ID 原文 译文
18925 先对接收到的信道状态信息(CSI)进行预处理以消除相位误差和幅值噪声，再利用CSI的时序相关性和子载波相关性从相关系数矩阵中提取多维信号特征，最后使用BP神经网络完成特征与检测结果之间的映射。 Firstly, the received Channel State Information(CSI) is preprocessed to eliminate the phase error and amplitude noise, and the multidimensional signal features are fully extracted from the correlation coefficient matrix by using time correlation and subcarrier correlation of CSI. Finally, the mapping between features and detection results isestablished by BP neural network.
18926 实验结果表明，该算法在玻璃墙、砖墙和混凝土墙环境的识别精度分别在0.98,0.90, 0.85以上。 The experimental results show that the recognition accuracy of this algorithm in the environment with glass wall, brick wall and concrete wall is above 0.98, 0.90, 0.85, respectively.
18927 根据所统计的4000个各类样本的检测结果，与现有基于单一信号特征的检测算法相比，该文算法在对不同数量运动目标的检测上，获得了平均0.45的精度提升。 According to the detection results of 4000 samples, compared with the existing detection algorithms based on single signal feature, the proposed algorithm achieves an average accuracy improvement of 0.45 in the detection of different number of moving targets.
18928 针对5G网络中因小区重叠覆盖区域的干扰问题，为缓解密集小蜂窝网络中移动用户的业务连续性，提高频谱资源利用率，该文提出一种基于不活跃用户的最优能量效率资源分配方案(EEI)。 Considering the interference problem of overlapping areas of cells, the service continuity of mobileusers and the utilization of spectrum resources in the 5G network, an Energy Efficient resource allocationscheme for the Inactive user(EEI) is proposed.
18929 首先，该方案依据不活跃用户通知区域，建立以用户为中心的虚拟小区，小区内小蜂窝基站可协作为用户提供通信服务，提高用户通信质量，缓解小蜂窝同层干扰，减少切换信令开销。 Firstly, a user-centered virtual cell is generated based on thenotification area of the inactive users, and the intra-cell next-generation NodeBs (gNBs) could cooperativelyprovide communication services for users to improve the communication quality, lower the inter-cellinterference, and reduce the handover signaling overhead.
18930 其次，基于Lyapunov优化理论，该方案将整体网络平均能量效率优化问题，转换为用户最优传输资源分配和最优功率分配两个子问题，在最大化系统平均能量效率同时保证系统队列稳定性。 Secondly, Lyapunov optimization method is used tomaximize the energy efficiency of the network, while ensuring the stability of the data queue. To make the optimization problem tractable, the scheme is decomposed into two sub-problems: the optimal transmission resource allocation and optimal transmission power allocation.
18931 由于该文将原优化问题进行了松弛，所得结果是局部最优解，而不是全局最优解。 Notice that, the optimal solutions are local optimal, which are based on the relaxed optimization problem.
18932 仿真结果表明，该文提出的基于不活跃用户的最优能量效率资源分配算法，其系统能量效率优于对比算法而计算复杂度较高。 The simulation results show that the proposedenergy efficiency resource allocation scheme based on the inactive users could achieve a better performance thanthe comparison algorithms,in the price of higher computational complexity.
18933 路预测旨在利用网络中已有的拓扑结构或其他信息，预测未连边节点间存在连接的可能性。 Link prediction considers to discover the unknown or missing links of complex networks by using the existing topology or other information.
18934 资源分配指标具有较低复杂度的同时取得了较好的预测效果，但在资源传输过程的描述中缺少对路径有效性的刻画。 Resource Allocation index can achieve a good performance with lowcomplexity. However, it ignores the path effectiveness of resource transmission process.