国家自然科学基金面上项目，“车联网环境下的事件检测和分发研究（61472408）” 返回上页

  • 项目起止时间：2014.1-2018.12，项目负责人：金蓓弘
  • 项目简介：车联网是以车辆为主要节点，依托车载自组织网络、移动互联网构成的网络，是物联网的一类具体实现，其应用广泛。本项目从基于事件的分布式系统角度，依托来自实际场景的海量人车轨迹数据，对车联网路由和车联网事件检测进行了研究，完成了下列研究工作：(1) 深入调研了车载自组织网络的数据传递机制，针对公交车自组织网络，通过挖掘公交车轨迹的时空规律、社区特征等，提出了多种高效的路由算法；(2)从三个方面，即，检测交通事件、拓展事件检测方式、挖掘事件语义，开展车联网事件检测研究。针对高速公路场景，本项目融合多种感知数据，挖掘数据内在的时空约束，设计或应用机器学习算法，实现了对高速公路全路段交通状况的高精度、低成本检测，从而实时获得高速公路上运行的车辆的速度、车流量和车辆类型，这部分研究成果已完成应用示范，检测效果得到了交通部门的认可。针对城市公共交通场景，本项目挖掘公交乘客的轨迹数据，从中检测出公交乘客的频繁出行模式(稠密事件)；设计深度神经网络及时空注意力机制，提供对公交站点乘客的流量预测；建立周期性时间序列的动态变化模型，捕获公交站点乘客的流量异常(异常事件)；本项目还分析了公交车辆的轨迹数据，建立鲁棒的异常检测模型，融合特征选择和模型参数优化，从而从极不平衡的轨迹数据集中检测出异常公交驾驶行为(异常事件)。在事件检测方式方面，本项目研究了订阅匹配型事件检测方式相关的算法和系统，同时，通过分析用户移动轨迹来选择群智感知活动的参与者，从而支持以群智感知方式发现事件。另外，本项目还研究了通过为微博、POI数据等建立主题模型来挖掘事件的语义。本项目的研究拓展了车联网应用的深度和广度，提供了轨迹数据分析挖掘的新见解和新方法，特别是，多项研究成果具有实际应用前景。
  • 研究成果-论文
    1. 张扶桑，金蓓弘，汪兆洋，胡佳锋，张利锋，基于轨迹挖掘的公交车自组织网络路由机制，计算机学报，Vol. 38，No. 4，2015年3月
    2. Fusang Zhang, Hai Liu, Yiu-Wing Leung, Xiaowen Chu and Beihong Jin, Community-based Bus System as Routing Backbone for Vehicular Ad Hoc Networks, ICDCS 2015, the 35th IEEE International Conference on Distributed Computing Systems, June 29th-July 2nd, 2015, Columbus, Ohio, USA
    3. Jiafeng Hu, Reynold Cheng, Dingming Wu, and Beihong Jin, Efficient Top-k Subscription Matching for Location-Aware Publish/Subscribe, SSTD 2015, the International Symposium on Spatial and Temporal Databases 2015, August 26-28, Seoul, South Korea
    4. Fusang Zhang, Yuwei Yang, Yuyao Yang, Beihong Jin, Optimizing the Quality of Service for a Pub/Sub System, ATC 2015, the 12th IEEE International Conference on Advanced and Trusted Computing, August 10-14, 2015, Beijing, China.
    5. 金蓓弘，张扶桑，张利锋，车载自组织网络中的数据传递，集成技术，2015年9月，第4卷，第5期
    6. Fusang Zhang, Beihong Jin, Zhaoyang Wang, Hai Liu, Jiafeng Hu and Lifeng Zhang, On Geocasting over Urban Bus based Networks by Mining Trajectories, IEEE Transactions on Intelligent Transportation Systems, 17(6): 1734-1747, 2016
    7. Zhejun Zheng, Beihong Jin, Yanling Cui, Qiang Ji, Detecting Live Events by Mining Textual and Spatial-Temporal Features from Microblogs, WAIM 2016 Part II, the 17th International Conference on Web-Age Information Management, June 3-5, 2016, Nanchang, China, pp. 356-368
    8. Beihong Jin, Yanling Cui, Fushang Zhang, Fusing Static and Roving Sensor Data for Detecting Highway Traffic Conditions in Real Time, IEEE COMPSAC 2016, the 40th IEEE International Conference on Computers, Software and Applications, June 10-14, 2016, pp. 807-816, Atlanta, Georgia, USA
    9. Fusang Zhang, Beihong Jin, Tingjian Ge, Qiang Ji and Yanling Cui, Who are My Familiar Strangers? Revealing Hidden Friend Relations and Common Interests from Smart Card Data,  ACM CIKM 2016, the 25th ACM International Conference on Information and Knowledge Management, October 24-28, 2016, Indianapolis,USA, pp. 619-628
    10. Zhaoyang Wang, Beihong Jin, Fusang Zhang, Ruiyang Yang, Qiang Ji, Discovering Trip Patterns from Incomplete Passenger Trajectories for Inter-zonal Bus Line Planning, NPC 2016, the 13th IFIP International Conference on Network and Parallel Computing, October 28-29, 2016, Xi'an, China, pp.
