ID 原文 译文
53587 基于导航卫星的星-地双基地 SAＲ( GNSS-BSAＲ) 作为一种新型的地表观测手段，具有重访时间短、覆盖范围广、系统成本低等显著优势。 Space-Surface bistatic SAＲ based on global navigation satellite system ( GNSS-BSAＲ) , as a new type of surface observation method, has significant advantages such as short revisit time, wide coverage, and low system cost.
53588 当地面接收机与目标场景距离较近时，由于 GNSS-BSAＲ 的分辨率较低，导致目标场景的成像结果与其在同一等距离线上的镜像混叠在一起，无法进行图像解译和形变反演处理。 When the ground receiver is close to the target scene, due to the low resolution of GNSS-BSAＲ, the imaging result of the target scene is mixed with the mirror image on the same equidistance line, and image interpretation and deformation inversion cannot be performed. Performing processing.
53589 针对以上问题，本文提出了一种基于分辨率设计和等距离多普勒特性分析的导航卫星双基地 SAＲ 几何优选方法。 In view of the above problems, this paper proposes a geometric optimization method for navigation satellite bistatic SAＲ based on resolution design and equidistant Doppler characteristic analysis.
53590 该方法在选定实验场景的基础上，进行 GNSS-BSAＲ 分辨性能与等距离-多普勒特性的多目标联合优化，选定能够避免镜像模糊现象的导航卫星辐射源，实现 GNSS-BSAＲ 几何构型优选。 This method performs multi-objective joint optimization of GNSS-BSAＲ resolution performance and equidistance-Doppler characteristics, on the basis of selected experimental scenes, selects a navigation satellite radiation source that can avoid the phenomenon of mirror image blur, and realizes the optimization of GNSS-BSAＲ geometric configuration.
53591 基于以上方法，在重庆边坡地区设计 GNSS- BSAＲ 实验，成功获取了无镜像模糊的实测边坡成像结果，验证了几何优选方法的有效性。 Based on the above methods, a GNSS-BSAＲ experiment was designed in the Chongqing slope area, and the measured slope imaging results without mirror blur were successfully obtained, which verifies the effectiveness of the proposed geometry optimization method.
53592 流量加密技术给流量分类带来了新的挑战，为实现加密流量的快速准确分类，提出了一种基于卷积注意力门控循环网络的加密流量分类方法。 The emergence of traffic encryption technology brought new challenges to traffic classification. In order to classi- fy the encrypted traffic quickly and accurately, an encrypted traffic classification method based on convolutional attention gated recurrent network was proposed.
53593 将卷积神经网络和门控循环单元相结合，针对流量数据的特点，修改卷积神经网络的池化层以提取单个数据包特征，通过注意力机制寻找单个数据包的关键特征并赋予高权重; This model combines a convolutional neural network and a gated recurrent unit. Ac- cording to the characteristics of the traffic data, the pooling layer of convolutional neural network was modified to extract the characteristics of single data packet. The key features of a single packet were found by attention mechanism and given high weight.
53594 然后采用门控循环单元提取流层面数据包间的时间序列特征，从包层面和流层面全面反映流量的整体和局部特征。 Then, the time series characteristics between packets at the flow level were extracted by gated recurrent unit, which reflected the overall and local features of traffic from packet level and flow level.
53595 实验证明该方法相对于现有方法，提高了分类准确率、实时性和训练效率。 Experimental results show that this method improves the classification accuracy, real-time performance and training efficiency compared with the traditional methods.
53596 为了提高人脸特征提取网络的性能，进而提高人脸识别算法的准确率，本文对基于卷积神经网络的人脸特征提取网络进行研究，提出了 SFＲNet ( Sparse Feature Ｒeuse Network) 。 In order to improve the performance of the face feature extraction network and then the accuracy of the face rec- ognition algorithm, this paper studies the network of the face feature extractor based on the convolutional neural network and proposes SFＲNet ( Sparse Feature Ｒeuse Network) .