ID	原文	译文
3353	通过有效地捕获城市私家车出行的时空特征，提出一种多源异构数据融合的私家车流量预测模型。	By effectively capturing the spatio-temporal characteristics of urban private car travel, a multi-source hetero-geneous data fusion model for private car volume prediction was proposed.
3354	首先，融合私家车轨迹和城市区域数据表征城市私家车的出行分布；	Firstly, private car trajectory andarea-of-interest data were integrated.
3355	其次，通过多视角时空图建模私家车出行和城市区域之间的动态关联，设计了多图卷积−注意力网络以提取车流量演变的时空特征；	Secondly, the spatio-temporal correlations between private car travel and urbanareas were modeled through multi-view spatio-temporal graphs, the multi-graph convolution-attention network(MGC-AN) was proposed to extract the spatio-temporal characteristics of private car travel.
3356	最后，进一步融合时空特征与天气等外部特征，联合预测私家车流量。	Finally, the spatio-temporal characteristics and external characteristics such as weather were integrated for joint prediction.
3357	在长沙市和深圳市采集的真实数据上进行验证，实验结果表明，与现有的模型相比，所提模型的均方根误差约降低了 11.3%～20.3%，平均绝对百分误差约降低了 10.8%～36.1%。	Experiments were con-ducted on real datasets, which were collected in Changsha and Shenzhen. The experimental results show that, comparedwith the existing prediction model, the root mean square error of the MGC-AN is reduced 11.3%～20.3%, and the aver-age absolute percentage error is reduced 10.8%～36.1%.
3358	针对物理层安全研究中主窃信道具有相关性的场景，研究了主窃信道间的相关性对系统安全性能产生的影响，推导得到了遍历保密容量及中断概率的精确计算式，以及主窃信道的信道状态差异较大和较小这 2 种场景下的渐近计算式，	In view of the correlation of the main and eavesdropper's channels in physical layer security, the impact of channel correlation on the secrecy performance was studied, the exact form ulations of ergodic secrecy capacity andsecrecy outage probability were derived, and then the asymptotic formulations in the scenarios where the channel stateswere large and small were given.
3359	并通过仿真验证了理论分析的正确性。	The theoretical analysis were verified by the numerical simulations.
3360	研究结果表明，信道相关性会造成遍历保密容量的损失，但信道相关性强并不一定表明通信中断概率大。	The simulation re-sults show that channel correlation will cause the loss of ergodic secrecy capacity, however, it does not mean the outageprobability of communication will increase with high channel correlation.
3361	当目标速率设置合理时，信道相关性的影响与接收端平均信噪比有关，在高信噪比区域，强相关性会降低中断概率；	Actually, when the outage rate is set reasonably,the impact of channel correlation is related to the average signal-to-noise ratio (SNR) at the receiver end.
3362	在低信噪比区域，强相关性会增大中断概率；在中信噪比区域内，相关性几乎不影响系统的中断概率。	At high SNRrange, high correlation will decrease the outage probability, at low SNR range, high correlation will increase the outageprobability, and at medium SNR range, the correlation will not affect the outage probability significantly.