ID	原文	译文
53147	进而根据S稀疏性重构网联车辆自适应巡航状态;	Furthermore, the initial state of the connected vehicle's cruise state is reconstructed based on S-sparsity.
53148	最后，通过典型车辆自适应巡航场景仿真验证该方法的有效性。	Finally, the effectiveness of the algorithm is verified by simulation of typical vehicle cruise scenarios.
53149	对作者合著网络进行社区划分有助于挖掘科研人员的合作和交流模式。	The community detection in co-authorship networks is of great significance for understanding the cooperation and communication patterns of researchers.
53150	采用Louvain算法将C-DBLP作者发文合作关系公开数据集进行了社区划分，并采用模块度对划分结果进行评估。	In this paper, Louvain algorithm is used in community detection in CDBLP dataset, and the results are evaluated by modularity.
53151	结果表明，Louvain算法能够快速高效地处理具有数千个节点的网络，与LED算法和GN算法相比，能更有效地进行社区划分。	Louvain algorithm can efficiently deal with networks with thousands of nodes, compared with the LED algorithm and G-N algorithm, it's more effectively in the community detection.
53152	研究结果揭示了各个学科不同的合作交流模式，有助于挖掘潜在的合作团体，为学科合作研究提供帮助。	The results reveal different disciplines' cooperation and communication mode, helping to mining potential cooperative groups and helping for collaborative research.
53153	传统以网络为中心的移动网络运维往往是在接到用户投诉时才采取相应补救措施，随着移动互联网(OTT)业务的高速发展，这一问题愈发突出。	Traditional network-centric mobile network operation often takes corresponding remedial measures when receiving user complaints about service quality. With the rapid development of over-the-top(OTT) services, this problem has become increasingly prominent.
53154	如何在监测用户业务感知的基础上对用户业务质量进行预测预警并及时干预，是提高移动业务保障能力和网络运维智能化水平的重要手段。	How to predict and warn the user's service quality and timely intervene based on the service perception monitoring is an important means to improve the intelligence of network operation.
53155	本文利用从普通用户终端上采集的海量业务感知数据，重点针对网页浏览业务，研究了ML-ReliefF算法在业务感知采样数据降维中的应用。	In this paper, the service perception data crowdsensed from massive user terminals are utilized, focusing on the web browsing service, and the ML-ReliefF algorithm in the dimension reduction of service perception data is applied.
53156	在此基础上，将特征选择结果与多标记k近邻(kNN)算法相结合，提出了基于特征加权的多标记k近邻算法应用于业务关键质量指标(KQI)预测。	On this basis, combined with the feature selection results with the multi-label k-nearest neighbor(ML-kNN) algorithm, a feature weighted key quality indicator(ML-kNN for KQI) prediction is proposed.