ID 原文 译文
24975 理论分析和仿真验证结果表明:所提方法处理过程简单，对低信噪比和强冲击噪声情况下的测向性能有很大的改善和提高。 Theoretical analysis and simulation results show that the proposed method has small computational load as well as excellent performance, and can improve the estimation performance at low signal to noise ratio and strong impulsive noise remarkably．
24976 目前的新闻分类研究以英文居多，而且常用的传统机器学习方法在长文本处理方面，存在局部文本块特征提取不完善的问题。 At present, most of the researches on news classification are in English, and the traditional machine learning methods have a problem of incomplete extraction of local text block features in long text processing．
24977 为了解决中文新闻分类缺乏专门术语集的问题，采用构造数据索引的方法，制作了适合中文新闻分类的词汇表，并结合 word2vec 预训练词向量进行文本特征构建。 In order to solve the problem of lack of special term set for Chinese news classification, a vocabulary suitable for Chinese text classification is made by constructing a data index method, and the text feature construction is combined with word2vec pre-trained word vector．
24978 为了解决特征提取不完善的问题，通过改进经典卷积神经网络模型结构，研究不同的卷积和池化操作对分类结果的影响。 In order to solve the problem of incomplete feature extraction, the effects of different convolution and pooling operations on the classification results are studied by improving the structure of classical convolution neural network model．
24979 为提高新闻文本分类的精确率，本文提出并实现了一种组合-卷积神经网络模型，设计了有效的模型正则化和优化方法。 In order to improve the precision of Chinese news text classification, this paper proposes and implements a combined-convolution neural network model, and designs an effective method of model regularization and optimization．
24980 实验结果表明，组合-卷积神经网络模型对中文新闻文本分类的精确率达到 93. 69% ，相比最优的传统机器学习方法和经典卷积神经网络模型精确率分别提升 6. 34% 和 1.19% ，并在召回率和 F 值两项指标上均优于对比模型。 The experimental results show that the precision of the combined-convolutional neural network model for Chinese news text classification reaches 93. 69% , which is 6.34% and 1.19% higher than the best traditional machine learning method and classic convolutional neural network model, and it is better than the comparison model in recall and F-measure．
24981 本文提出了一种基于增材加工工艺的带通频率选择表面设计。 A band-pass frequency selective surface (FSS) design based on additive processing is presented．
24982 传统频率选择表面(Frequency SelectiveSurface，FSS)通常由 PCB(Printed Circuit Board)工艺加工实现，难以与大面积柔性覆盖等场合兼容。 The traditional FSS is usually processed by PCB (Printed Circuit Board) technology, which is difficult to be compatible with large-area flexible coverage．
24983 为此，本文提出了基于丝网印刷与电镀的增材加工方法实现对带通频率选择表面的加工，并通过一种螺旋风车形缝隙结构带通 FSS 设计进行验证。 To this end, this paper proposes an additive processing method based on screen printing and electroplating to realize the processing of the band-pass FSS, and is verified by a design of band-pass FSS with spiral windmill-shaped slot structure．
24984 设计与测试表明，实现的带通 FSS 在 C 波段提供了 6 ～ 8GHz 的通带，带内最小插损 2. 48dB。 The design and experiment show that the realized band-pass FSS provides a pass-band of 6 ～ 8GHz in the C-band, and the minimum insertion loss is about 2.48 dB．