ID	原文	译文
5484	最后，提出几个可能发展的基于深度学习的物理层无线通信技术。	Finally, several potential techniques indeep learning based physical layer wireless communications were pointed out.
5485	5G 的设计目标是满足 2020 年以后移动通信市场的业务发展新需求，满足更高速率、更低时延、更大连接数密度等能力要求。	The 5 th generation mobile system (5G) was designed to fulfill the mobile market requirements for higher datarate, lower latency and higher connection density beyond 2020.
5486	3.5 GHz 是目前全球规划的最典型的 5G 频率，并有望实现全球统一划分，5G 在该频段上的性能表现对未来全球的 5G 部署具有极大的参考意义。	3.5 GHz spectrum was a typical band for 5G deploymentand could be a global band for 5G development. The performance of 3.5 GHz 5G would be very meaningful as a refer-ence for global operators.
5487	结合 5G 新空口标准的第一个版本，中国移动联合国内合作伙伴开展了面向 3.5 GHz 的 5G 样机设计和优化，并在典型的城区外场环境开展了小规模的外场实验，针对 5G 系统的峰值速率、小区吞吐量、覆盖能力等进行了测试验证。	Based on the first release of 5G specification frozen in June 2018 by 3 rd generation partnerproject (3GPP), field trials of 5G network in typical urban area were conducted to validate the peak data rate, cellthroughput and latency of 5G network.
5488	测试结果充分证明，5G 新空口系统可以实现 1 Gbit/s 以上的峰值速率和 4 ms 的空口单向时延。	The trial results show that 5G NR system can achieved 1 Gbit/s peak data rate and4 ms latency of single direction.
5489	传统的隐私保护的图像检索方案会带来较大的计算量和通信开销，且在多用户场景下无法保护图像特征向量和查询请求的隐私。	The traditional privacy-preserving image retrieval schemes not only bring large computational and communi-cation overhead, but also cannot protect the image and query privacy in multi-user scenarios.
5490	为此，提出了多用户场景下高效隐私保护的基于内容的图像检索方案。	To solve above problems, anefficient privacy-preserving content-based image retrieval scheme was proposed in multi-user scenarios.
5491	该方案利用隐私保护的欧式距离比较技术对图像特征向量进行相似度排序并返回 top-k 结果。	The schemeused Euclidean distance comparison technique to rank the pictures according to similarity of picture feature vectors andreturn top-k returned.
5492	同时，设计的高效密钥转换协议允许每一个检索用户使用自身的私钥生成查询请求，并检索不同数据拥有者生成的加密图像。	Meanwhile, the efficient key conversion protocol designed in proposed image retrieval scheme al-lowed each search user to generate queries based on his own private key so that he can retrieval encrypted images gener-ated by different data owners.
5493	安全分析表明，图像检索过程中，用户个人隐私以及云端数据安全都可以得到保护，且基于实际数据集的性能分析表明提出的图像检索方案在实际应用中是高效可行的。	Strict security analysis shows that the user privacy and cloud data security can be well pro-tected during the image retrieval process, and the performance analysis using real-world dataset shows that the proposedimage retrieval scheme is efficient and feasible in practical applications.