With the rapid development and application of cloud computing,big data,artificial intelligence,5G,satellite communication,blockchain and other emerging information technologies,conditions have been provided for the in...With the rapid development and application of cloud computing,big data,artificial intelligence,5G,satellite communication,blockchain and other emerging information technologies,conditions have been provided for the intelligent development of urban rail vehicles.With the development of smart urban rail vehicles,the standards system of traditional urban rail vehicle cannot meet the development requirements,so it is necessary to study and reconstruct the standards system.To embody the intelligent level of urban rail vehicles,the paper conducts the research on the standards for the urban rail vehicle train control system,monitoring and diagnosis system,passenger service system,and then proposes the overall architecture and standard list of smart city rail vehicle technical standards system,providing reference for the planning and establishment of China's smart city rail standards system.展开更多
尽管基于城市轨道交通自动售检票(automatic fare collection,AFC)系统采集的智能卡数据(smart card data,SCD)能够精准记录人们的出行时间和地点,但无法直接反映出行目的或活动类型.本研究提出一种方法,将约束种子K-means算法的站点聚...尽管基于城市轨道交通自动售检票(automatic fare collection,AFC)系统采集的智能卡数据(smart card data,SCD)能够精准记录人们的出行时间和地点,但无法直接反映出行目的或活动类型.本研究提出一种方法,将约束种子K-means算法的站点聚类与隐含狄利克雷分布(latent Dirichlet allocation,LDA)模型的客流出行目的挖掘相结合,以揭示城市轨道交通客流出行数据中的潜在活动模式.首先,基于车站周边的人口特征、客流特征及兴趣点(points of interest,POI)分布,使用约束种子K-means算法将站点划分为8类:就业集聚型、居住集聚型、职住复合型、商业中心型、旅游景点型、综合枢纽型、对外枢纽型以及客流培育型.其次,基于出站时间、活动时长、起点车站类型以及终点车站类型构建了LDA模型.该模型成功识别出5类主要活动,分别为购物消费、工作、回家、休闲旅游及其他.此外,这些模式进一步细分为若干子主题,每个子主题在时间和空间特征上具有显著差异,为深入理解节假日城市轨道交通客流出行行为提供了理论支持.展开更多
基金the Major Science&Technology Development Project of China CRRC in 2022.Project number:2022CKA054。
文摘With the rapid development and application of cloud computing,big data,artificial intelligence,5G,satellite communication,blockchain and other emerging information technologies,conditions have been provided for the intelligent development of urban rail vehicles.With the development of smart urban rail vehicles,the standards system of traditional urban rail vehicle cannot meet the development requirements,so it is necessary to study and reconstruct the standards system.To embody the intelligent level of urban rail vehicles,the paper conducts the research on the standards for the urban rail vehicle train control system,monitoring and diagnosis system,passenger service system,and then proposes the overall architecture and standard list of smart city rail vehicle technical standards system,providing reference for the planning and establishment of China's smart city rail standards system.
文摘尽管基于城市轨道交通自动售检票(automatic fare collection,AFC)系统采集的智能卡数据(smart card data,SCD)能够精准记录人们的出行时间和地点,但无法直接反映出行目的或活动类型.本研究提出一种方法,将约束种子K-means算法的站点聚类与隐含狄利克雷分布(latent Dirichlet allocation,LDA)模型的客流出行目的挖掘相结合,以揭示城市轨道交通客流出行数据中的潜在活动模式.首先,基于车站周边的人口特征、客流特征及兴趣点(points of interest,POI)分布,使用约束种子K-means算法将站点划分为8类:就业集聚型、居住集聚型、职住复合型、商业中心型、旅游景点型、综合枢纽型、对外枢纽型以及客流培育型.其次,基于出站时间、活动时长、起点车站类型以及终点车站类型构建了LDA模型.该模型成功识别出5类主要活动,分别为购物消费、工作、回家、休闲旅游及其他.此外,这些模式进一步细分为若干子主题,每个子主题在时间和空间特征上具有显著差异,为深入理解节假日城市轨道交通客流出行行为提供了理论支持.
