注塑产品动态装配模型的集成知识模型研究

基于MBR(基于模型的推理)技术，建立了注塑模具动态装配结构模型；基于RBR(基于规则的推理)技术，应用面向对象的规则模型(OOR)，建立了动态装配规则的知识表示模型。最后，该文将两种知识表示模型集成，建立了完整的知识模型，为整个系统的后续工作奠定了基础。     

基于神经网络的数控机床位置控制的研究

本文提出了一种新型的神经网络结构的位置控制器，给出了该控制器的学习算法，并进行了数控机床位置伺服系统的仿真实验，结果表明这种控制器性能优越，自适应能力强。     

IC芯片粘片机并联焊头机构的插补算法及误差分析

针对所设计的IC芯片粘片机的并联焊头机构,对其在平面上任意曲线的插补算法进行了分析.利用驱动轴的PVT插补规律和对分式原则对并联焊头机构运动轨迹的插补误差进行了计算,并通过Matlab软件进行了仿真.结果表明, 轨迹的插补误差与插补直线的斜率、所分的段数和焊头机构的位置有关.     

Development and application of a simulation model for reservoir management

The success of irrigation system operation and planning depends on accurate quantification of supply and demand, and an equitable distribution of available water. The ultimate aim of this study was to determine how to meet the irrigation water demands if possible or to minimize the gap between the water supply and the demand. Most of the irrigation literature focuses only on the demand and the distribution aspects of this issue Irrigation projects that receive water from reservoirs, however, can be challenging to manage because the annual fluctuations in available water release from a reservoir can have a considerable impact on the irrigation management strategy. In real‐world situations, the reservoir operating rules guide reservoir operators in making actual water release decisions. This study develops a water balance simulation model for reservoir management, as well as testing it for Kangsabati Reservoir, West Bengal, India. Two rule curves for deciding irrigation water available from the reservoir were generated by taking the average and minimum stage values on a daily basis for a 16‐year period (1988–2003). Maintaining a minimum stage of 120.4 m throughout the year served as another rule to decide the release water available for irrigation. The minimum allowable stage of reservoir corresponding to a particular date of the year can be determined from those reservoir specific rule curves generated for irrigation purposes. The maximum permissible water release/outflow for irrigation from the test reservoir was taken as the volume of water available above the minimum allowable stage corresponding to the selected rule curve. The saturated hydraulic conductivity value (K_S) was calibrated to be 4.31 mm day^?1 for Kangsabati Reservoir.     

Extended Reflexive Ontologies for the Generation of Clinical Recommendations

Decision recommendations are a set of alternative options for clinical decisions (e.g., diagnosis, prognosis, treatment selection, follow-up, and prevention) that are provided to decision makers by knowledge-based Clinical Decision Support Systems (k-CDSS) as aids. We propose to follow a “reasoning over domain” approach for the generation of decision recommendations by gathering and inferring conclusions from production rules. In order to rationalize our approach, we present a specification that will sustain the logic models supported in the knowledge bases we use for persistence. We introduce first the underlying knowledge model and then the necessary extensions that will convey toward the solution of the reported needs. The starting point of our approach is the proposition of Reflexive Ontologies (RO). Here, we go a step further, proposing an extension of RO that includes the handling and reasoning that production rules provide. Our approach speeds up the recommendation generation process.     

基于GPU加速的超精简型编码数据库系统

在数据爆发式增长的今天,特别是通信、金融、互联网等领域产生的大规模数据,在存储和查询方面给业界带来了前所未有的压力.在这种背景下,当前的数据库和数据仓库系统通过对数据进行压缩编码,在节约空间的同时减少了数据表查询时所需的I/O,获得性能上的提升,但大部分系统在面对实际大规模企业数据应用时依然无法在压缩比、导入时间或查询性能上完全满足企业需求.通过基于一定的规则对数据重新进行编码和精简,实现了一种新型超精简型编码的数据库系统HEGA-STORE.采用行列混合存储的架构;提出基于列内和列间规则挖掘和编码的数据导入存储计划;同时在规则挖掘和编码中使用GPU作为协处理器并行处理算法从而提高效率.通过开发编解码原型系统,对大规模网易易信通信记录数据和网易后台日志数据的导入和查询分别进行了测试,并与其他压缩编码算法和数据库、数据仓库产品进行比较.对比实验结果表明,相比同类数据库和数据仓库产品,原型系统拥有极高的压缩比,并且在导入速度和全表扫描查询速度也处于领先地位,同时使用GPU和CPU协作进行数据处理时也能进一步提高系统性能,验证了提出的超精简型编码数据库系统的实际应用价值.     

基于CRF和规则相结合的地理命名实体识别方法

为了识别文本中海量的地理命名信息,以CRF(条件随机场)模型识别为基础,加入制定的规则,来提高CRF模型识别的召回率,从而提高整体的地理命名实体识别效果。通过选取适合的地理命名实体识别的特征模板,验证特征的有效性以及分析CRF模型识别结果中的未识别实体样本,设计针对未识别实体的规则用以修正识别结果。实验表明,对地名和组织名结合规则进行修正后的F值达到了91.61%和85.74%,有了显著提高。     

地下结构震害风险信息融合方法研究

为提高地下结构震害风险判决的科学性和智能化水平,提出一种基于证据理论的地下结构震害风险信息融合方法。在地下结构震害风险智能监测的基础上,根据震害风险融合原理,构建基于智能监测和专家判决的地下结构震害风险融合模型。遵循证据理论的原则和模型规则,构造统一的地下结构震害状态空间和风险概率表达方式,建立风险融合证据框架,确定判决规则,设计风险融合证据模型组件。计算结果表明,该模型能有效提高地下结构震害信息诊断的可信度,充分显示了该融合模型组件的有效性。     

基于显著区域的行人检测算法

针对经典行人检测算法(HOG+SVM algorithm)因滑动窗口滑动次数过多引起的计算量过大问题,提出一种基于显著区域的行人检测算法。把提取的显著度和原图结合得出有效图,实现由整张图像行人检测到局部有效图行人检测的转变;用贝叶斯准则将有效区域和基于协方差的行人检测有机结合,达到在降低计算量的同时提高检测准确率的效果。在公开数据集INRIA上的实验结果表明,该算法降低了计算量,明显改善了误检率。