    11. Fusang Zhang, Beihong Jin, Hai Liu, Yiu-Wing Leung and Xiaowen Chu, Minimum-Cost Recruitment of Mobile Crowdsensing in Cellular Networks, IEEE GlobeCom 2016, the 59th annual IEEE Global Communications Conference, December 4-8 2016, Washington DC, USA
    12. Fusang Zhang, Hai Liu, Yiu-Wing Leung, Xiaowen Chu, Beihong Jin, CBS: Community-based Bus System as Routing Backbone for Vehicular Ad Hoc Networks, IEEE Transactions on Mobile Computing, 16(8): 2132-2146 (2017)
    13. 崔艳玲，金蓓弘，张扶桑，基于数据融合的高速公路交通状况检测，计算机学报，Vol. 40，No. 8，2017年8月
    14. Zhaoyang Wang, Beihong Jin, Fusang Zhang, Ruiyang Yang and Ji Qiang, Exploiting Trip Patterns in Passenger Trajectory Streams for Bus Scheduling Optimization in Real Time, MDM 2017, the 18th IEEE International Conference on Mobile Data Management, May 29 - June 1, 2017, Daejeon, South Korea, pp. 266-271
    15. Qiang Ji, Beihong Jin, Yanling Cui and Fusang Zhang, Using Mobile Signaling Data to Classify Vehicles on Highways in Real Time, MDM 2017, the 18th IEEE International Conference on Mobile Data Management, May 29 - June 1, 2017, Daejeon, South Korea, pp. 174-179
    16. Yanling Cui, Qiang Ji, Fusang Zhang, Beihong Jin, Leveraging Mobile Signaling Data for Monitoring Vehicles on Highways in Real Time, BigCom 2017, the 3rd International Conference on Big Data Computing and Communications, August 10th-11th, Chengdu, Sichuan, China, pp. 340-349
    17. Yanling Cui, Beihong Jin, Fusang Zhang, Boyang Han and Daqing Zhang, Mining Spatial-temporal Correlation of Sensory Data for Estimating Traffic Volumes on Highways, Mobiquitous 2017, the 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Nov. 7–10, 2017, Melbourne, Australia, Best paper award runner-up
    18. Yanling Cui, Beihong Jin, Fusang Zhang and Tingjian Ge, Towards Adaptive Sensory Data Fusion for Detecting Highway Traffic Conditions in Real Time, DASFAA 2018, the 23rd International Conference on Database Systems for Advanced Applications, May 21-24, 2018, Gold coast, Australia
    19. Miao Li, Beihong Jin, Hongyin Tang, Fusang Zhang, Clustering Large-Scale Origin-Destination Pairs: A Case Study for Public Transit in Beijing, UIC 2018, the 15th IEEE International Conference on Ubiquitous Intelligence and Computing, October 8-12, 2018, Guangzhou, China
    20. Bo Tang, Hongyin Tang, Xinzhou Dong, Beihong Jin, Tingjian Ge, On Real-time Detecting Passenger Flow Anomalies, CIKM 2018, the 27th ACM International Conference on Information and Knowledge Management, October 22-26, 2018, Turin, Italy
    21. Xinzhou Dong, Beihong Jin, Bo Tang, Hongyin Tang, On Real-time Monitoring on Data Stream for Traffic Flow Anomalies, ISPA 2018, the 16th IEEE International Symposium on Parallel and Distributed Processing with Applications, 11-13 Dec. 2018, Melbourne, Australia
  • 研究成果-专利
    1. 一种基于数据融合的高速公路路况信息实时获取方法，专利号：ZL201610584675.4
    2. 一种挖掘时空关联关系的实时高速公路流量估计方法，专利号：ZL201710716406.3
    3. 一种基于神经网络时空注意力机制的实时站点流量预测方法，申请号：201910097165.8
  • 研究成果-获奖
    1. 基于手机信令的路网运行监测与出行信息服务关键技术研究及示范应用，2017中国公路学会科学技术奖三等奖，主要完成单位：交科院（北京）交通技术有限公司，交通运输部路网监测与应急处置中心，中国移动通信集团福建有限公司厦门分公司，中国科学院软件研究所，集美大学，主要完成人：萧赓，王虎，金蓓弘，郝盛，崔艳玲