ID 原文 译文
57808 从国内外身份关联技术的研究现状出发，介绍了用户身份关联及分析框架，整理了身份数据采集标准和社交网络数据集; Starting from the research status of identity association technology at home and abroad，the framework of user i- dentity association and analysis is introduced，and the standards of identity data acquisition and social network data sets are collated.
57809 分析了近几年用户身份关联技术，并归纳了身份关联评价指标，阐述了基于身份关联的社交网络数据挖掘及分析框架; Subsequently，the technology of user identity association in recent years is analyzed and the evaluation index of identity association is summarized，and the social network data min- ing and analysis based on identity association is expounded.
57810 最后对身份关联中的研究难点及热点进行了讨论和展望. Finally，the research difficulties and hotspots of identity association are discussed and prospected.
57811 从安全性角度对一种车载网隐私保护方案进行了研究，指出该方案存在无法抵抗共谋攻击的问题，对该方案进行改进，提出了新的车载网隐私保护方案，解决了车载网的隐私保护、匿名性、共谋攻击、重放攻击等多种安全问题. Through analysis a privacy protection scheme in vehicle Ad hoc network ( VANET) ，it is re- vealed that the scheme cannot resist the collusion attack. Based on the scheme，a novel privacy protec- tion scheme is proposed.
57812 与现有的车载网隐私保护方案相比，新方案提高了安全性. It is proved that the proposed scheme solves privacy protection，anonymity，col- lusion attack，replay attack，etc. Compared with current privacy protection schemes in VANET，the no- vel scheme is more security.
57813 为解决大流检测过程中普遍存在的精度低、耗费高等问题，提出了一种面向软件定义网络的大流检测机制SampleFlow. SampleFlow，a heavy hitter detection mechanism in software defined networks，is proposed to solve the problems of low detection accuracy and high measurement cost.
57814 通过综合 sFlow 和 OpenFlow 技术优势，使用粗粒度的采样技术识别出疑似大流，在 OpenFlow 交换机上安装测量流表项，对这些疑似大流进行细粒度测量判别，以达到准确检测大流的目标，通过采样点优化选择算法，还可降低采样的冗余性. By combining the technical ad- vantage of sFlow and OpenFlow，SampleFlow firstly detects a set of suspicious heavy hitters by using the coarse-grained sFlow sampling method，and then installs measurement flow entries on specific OpenFlow switches to perform a fine-grained measurement on these suspicious heavy hitters，so as to determine the true heavy hitters. Besides，SampleFlow also uses a sampling position optimization method to decrease the sampling redundancy.
57815 实验结果表明，SampleFlow 能够有效降低测量负载，并提升大流检测的精度. Experiment results show that SampleFlow can decrease the measurement cost， and increase the heavy hitter detection accuracy effectively.
57816 针对 PM2.5浓度的非线性和不确定性，提出了一种基于集成树－梯度提升决策树( EnsembleTrees-GBDT) 的 PM2.5预测模型. The increase of PM2. 5 is a cause of haze. Effectively predicting PM2. 5 concentration and an- alyzing its influence factors play an important role in air quality forecasting and controlling.
57817 该模型首先在集成树框架下进行特征选择，即选取 PM2.5浓度主要影响因素，使用算术均值聚合法计算出各项特征对 PM2.5浓度增加的影响程度，并以影响程度由强到弱的次序排序;其次使用网格搜索对 GBDT 算法进行参数优化，选取树的深度等参数的最优值; Considering nonlinearity and uncertainty of PM2. 5 concentration，a PM2. 5 concentration prediction model which firstly selects features using integrated trees was presented based on ensemble trees-gradient boosting deci- sion tree( GBDT) .