ID 原文 译文
20165 其次，利用改进后的SE-DenseNet算法对融合后的航班数据集进行自动特征提取； Then, the improved SE-Dense Net algorithm is used to extract feature automatically based on the fused flight data set.
20166 最后，构建Softmax分类器进行航班离港延误等级的预测。 Finally, the softmax classifier is used to predict the delay level of flight.
20167 该文提出的SE-DenseNet结构融合了DenseNet和SENet二者的优势，既能加强深层信息的传递，避免梯度消失，又可以实现特征提取过程中的特征重标定。 The proposed SE-DenseNet, combing the advantages of DenseNet andSENet, can not only enhance the transmission of deep information, avoid the problem of vanishing gradients,but also achieve feature recalibration by the feature extraction process.
20168 实验结果表明，数据融合后，预测准确率较只考虑航班属性提高约1.8%； The results indicate that after datafusion, the accuracy of the model is improved 1.8% than only considering the characteristics of the flight itself.
20169 算法改进后可以有效提升网络性能，模型最终准确率达93.19%。 The improved algorithm can effectively improve the network performance. The final accuracy of the modelreaches 93.19%.
20170 为满足雷达舰船目标识别的高实时性和高泛化性的需求，该文提出了一种基于深度多尺度1维卷积神经网络的目标高分辨1维距离像(HRRP)识别方法。 In order to meet the demand for high real-time and high generalization performance of radar recognition, a radar High Resolution Range Profile (HRRP) recognition method based on deep multi-scale one dimension convolutional neural network is proposed.
20171 针对高分辨1维距离像特征提取难的问题，所提方法通过共享卷积核的权值，使用多尺度的卷积核提取不同精细度的特征，并构造中心损失函数来提高特征的分辨能力。 The multi-scale convolutional layer that can represent the complex features of HRRP is designed based on two features of the convolution kernels which are weight sharing and extraction of different fineness features from different scales, respectively. At last, the center lossfunction is used to improve the separability of features.
20172 实验结果表明，该模型可以显著提高目标在非理想条件下的识别正确率，克服目标姿态角敏感性问题，具有良好的鲁棒性和泛化性。 Experimental results show that the model can greatly improve the accuracy of the target recognition under non-ideal conditions and solve the problem of the target aspect sensitivity, which also has good robustness and generalization performance.
20173 针对5G网络场景下缺乏对资源需求的有效预测而导致的虚拟网络功能(VNF)实时性迁移问题，该文提出一种基于深度信念网络资源需求预测的VNF动态迁移算法。 To solve the problem of real-time migration of Virtual Network Function (VNF) caused by lacking effective prediction in 5G network, a VNF migration algorithm based on deep belief network prediction of resource requirements is proposed.
20174 该算法首先建立综合带宽开销和迁移代价的系统总开销模型，然后设计基于在线学习的深度信念网络预测算法预测未来时刻的资源需求情况，在此基础上采用自适应学习率并引入多任务学习模式优化预测模型， The algorithm builds firstly a system cost evaluation model integrating bandwidth cost and migration cost, and then designs a deep belief network prediction algorithm based on online learning which adopts adaptive learning rate and introduces multi-task learning mode to predict future resource requirements.