基于序贯蒙特卡洛算法的交通流事件重构

计算机工程与科学

基于序贯蒙特卡洛算法的交通流事件重构

冯向文，燕雪峰

（南京航空航天大学计算机科学与技术学院,江苏南京 210016）

收稿日期:2015-05-26 修回日期:2015-09-15 出版日期:2016-09-25 发布日期:2016-09-25
基金资助:
十三五重点基础科研项目（JCKY2016206B001）

Event reconstruction for traffic flow simulation based on sequential Monte Carlo

FENG Xiang-wen，YAN Xue-feng

（College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China）

Received:2015-05-26 Revised:2015-09-15 Online:2016-09-25 Published:2016-09-25

摘要/Abstract

摘要：

针对交通数据重构应用性差、缺乏对交通事件重构的研究等问题，结合交通流非线性非高斯的特点，提出一个基于序贯蒙特卡洛方法的交通流堵塞事件重构模型。该模型不断同化道路上的传感器数据，使仿真中的交通状态不断逼近真实路况，通过分析仿真数据以探测真实路网中存在的堵塞事件。模型能够对探测到的堵塞进行多粒子模拟来实现对真实道路上堵塞事件的重构。实验结果表明，该模型能够推测并重构出道路上的堵塞事件，对堵塞起始位置重构的平均误差为17 m，对堵塞范围重构的平均覆盖率为82%。

关键词: 序贯蒙特卡洛算法, 动态数据驱动应用系统, 交通流仿真, 事件重构

Abstract:

Combining with the nonlinear and non-Gaussian characteristics of the traffic flow, we propose a traffic flow congestion event reconstruction framework based on the Sequential Monte Carlo (SMC) to deal with the congestion reconstruction problem. The simulation's states can get close to the real scene continuously when the data assimilation model assimilates the real-time sensor data constantly. The congestion event in real scene can be estimated based on the simulation data. Thus, the simulation model can simulate the congestion via different particle simulations and finally reconstruct the congestion event. Experimental results show that the framework can detect and reconstruct the congestion event on the real road network; the average error of the start position is 17m, while the average coverage rate of the congestion range is 82%.

Key words: SMC, DDDAS, traffic flow simulation, event reconstruction

冯向文，燕雪峰. 基于序贯蒙特卡洛算法的交通流事件重构[J]. 计算机工程与科学.

FENG Xiang-wen，YAN Xue-feng. Event reconstruction for traffic flow simulation based on sequential Monte Carlo [J]. Computer Engineering & Science.

参考文献

［1］Olayiwola K O,Olaseni A M,Fashina O.Traffic congestion problems in central business district (CBD) Ikeja,Lagos Metropolis,Nigeria［J］.Research on Humanities and Social Sciences,2014,4(1):23-32.
［2］Treiber M, Helbing D. Reconstructing the spatio-temporal traffic dynamics from stationary detector data［J］.Cooperative Transportation Dynamics,2002,1(3):3.1-3.21.
［3］Herrera J C,Bayen A M.Traffic flow reconstruction using mobile sensors and loop detector data［J］.Transportation Research Board,2007,1(1):12-17.
［4］Liao Y C,Langweg H.Resource-based event reconstruction of digital crime scenes［C］∥Proc of IEEE Intelligence and Security Informatics Conference (JISIC),2014:129-136.
［5］Ayodeji O O,Jiya J Y,Hale J M.Event reconstruction by digital filtering［J］.Advances in Signal Processing,2013,1(3):48-56.
［6］Pawlowski A,Guzman J L,Berenguel M,et al.Lagrange interpolation for signal reconstruction in event-based GPC［C］
∥Proc of IEEE Emerging Technology and Factory Automation (ETFA),2014:1-7.
［7］Gianelle A,Amerio S,Bastieri D,et al.Applications of many-core technologies to on-line event reconstruction in high energy physics experiments［C］∥Proc of IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC),2013:1-5.
［8］Yan X,Gu F,Hu X,et al.A dynamic data driven application system for wildfire spread simulation［C］∥ Proc of the 2013 IEEE Winter Simulation Conference,2013:3121-3128.
［9］Bi Jun, Chang Can, Fan Yang. Particle filter for estimating freeway traffic state in Beijing［J］.Mathematical Problems in Engineering,2013,70(2):717-718.
［10］Zhang G, Huang D. Short-term network traffic prediction with ACD and particle filter［C］∥Proc of IEEE 2013 5th International Conference on Intelligent Networking and Collaborative Systems (INCoS),2013:189-191.
［11］Prudencio E E, Bauman P T, Williams S V, et al. A dynamic data driven application system for real-time monitoring of stochastic damage［J］.Procedia Computer Science,2013,18(1):2056-2065.
［12］Patra A,Bursik M,Dehn J,et al.A DDDAS framework for volcanic ash propagation and hazard analysis［J］.Procedia Computer Science,2012,9(1):1090-1099.
［13］Vodacek A,Kerekes J P,Hoffman M J.Adaptive optical sensing in an object tracking DDDAS［J］.Procedia Computer Science,2012,9(1):1159-1166.
［14］Madey G R,Blake M B,Poellabauer C,et al.Applying DDDAS principles to command,control and mission planning for uav swarms［J］.Procedia Computer Science,2012,9(1):1177-1186.
［15］Darema F,Rotea M.Dynamic data-driven applications systems［C］∥ Proc of the 2006 ACM/IEEE Conference on Supercomputing, 2006:2.