ID	原文	译文
5474	针对这一需求，提出了一种基于移动网络用户位置信息的区域人群流量预测的深度时空网络模型。	A deep spatial-temporal networkfor regional crowd flows prediction was proposed, by using the spatial-temporal data acquired from mobile networks.
5475	通过建模不同尺度的时空依赖关系，融合各种外部特征信息，并以短时局部流量信息降低对实时全局信息传输的要求，实现了城市范围的区域人群流量预测，对提高 5G 网络性能具有重要意义。	A deeplearning based method was used to model the spatial-temporal dependencies with different scales. External factors werecombined further to predict citywide crowd flows. Only data from local regions was applied to model the closeness of prop-erties of the crowd flows, in order to reduce the requirements for transmitting the globe data in real time. It is of importancefor improving the performance of 5G networks.
5476	通过基于呼叫详单数据的区域人群流量预测实验表明，与现有流量预测模型相比，所提模型具有更高的预测精度。	The proposed model was evaluated based on call detail record data set. The experiment results show that the proposed model outperforms the other prediction models in term of the prediction precision.
5477	针对蜂窝网资源分配多目标优化问题，提出了一种基于深度强化学习的蜂窝网资源分配算法。	In order to solve multi-objective optimization problem, a resource allocation algorithm based on deep rein-forcement learning in cellular networks was proposed.
5478	首先构建深度神经网络（DNN），优化蜂窝系统的传输速率，完成算法的前向传输过程；	Firstly, deep neural network (DNN) was built to optimize thetransmission rate of cellular system and to complete the forward transmission process of the algorithm.
5479	然后将能量效率作为奖惩值，采用 Q-learning 机制来构建误差函数，利用梯度下降法来训练 DNN 的权值，完成算法的反向训练过程。	Then, theQ-learning mechanism was utilized to construct the error function, which used energy efficiency as the rewards. The gra-dient descent method was used to train the weights of DNN, and the reverse training process of the algorithm was com-pleted.
5480	仿真结果表明，所提出的算法可以自主设置资源分配方案的偏重程度，收敛速度快，在传输速率和系统能耗的优化方面明显优于其他算法。	The simulation results show that the proposed algorithm can determine optimization extent of optimal resourceallocation scheme with rapid convergence ability, it is obviously superior to the other algorithms in terms of transmissionrate and system energy consumption optimization.
5481	对无线通信系统的高可靠性与超高容量需求促进了第五代移动通信（5G）的发展，	The development of the fifth-generation wireless communications (5G) system is promoted by the high re-quirements of the high reliability and super-high network capacity.
5482	然而，随着通信系统的日益复杂，现有的物理层无线通信技术难以满足这些高的性能需求。	However, existing communication techniques are hardto achieve the high requirements due to the more and more complexity design in 5G system.
5483	目前，深度学习被认为是处理物理层通信的有效工具之一，基于此，主要探讨了深度学习在物理层无线通信中的潜在应用，并且证明了其卓越性能。	Currently, deep learning isconsidered one of effective tools to handle the physical layer wireless communications. Several potential applicationsbased on deep learning were reviewed, and their effectiveness were confirmed.