城市轨道交通客流预测算法设计与仿真

计算机科学 ›› 2014, Vol. 41 ›› Issue (2): 276-279.

城市轨道交通客流预测算法设计与仿真

李少伟,陈永生

同济大学电子与信息工程学院上海201804;同济大学电子与信息工程学院上海201804

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家科技支撑计划(2009BAG18B04),上海市重点学科建设项目(S30602)资助

Design and Simulation of Passenger Flow Forecast Algorithm for Urban Rail Transit

LI Shao-wei and CHEN Yong-sheng

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 为了更好地解决城市轨道交通的客流预测问题,提出了基于混合神经网络与卡尔曼滤波器的客流预测多层次模型。首先采用ELAN神经网络实现客流量的初步预测；然后采用卡尔曼滤波器对神经网络预测结果进行修正,以进一步提高预测结果精度；最后为了验证模型的正确性,以上海地铁交通作为研究对象,进行了客流观测和预测模拟。实验结果表明,所提出的多层次模型比单纯其中一种算法能减少约0.8%的误差,并且具有更好的实际效果。

关键词: 轨道交通,客流预测,ELAN神经网络,卡尔曼滤波器,系统仿真中图法分类号U293.5文献标识码A

Abstract: To forecast exactly the passenger flow of the urban rail transit,a hierarchical framework based on neural network and Kalman-filter model was presented．First,ELAN neural network model is employed to implement the prediction of the passenger flow．Then the Kalman-filter was used to refine the forecast data of the passenger flow so as to advance the accuracy of the predicted results．Finally,in order to validate the proposed model,the passenger flow of Shanghai subway transport hub was observed and simulated．Experimental results show that the proposed hierarchical model reduces error about 0.8% and has better effects in contrast with any single algorithm.

Key words: Rail transit,Passenger flow forecast,ELAN neural network,Kalman filter,System simulation

李少伟,陈永生. 城市轨道交通客流预测算法设计与仿真[J]. 计算机科学, 2014, 41(2): 276-279. https://doi.org/

LI Shao-wei and CHEN Yong-sheng. Design and Simulation of Passenger Flow Forecast Algorithm for Urban Rail Transit[J]. Computer Science, 2014, 41(2): 276-279. https://doi.org/

参考文献

[1] 黄树森,宋瑞,陶媛.大城市居民出行方式选择行为及影响因素研究-以北京为例[J].交通标准化,2008,8(9):124-128
[2] Li Shao-wei,Chen Yong-sheng．Dynamic schedule strategy for urban rail transit[J].International Journal of Digital Content Technology and its Applications,2012,6(3):86-92
[3] 吕慎,过秀成.轨道线网客流预测方法研究[J].系统工程理论与实践,2001,3(8):106-110
[4] Zhang Dong-quan．Passenger Flow Forecast of Urban Rail Transit Based on BP Neural Networks[C]∥Intelligent Systems and Applications.Qingdao:IEEE,2011:1-4
[5] 鲁明旭,叶银忠,马向华.神经网络在地铁客流预测中的应用[J]．机械研究与应用,2012,5(3):86-89
[6] 陈大伟,肖为周,李旭宏,等.迭代反馈约束下的城市轨道交通客流预测分析[J].华南理工大学学报:自然科学版,2011,9(8):99-103
[7] 顾杨,韩印,方雪丽.基于ARMA模型的公交枢纽站客流量预测方法研究[J].交通信息与安全,2011,9(2):5-9
[8] Zhu Hai-yan.N days average volume based ARIMA forecasting model for Shanghai metro passenger flow[C]∥International Conference on Artificial Intelligence and Education,ICAIE．Hangzhou:IEEE,2010:631-635
[9] Ghosh B,Basu B,O’Mahony M．Multivariate Short-Term Traffic Flow Forecasting Using Time-Series Analysis[J].IEEE Transactions on Intelligent Transportation Systems,2009,0(2):246-254
[10] 张春辉,宋瑞,孙杨.基于卡尔曼滤波的公交站点短时客流预测[J].交通运输系统工程与信息,2011,1(4):154-159
[11] 姜平,黄志鹏.基于神经网络的公交客流预测[J].交通标准化,2008,8(12):28-31
[12] 刘凯,李文权,赵锦焕.短时公交客流小波预测方法研究[J].交通运输工程与信息学报,2010,8(2):111-117
[13] 任崇岭,曹成铉,李静,等．基于小波神经网络的短时客流量预测研究[J].科学技术与工程,2011,1(21):5099-5110
[14] 张余生,夏秀渝,杨莎.基于神经网络和卡尔曼滤波算法的说话人识别[J]．成都信息工程学院学报,2008,3(4):384-388
[15] Haykin S.Neural Networks Principle:2nd Edition[M].Beijing:China Machine Press,2004
[16] Hagan M T.Design Neural Network[M].Beijing:China Ma-chine Press,2002
[17] Welch G,Bishop G．An Introduction to the Kalman Filter[R]．Carolina:Department of Computer Science University of North Carolina,2006
[18] Hanselman D,Littlefield B．Mastering Matlab 7[M].Beijing:Tsinghua University Press,2006
[19] 葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007
[20] 周开利,康耀红.神经网络模型及MATLAB仿真程序设计[M].北京:清华大学出版社,2005

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed