.理论和实验均证明,本数据容灾系统较好地保证了数据可靠性和可用性.     

一种基于节点位置和密度的非均匀分簇路由算法

分析了现有分簇路由算法,提出了基于节点位置和密度的非均匀分簇路由算法。簇头选举阶段,考虑了节点的剩余能量,并引入竞争机制进行簇头选择;成簇阶段,综合考虑节点与基站的距离、节点密度以进行非均匀分簇,达到节点能耗均衡的效果,同时解决路由热区问题;簇间路由阶段,通过设立通信簇头节点,使簇间数据转发任务从簇头中分离,簇头节点只负责簇内的数据收集和融合,而通信簇头节点负责簇间数据传输,减少了簇头的能量消耗。实验结果表明,改进后的路由算法能够有效地均衡网络负载,并显著地延长网络的生命周期。     

基于预分类的逆变异分类器算法

遗传算法已经在许多领域得到了成功的应用,在解决模式识别问题时,由于遗传中的变异过程的存在导致了模式差异,如果能够减少这种差异性,就可以提高模式分类的正确率。针对这种情况,本文提出了在预分类基础上的一种逆变异算法,该算法采用遗传算法中变异过程的逆过程,来减少模式的差异性,达到提高模式分类正确率的目的。在ORL人脸库上的实验结果表明,该分类器的模式识别率明显高于传统的分类器算法及遗传算法。