We introduce a model to implement incremental update of views. The principle is that unless a view is accessed, the modification related to the view is not computed. This modification information is used only when vie...We introduce a model to implement incremental update of views. The principle is that unless a view is accessed, the modification related to the view is not computed. This modification information is used only when views are updated. Modification information is embodied in the classes (including inheritance classes and nesting classes) that derive the view. We establish a modify list consisted of tuples (one tuple for each view which is related to the class) to implement view update. A method is used to keep views from re-update. Key words object-oriented database - incremental computation - view-computation - engineering information system CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China(60235025)Biography: Guo Hai-ying (1971-), female, Ph. D, research direction: CAD and engineering information system.展开更多
针对深度学习模型易出现灾难性遗忘的关键难点,提出了一种基于原型对比的合成孔径雷达(synthetic aperture radar,SAR)图像增量小样本目标检测算法-InFSAR(prototype contrast based incremental few-shot SAR object detection)。首先...针对深度学习模型易出现灾难性遗忘的关键难点,提出了一种基于原型对比的合成孔径雷达(synthetic aperture radar,SAR)图像增量小样本目标检测算法-InFSAR(prototype contrast based incremental few-shot SAR object detection)。首先,采用基础数据集对检测器进行预训练,以构建初步的特征提取能力;其次,设计一种类原型表征生成模块,以构建一组能够代表数据内在特征的类原型。在增量学习阶段,设计一种混合类原型对比编码模块,以有效学习新类别与基础类别之间的区分性特征。此外,为缓解灾难性遗忘问题,引入类原型校准策略,使模型在类原型上的预测分布逐步逼近真实分布,从而保持对基础类别识别的稳定性。在小样本目标检测数据集SRSDD-v1.0上的实验结果表明,在5-shot设置下,InFSAR对船舶细粒度目标的检测精度达到46.5%。同时,该方法能够在无需访问基础类训练数据的情况下,实现对少量标注新类别的增量检测与识别。展开更多
文摘We introduce a model to implement incremental update of views. The principle is that unless a view is accessed, the modification related to the view is not computed. This modification information is used only when views are updated. Modification information is embodied in the classes (including inheritance classes and nesting classes) that derive the view. We establish a modify list consisted of tuples (one tuple for each view which is related to the class) to implement view update. A method is used to keep views from re-update. Key words object-oriented database - incremental computation - view-computation - engineering information system CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China(60235025)Biography: Guo Hai-ying (1971-), female, Ph. D, research direction: CAD and engineering information system.
文摘针对深度学习模型易出现灾难性遗忘的关键难点,提出了一种基于原型对比的合成孔径雷达(synthetic aperture radar,SAR)图像增量小样本目标检测算法-InFSAR(prototype contrast based incremental few-shot SAR object detection)。首先,采用基础数据集对检测器进行预训练,以构建初步的特征提取能力;其次,设计一种类原型表征生成模块,以构建一组能够代表数据内在特征的类原型。在增量学习阶段,设计一种混合类原型对比编码模块,以有效学习新类别与基础类别之间的区分性特征。此外,为缓解灾难性遗忘问题,引入类原型校准策略,使模型在类原型上的预测分布逐步逼近真实分布,从而保持对基础类别识别的稳定性。在小样本目标检测数据集SRSDD-v1.0上的实验结果表明,在5-shot设置下,InFSAR对船舶细粒度目标的检测精度达到46.5%。同时,该方法能够在无需访问基础类训练数据的情况下,实现对少量标注新类别的增量检测与识别。
文摘为提高双点渐进成形(double-side incremental sheet forming,DSIF)制件的成形精度,以方锥盒制件作为试验制件,以刀具直径、层间距、成形角、板厚和成形深度等工艺参数为影响因素,以底部回弹值和侧壁鼓凸最小值作为优化目标设计正交试验,利用Abaqus数值仿真计算出试验结果数据,通过建立多输入和多输出的BP(back propagation)神经网络预测模型,结合带精英策略的非支配排序遗传算法(non-dominated sorting genetic algorithm,NAGA-Ⅱ)求解双点渐进成形工艺参数多目标优化问题,基于熵权逼近理想解排序法(technique for order preference by similarity to ideal solution,TOPSIS)从Pareto解集中决策出一组最优工艺参数组合以提高优化结果的精确度,通过优化和筛选得到的最佳工艺参数组合进行对应试验。结果表明,经实测得到制件的底部回弹值为0.693 mm,侧壁鼓凸值为0.934 mm,筛选出的目标值误差分别为6.31%和2.09%。由此可见,建立的多目标优化流程具有可行性,为双点渐进成形制件的回弹减少提供了有效的优化方案。
