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.     

Point-based online value iteration algorithm in large POMDP

Partially observable Markov decision process (POMDP) is an ideal framework for sequential decision-making under uncertainty in stochastic domains. However, it is notoriously computationally intractable to solving POMDP in real-time system. In order to address this problem, this paper proposes a point-based online value iteration (PBOVI) algorithm which involves performing value backup at specific reachable belief points, rather than over the entire belief simplex, to speed up computation processes, exploits branch-and-bound pruning approach to prune the AND/OR tree of belief states online, and proposes a novel idea to reuse the belief states that have been searched to avoid repeated computation. The experiment and simulation results show that the proposed algorithm can simultaneously satisfy the requirement of low errors and high timeliness in real-time system.     

不同载体钯催化剂的结构表征及其在笼形叔胺脱N-苄基上的应用

以γ Al2O3、木质活性炭、煤质活性炭为载体,以氯化钯为前体制备了Pd(OH)2/Al2O3、Pd(OH)2/C催化剂,并用X射线衍射、透射电镜和X射线光电子能谱等技术对这些催化剂进行了结构表征。以六苄基六氮杂异伍兹烷(HBIW)的脱苄反应为例,研究了不同载体Pd(OH)2催化剂对笼形叔胺N 苄基脱苄反应的活性,分析了影响催化剂活性的各种因素。实验结果表明,当催化剂用量为HBIW质量的0 2%(以Pd计)时,氢解产品四乙酰基二苄基六氮杂异伍兹烷(TADBIW)的收率可达88%,其中以煤质活性炭为载体的催化剂已用于HBIW氢解脱苄的20kg级放大实验,TADBIW产品收率为82%。     

Mechanical properties and thermal stability of double‐shell thermal‐energy‐storage microcapsules

Double‐shell‐structured microcapsules encapsulating phase‐change materials (micro‐PCMs) with an average diameter of 5–10 μm were successfully fabricated with a melamine–formaldehyde resin as the coating material. The mechanical properties of the obtained piled micro‐PCMs, tested under compression, were evaluated with a pressure sensor. Typical stress–strain curves showed that both the single‐shell‐ and double‐shell‐structured microcapsules had yield points and maximum point pressures. The morphological changes in the shell surface confirmed the existence of yield points by scanning electron microscopy. When the pressure was beyond the yield point, the microcapsules showed conventional plastic behavior, and the double‐shell structure was more mechanically stable than the single‐shell one. Differential scanning calorimetry analysis results revealed that the properties of the phase‐change materials experienced no variation after coating with a single‐shell‐ or double‐shell‐structured polymer. Thermogravimetric analysis showed that the double‐shell‐structured micro‐PCMs experienced a weight loss of only about 5% from 86.3 to 232°C but did so more rapidly from 232 to 416°C. Thermoregulation was determined with periodical heating and cooling tests. The data showed that the micro‐PCMs changed temperature in a narrow range of 20–25°C with a time lag of 20 min to reach the maximum or minimum temperature in comparison with a reference temperature of 18–28°C. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 103: 1295–1302, 2007     

玉米芯木聚糖硫酸酯化条件的研究

用碱提法从玉米芯中提取木聚糖,采用氯磺酸吡啶法进行硫酸酯化,通过正交试验确定最佳工艺条件为:吡啶与氯磺酸摩尔比1∶1,温度65℃,时间6h;木聚糖硫酸酯wisX-S通过DEAESepharoseFF层析柱分离得到一个相对分子量为1.3×104的组分,硫酸基取代度为2.24。对此木聚糖硫酸酯进行红外光谱分析,结果显示在波数1259、1228和813cm-1处分别有S=O和C-O-S键的特征吸收峰。     

勃劳特换热器的性能

勃劳特换热器的性能周绪美，陈建铭，张鹏远，冯元鼎，丁华（北京化工大学化学工程系）关键词勃劳特换热器；压降１引言在生产过程中，气体与气体之间进行热量交换的换热器，在性能评比时，应该用两项指标来衡量。其一是单位产品所需传热面积要小，其二是单位压降的传热膜...     

1，1，3-三甲基-3-苯基茚满的催化合成木

本文研究了在酸性离子液体的催化作用下α-甲基苯乙烯二聚合成1,1,3-三甲基-3-苯基茚满。实验结果表明,在无溶剂的条件下室温离子液体（CH3CH2）3NHCl-AlCl3对该反应具有很高的催化活性和目标产物的选择性,反应进行到5min即可达到100%的α-甲基苯乙烯转化率和97%的环状二聚物1,1,3-三甲基-3-苯基茚满的选择性。     

基于主动轮廓的声呐图像水雷识别方法

针对声呐图像具有噪声大、目标边缘模糊等特点,提出了一种基于主动轮廓的声呐图像水雷目标识别方法.首先根据水雷目标在声呐图像中的形状特征,采用水平集思想,得到了引入超椭圆形状约束的水平集函数;然后根据水雷目标在声呐图像中的灰度特征,采用Chan-Vese模型的演化思想,提出了一种基于超椭圆形状约束的多相水平集主动轮廓模型.将该模型用于声呐图像水雷目标的识别实验,实验结果表明,该方法对声呐图像中的水雷目标具有很好的识别效果,而且具有抗噪性和抗变形性能.     

一种支持服务关联的Web服务选择方法

目前存在的大多数基于QoS(quality of service)的Web服务选择方案都忽略了服务之间的关联关系, 认为服务之间是相互独立的, 使得组合服务的结果与实际有所偏差。为了提高组合Web服务QoS的精确性, 考虑到服务之间的关联关系对组合服务质量的影响, 分别对服务之间的接口关联、业务关联和统计关联三种关联关系进行研究, 提出了一种基于关联度的关联服务集合发现方法, 将支持服务关联的选择问题转换为混合整数规划模型进行求解。实验结果表明, 考虑服务之间的关联关系会提高组合Web服务的质量。