异构分类器融合环境下的非平衡数据分类模型

为解决非平衡数据分类中的正样本分类精度不高的瓶颈问题,提出了一种异构分类器融合环境下的非平衡数据分类模型.该模型基于差异采样率的重采样算法和改进的Adaboost算法,融合了SVM和C5.0两种基分类器;基于知识融合机制,采用了独特的分类器选择策略、分类器集成方法、分类决策方案.仿真实验结果表明,SCECM模型分类性能...     

基于核超限学习机的中文文本情感分类

针对传统情感分类算法存在的参数学习困难及分类性能较低等问题,提出了一种基于核超限学习机的中文文本情感分类方法.首先通过信息增益对训练数据进行特征选择以降低输入维数,然后通过构建基于小波核超限学习机的分类器实现对中文文本的情感分类.实验结果表明,新方法参数学习容易,且其文本情感分类性能通常优于支持向量机和朴素贝叶斯.     

基于协同采样主动学习的恶意代码检测

研究了基于机器学习分类算法的恶意代码检测,考虑到目前主要采用传统分类方法对恶意代码进行分类识别,这些方法需要通过学习大量标记样本来获得精准的分类器模型,然而样本标记工作只有少数专家才能完成,导致标记样本往往不足,致使分类结果准确率不高,提出了一种基于协同采样的主动学习方法。运用这种学习方法,仅需少量标记样本即可有效识别出恶意代码。实验证明,相对于传统的恶意代码分类方法,该方法能够显著提升分类准确率和泛化性能。     

基于支持向量机的步态分类方法

针对小样本步态数据引起的分类器泛化能力差的问题,提出了基于支持向量机的步态分类方法.采集了24名青年和24名老年受试者的步态数据,提取24个步态特征训练支持向量机,采用交叉验证方法评估分类器的泛化性能.结果表明,本文提出的方法能够有效地对小样本步态数据分类,并且具有良好的泛化性.不同的核函数对分类性能影响较小.与传统反向传播学习算法的神经网络分类器进行了比较,支持向量机分类性能明显优于传统反向传播学习算法的神经网络.支持向量机在步态分类中具有广泛的应用前景.     

基于TSVM与主动学习融合的蛋白质交互作用关系抽取

针对蛋白质交互作用关系(PPI)抽取研究中已标注语料有限而未标注生物医学自由文本易得的问题,进行了基于直推式支持向量机(TSVM)与主动学习融合的蛋白质交互作用关系抽取研究.通过自主选择最优的未标注样本加入到TSVM的训练过程中,最大程度地提高了系统的性能.实验结果表明,TSVM与主动学习融合的算法在少量已标注样本和大量未标注样本组成的混合样本集上取得了较好的学习效果,与传统的支持向量机(SVM)和TSVM算法相比,能有效地减少学习样本数,提高分类精度,在AImed语料上取得了F测度为64.12%的较好性能.     

基于在线半监督学习的故障诊断方法研究

针对机械故障诊断中准确、完备的故障训练样本获取困难,而现有分类方法难以有效地发掘大量未标记故障样本中蕴含的有用信息,提出了一种基于在线半监督学习的故障诊断方法.该方法基于Tri-training算法将在线贯序极限学习机从监督学习模式扩展到半监督学习模式,利用少量不精确的标记样本构建初始分类器,并从大量未标记样本中在线扩充标记样本,对分类器进行增量式更新以提高其泛化性能.半监督基准数据试验结果表明,训练样本总数相同但标记样本数与未标记样本数比例不同时,所提算法得到的分类准确率相当且训练时间相差小于1.2倍.以柴油机8种工况的故障模式为对象进行试验验证,结果表明标记故障样本较少时,未标记故障样本的加入可使故障分类准确率提高5％～8％.     

基于小波包变换和随机森林算法的光伏系统故障分类

针对光伏系统故障分类问题,提出一种小波包变换和随机森林算法相结合的故障分类方法。采集光伏系统的故障电压数据,利用小波包变换对电压信号进行分解,提取各频带能量作为故障特征,将特征样本送入随机森林算法中进行分类。随机森林算法是结合集成学习理论和随机子空间方法的一种算法,可以对多种故障做出准确分类。使用PSCAD/EMTDC搭建独立光伏发电系统,选取12种故障进行模拟,得到600个故障样本,选取其中360个样本用于训练分类器,240个样本用于测试分类器的分类性能。仿真结果表明:该方法可有效辨别光伏系统的12种故障,分类准确率达到97.92%。与RBF神经网络分类器相比,故障分类准确率提高了4.17%,对进一步实现光伏系统故障诊断研究具有重要意义。     

