| ID | 原文 | 译文 |
| 53767 | 基于Sentinel-1和高分三号大场景实测数据实验表明，相比于传统CFAR、Faster-RCNN和RetinaNet方法，本文方法综合检测性能提升25. 7%，3. 7%和9. 9%，同时检测速度提升10. 0%以上。 | The experimental results based on Sentinel-1 and GF-3 large-scene images show that compared with traditional CFAR, Faster-RCNN and RetinaNet methods, our method obtains 25. 7%, 3. 7% and 9. 9% gains in the comprehensive detection performance, while the detection speed is improved more than 10. 0%. |
| 53768 | 无处不在的地磁场由于室内环境中建筑结构的差异而具有独特的特征。 | Ubiquitous geomagnetic field exhibits unique features due to differences between building structures in indoor environments. |
| 53769 | 此外，地磁信号的分辨难度会导致定位结果的不准确。 | In addition, the difficulty of resolving geomagnetic signals will lead to inaccurate positioning results. |
| 53770 | 本文提出了一种使用深度神经网络来提高定位精度的地磁室内定位系统。 | This paper proposes a geomagnetic indoor positioning system using deep neural networks to improve positioning accuracy. |
| 53771 | 为了解决地磁场的低分辨率问题，本文将连续的地磁信号矢量化为轨迹序列，并以此为基础设计了一种新的地图构建方法来搭建用于室内定位的地磁数据库。 | In order to solve the problem of low discernibility of the geomagnetic filed, continuous geomagnetic signals are vectorized into a trajectory sequence, and a novel map-building method is designed based on this to geomagnetic database for indoor positioning. |
| 53772 | 然后，通过引入时间卷积网络(TCN)来提取磁轨迹序列的深层特征。 | Then, temporal convolutional network(TCN) is introduced to extract deep features of geomagnetic trajectory sequences. |
| 53773 | 实验结果表明，这种方法优于KNN和基于LSTM的DRNN等其他机器学习算法。 | Experimental results show that the method outperforms other machine learning algorithms, such as KNN and LSTM-based DRNN. |
| 53774 | 传统毫米波传播损耗模型假设收发端天线高度比较低，不直接适用于空地传输场景，本文基于射线跟踪原理提出了一种空地场景下毫米波通信的传播损耗统计模型。 | The factor of altitude is not fully considered in traditional path loss models, which cannot be applied to the air-to-ground communication scenarios directly. Based on the ray tracing technique, this paper proposed a statistical path loss model for air-to-ground mmWave channels. |
| 53775 | 该模型推导分析了视距、反射、绕射和无信号四种不同传播情况的路径概率，并综合考虑了环境、频率、距离和天线高度等因素对路径损耗的影响。 | This model derived the path probabilities of four different propagation cases, i. e. , line-of-sight, reflection, diffraction and no signal, and comprehensively took the influences of environment, frequency, distance, and antenna height into account. |
| 53776 | 仿真分析结果表明，本文模型对不同场景和传播高度都具有良好的适用性，对于非视距情况的细化分类使其计算结果比传统模型更为精确且与射线跟踪仿真结果更为吻合，可用于空地毫米波通信系统设计和算法优化等领域。 | The simulation and analyze show that the proposed model has good applicability for different scenes and antenna heights. The classification of non-line-of-sight makes its calculation results of path loss more accurate than the ones of traditional models, and more consistent with the results of ray tracing method. It can be used in the system design and algorithm optimization of air-to-ground millimeter-wave communication systems. |