ID 原文 译文
24775 Er的脉冲幅值、半峰值宽度、脉冲宽度、过零幅度均随σ增大而减小，σ≤2.5×10-3S/m时尤为明显； The pulse amplitude, half peak width, pulse width and the zero-crossing amplitude of Er attenuate with the increase of σ, especially in the range of σ≤2. 5×10-3S/m.
24776 v 对 Er的影响随距离增大明显增强，100m 以外的脉冲幅值和 10km 以外的过零幅度随 v 增大有明显提高。 The influence of v on Er increase significantly as return-stroke distance increases. The pulse amplitude of Er increase significantly with the increase of v when r >100m, and the effect of v on the zero-crossing amplitude of Er reflects the similar law when r >10km.
24777 针对目前一些正确识别率高的 SVM（Support Vector Machines）分类器、超球 SVM 分类器、深度学习分类器在一些典型样本集上应用时仍然有2%左右的错误识别率和增量学习功能不强的问题，本文提出了一种具有合适拒识机制的高正确识别率分类器设计方案和相应的增量学习算法，较好地解决了上述问题。 At present, some SVM (Support Vector Machines) classifiers, hypersphere SVM classifier and deep learning classifier with high correct recognition rate still have about 2% false recognition rate and weak incremental learning function. In this paper, a high correct recognition rate classifier designed with appropriate rejection mechanism and incremental learning algorithm is proposed to solve the above problems.
24778 主要工作包括：同类特征集合的紧密包裹集构造算法； The main work include: the construction algorithm of compact packing set of homogeneous feature set;
24779 基于同类特征集合和紧密包裹集的同类特征区域紧密包裹面的求解算法； the algorithm for solving the compact packing surface of homogeneous feature region based on homogeneous feature set and compact packing set;
24780 设置所有紧密包裹面之外的公共区域为分类器的拒识区域的方法； the method of setting all the public areas outside the compact packing surface as the rejection area of the classifier;
24781 当增加新类别、增减训练样本时，以上算法的增量学习算法。 when adding new categories, increasing or decreasing training samples, the above algorithms are incremental learning algorithms.
24782 用 uci数据集做对比实验表明，在拒识率小于1.3%的情况下，本文方法设计的分类器正确识别率大于99.13%。 A comparison experiment with uci data sets shows that the correct recognition rate of the classifier is greater than 99.13%, when the rejection rate is less than 1.3%.
24783 聚类集成旨在通过融合多个不同的基聚类结果得到一个统一的类簇划分。 The purpose of clustering ensemble is to find a unified partition of objects by fusing a set of clustering results.
24784 针对现实环境中的模糊和不确定性数据，本文提出了一种基于阴影集的多粒度三支聚类集成算法。 This paper proposes a multi-granulation three-way clustering ensemble algorithm based on shadowed sets to deal with the fuzzy and uncertainty data in the actual world.