基于LSSVM的磁瓦表面瑕疵偏向性分类

针对磁瓦表面缺陷检测方法分类准确率低的问题,提出一种基于LSSVM技术的瑕疵偏向性分类方法。构造5个尺度8个方向Gabor滤波器组,提取经过Gabor变换后生成的40副子图的均值与方差为磁瓦图像特征。采用耦合模拟退火算法初步寻优,在所得初步参数的邻域使用网格算法进行精细搜索。为实现对缺陷磁瓦的偏向性预测分类,改进了虚拟少数类过采样算法。去除原始训练样本中的噪声样本数据,再在瑕疵边界样本与合格样本之间过采样。实验结果表明,最小二乘支持向量机分类器模型训练时参数寻优时间明显缩短,整体分类正确率达到95.56%,偏向性分类正确率达到99.09%,实现对缺陷磁瓦的偏向性分类。     

基于改进判别字典学习的故障诊断方法

近年来,基于稀疏表示的分类技术在模式识别中取得一定的成功。该框架中,字典的学习和分类器的训练通常是两个独立的模块,降低了方法的识别精度。针对以上问题,提出了一种特征提取和模式识别相融合的改进判别字典学习模型,将重构误差项、稀疏编码判别项及分类误差项进行了整合,并用K奇异值分解算法对目标函数进行优化,实现了字典和分类器的同步学习。该方法先对原始信号进行经验模态分解,并从分解的本征模态函数中提取时、频特征,形成故障样本;然后将训练样本输入改进模型用K奇异值分解优化;最后用习得字典及分类器权重对测试样本进行识别。实验结果表明：该算法不但适用于小样本故障问题,而且鲁棒性和分类性能都明显高于其它算法。         

基于多视角二维主动学习的多标签分类

针对多标签图像分类问题的特点,提出了一种多视角二维主动学习(MV-2DAL)算法,以通过多视角学习与主动学习的有机结合,深入挖掘样本、标签、视角三个维度上的相关性和冗余性.此算法以样本-标签对作为基本标注单位,在每个视角内,利用二维主动学习的方法计算样本、标签维度上的不确定度;在不同视角间,通过多视角融合的方法计算跨视...     

Insertion of triangulated surfaces into a meccano tetrahedral discretization by means of mesh refinement and optimization procedures

In this paper, we present a new method for inserting several triangulated surfaces into an existing tetrahedral mesh generated by the meccano method. The result is a conformal mesh where each inserted surface is approximated by a set of faces of the final tetrahedral mesh. First, the tetrahedral mesh is refined around the inserted surfaces to capture their geometric features. Second, each immersed surface is approximated by a set of faces from the tetrahedral mesh. Third, following a novel approach, the nodes of the approximated surfaces are mapped to the corresponding immersed surface. Fourth, we untangle and smooth the mesh by optimizing a regularized shape distortion measure for tetrahedral elements in which we move all the nodes of the mesh, restricting the movement of the edge and surface nodes along the corresponding entity they belong to. The refining process allows approximating the immersed surface for any initial meccano tetrahedral mesh. Moreover, the proposed projection method avoids computational expensive geometric projections. Finally, the applied simultaneous untangling and smoothing process delivers a high‐quality mesh and ensures that the immersed surfaces are interpolated. Several examples are presented to assess the properties of the proposed method.     

Certification Institutions Expected to Update and Transfer Information on Present Standards

Standards are the basis for production enterprises to organize production, ex-factory inspection, trade (delivery) and technical exchanges, product certification, quality arbitration and supervision.……     

Flow calorimeter for enthalpy increment measurements on condensed gases

A flow calorimeter for enthalpy increment measurements on condensed gases is presented. A better knowledge of the properties of the liquefied natural gas is needed, and therefore a liquid loop has been designed for our flow calorimeter. The fluid loop in the calorimeter is designed in order to avoid the two-phase region, since two phases would give compositional disturbances in the measurements. The avoidance of the two-phase region is made possible by increasing the pressure of the test fluid after the measurement section, then heating the fluid at super-critical pressure past the critical point. Finally, the fluid is throttled to the low-pressure gas state at the inlet condition of the compressor that circulates the fluid. To perform the pressure increase, a new cryogenic pump has been designed. To evaluate the new equipment, measurements were taken on liquid ethane over the temperature range 146–256 K at pressure between 0.9 and 5.1 MPa.     

