ID	原文	译文
1253	通过 PKU-SVD-B 测试集对训练出来的模型进行测试实验，并在 UMN 数据集上与几种方法做了对比实验，验证了本文提出的基于深度学习的异常事件检测算法，	Test the trained model with PKU-SVD-B test set, compared with vari-ous methods on the UMN datasets, and verify the algorithm of abnormal event detection based on deep learning proposed in this paper.
1254	在适应多种不同场景的前提下，对多种异常事件检测的准确率很高，表明训练出来的模型对异常事件检测具有极强的泛化能力。	Under the premise of adapting to different scenarios, various abnormal events are detected. The high accuracy rateindicates that the trained model has strong ability to generalize abnormal event detection.
1255	现有的基于深度学习的文本分类方法没有考虑文本特征的重要性和特征之间的关联关系，影响了分类的准确率。	The existing text classification methods based on deep learning do not consider the importance and associa-tion of text features.
1256	针对此问题，本文提出一种基于高效用神经网络(High Utility Neural Networks，HUNN)的文本分类模型，可以有效地表示文本特征的重要性及其关联关系。	The association between the text features perhaps affects the accuracy of the classification. To solve thisproblem, in this study, a framework based on high utility neural networks (HUNN)for text classification were proposed. Which can effectively mine the importance of text features and their association.
1257	利用高效用项集挖掘(Mining High Utility Itemsets，MHUI)算法获取数据集中各个特征的重要性以及共现频率。	Mining high utility itemsets(MHUI)fromdatabases is an emerging topic in data mining. It can mine the importance and the co-occurrence frequency of each feature inthe dataset.
1258	其中，共现频率在一定程度上反映了特征之间的关联关系。	The co-occurrence frequency of the feature reflects the association between the text features.
1259	将 MHUI 作为HUNN 的挖掘层，用于挖掘每个类别数据中重要性和关联性强的文本特征。	Using MHUI as themining layer of HUNN, it is used to mine strong importance and association text features in each type, select these text fea-tures as input to the neural networks.
1260	然后将这些特征作为神经网络的输入，再经过卷积层进一步提炼类别表达能力更强的高层次文本特征，从而提高模型分类的准确率。	And then acquire the high-level features with strong ability of categorical representationthrough the convolution layer for improving the accuracy of model classification.
1261	通过在 6 个公开的基准数据集上进行实验分析，提出的算法优于卷积神经网络(Convolutional Neural Networks，CNN)，循环神经网络(RecurrentNeural Networks，RNN)，循环卷积神经网络(Recurrent Convolutional Neural Networks，RCNN)，快速文本分类(Fast TextClassifier，FAST)，分层注意力网络(Hierarchical Attention Networks，HAN)等 5 个基准算法。	The experimental results showed that the proposed model performed significantly better on six different public datasets compared with convolutional neural networks(CNN), recurrent neural networks (RNN), recurrent convolutional neural networks (RCNN), fast text classifier (FAST), and hierarchical attention networks (HAN).
1262	现有谱峰搜索算法在应用于连续毫米波雷达后端中频信号处理时，或计算量较大，或精度不高。	Aiming at the problems existing in the application of existing peak search algorithm to back-end IF(Inter-mediate Frequency)signal processing of continuous millimeter wave radar, such as heavy computation, low precision,