Refrigerators Enter a New Era of Health Preservation Frestech initiates the establishment of China's first standard for household sterilization refrigerators

On November 30, 2007, the China Association for Standardization (CAS) held a press conference at Beijing Diaoyutai State Guest House. Leaders from the China Household Electric Appliance Research Institute, the China Household Electric Appliance Association, and the China Consumers' Association attended and made speeches.……     

Optimum-Simulation von Ernteprozessen

Zusammenfassung Bei der Gestaltung von Ernteprozessen — beispielsweise des Prozesses Mähdrusch, Körnertransport und -abnahme — als transportverbundene Fließarbeitsverfahren mit mindestens zwei verschiedenen Arbeitsmitteln gibt es einen großen Optimierungsspielraum. Solche Prozesse sind mehrstufige Bedienungsprozesse mit gemischter Anordnung der Bedienungseinrichtungen. Außerdem besitzen sie stark ausgeprägte räumliche Aspekte. Es wird vor allem gezeigt, welche Merkmale solcher Prozesse in Simulationsmodellen abgebildet sein müssen, welche Zielgrößen in Abhängigkeit von welchen Einflußgrößen unter Berücksichtigung welcher Prozeßbedingungen ermittelt werden sollten und wie der Bewertungsprozeß zur Ermittlung der gewünschten Informationen gestaltet werden muß.     

A study of centrifugal cast high boron high speed steel

In the present study a high‐boron high speed steel (HSS) roll material was designed. Many expensive alloy elements have been substituted by cheap boron alloy, and high‐boron high speed steel roll has been manufactured by centrifugal casting method. The microstructures, mechanical properties and wear resistance of centrifugal casting high‐boron high speed steel roll have been investigated by optical microscopy (OM), scanning electron microscopy (SEM), and X‐ray diffraction (XRD) analysis, hardness test, impact test and wear test. The results indicated that the solidification microstructures of high‐boron high speed steel roll consisted of M₂(B,C), (W,Mo)₂(B,C), M₃(B,C), M₂₃(B,C)₆ type borocarbides and martensite, a small amount of retained austenite. Borocarbides were continuously distributed over the grain boundary. After quenching from 1050 °C, local broken network appeared in partial borocarbides, and fine secondary borocarbide precipitated from the matrix. After tempering from 525 °C, the amount of precipitated borocarbide increased significantly. After heat treatment, the hardness of high‐boron high speed steel roll excelled 60 HRC, and its impact toughness excelled 8.0 J/cm². The single groove steel rolling amount of high‐boron high speed steel rolls increases by 500% than that of bainite cast iron roll, when the rolls are used in K₁ mill housing of bar mill.     

Thixotropy of Systems with Shear Thinning and Plastic Flow Behavior

The definition of the thixotropy is a decrease in viscosity with time in shear and a subsequent recovery of viscosity after the shear deformation is removed.We ...     

Effect of Oxide Assisted Metal Nanoparticles on Microstructure and Morphology of Gallium oxide Nanowires

Several researches have been reported about the characteristic of β-Ga2O3 nanowires which was synthesized on nickel oxide particle. But indeed, recent researches about synthesis of β-Ga2O3 nanowires on oxide-assisted transition metal are limited to nickel or cobalt oxide catalyst. In this work, Gallium oxide (β-Ga2O3 ) nanowires were synthesized by a simple thermal evaporation method from gallium powder in the range of 700 - 1000℃ using the iron, nickel, copper, cobalt and zinc oxide as a catalyst, respectively. The β-Ga2O3 nanowires with single crystalline without defects were successfully synthesized at the reaction temperature of 850, 900 and 950℃ in all the catalysts. But optimum experimental condition in synthesis of nanowires varied with the kind of catalyst. As increasing synthesis temperature,the morphology of gallium oxide nanowires changed from nanowires to nanorods, and its diameter increased. From these results, we could be proposed that the growth mechanism of β-Ga2O3 nanowires was changed with synthesis temperature of nanowires. Microstructure and morphology of Synthesized nanowire was characterized by HR-TEM, FE-SEM, EDX and XRD.     

Brainstorming for ISO Strategy 2016-2020

正Responding to ISO’s appeal for survey for the to-be-developed ISO Strategy Plan for 2016-2020,SAC hosted a special workshop over the needs and comments of various fi elds on June 8 in Beijing.The workshop was attended by ISO President-elect and Ansteel General Manager Zhang Xiaogang,SAC Vice-Administrator Yu Xinli,and 30 experts from