[1]杨敏,丁剑,王炜.基于ARIMA-SVM模型的快速公交停站时间组合预测方法[J].东南大学学报(自然科学版),2016,46(3):651-656.[doi:10.3969/j.issn.1001-0505.2016.03.033]
 Yang Min,Ding Jian,Wang Wei.Hybrid dwell time prediction method for bus rapid transit based on ARIMA-SVM model[J].Journal of Southeast University (Natural Science Edition),2016,46(3):651-656.[doi:10.3969/j.issn.1001-0505.2016.03.033]
点击复制

基于ARIMA-SVM模型的快速公交停站时间组合预测方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第3期
页码:
651-656
栏目:
交通运输工程
出版日期:
2016-05-20

文章信息/Info

Title:
Hybrid dwell time prediction method for bus rapid transit based on ARIMA-SVM model
作者:
杨敏丁剑王炜
东南大学交通学院, 南京 210096; 东南大学江苏省城市智能交通重点实验室, 南京 210096; 东南大学现代城市交通技术协同创新中心, 南京 210096
Author(s):
Yang Min Ding Jian Wang Wei
School of Transportation, Southeast University, Nanjing 210096, China
Jiangsu Key Laboratory of Urban ITS, Southeast University, Nanjing 210096, China
Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing 210096, China
关键词:
差分自回归 支持向量机 组合预测方法 快速公交 停站时间
Keywords:
difference autoregression support vector machine(SVM) hybrid prediction method bus rapid transit dwell time
分类号:
U492.3
DOI:
10.3969/j.issn.1001-0505.2016.03.033
摘要:
为了研究快速公交(BRT)系统公交站台停靠时间的可靠预测技术,对BRT车辆在站台停靠的物理过程进行分析.该过程既具有纵向时间相关性,又受到其他交通子系统的非线性作用,因此将BRT车辆停站时间拆解成线性部分和非线性部分.分别采用差分自回归移动平均(ARIMA)模型和支持向量机(SVM)方法对两部分进行预测,并将预测结果叠加,构成一种快速公交停站时间的组合预测方法.以常州BRT 2号线2个快速公交站的停站时间数据及其相关数据为样本进行建模,建模结果表明该组合预测方法行之有效.相较于单一的ARIMA模型和SVM模型,组合模型停站时间预测值的平均相对百分误差、均方误差均明显降低,误差1 s内命中百分率提高,且在训练数据足够时,组合模型的平均相对百分误差、均方误差分别为0.62%和4.05 s2,误差1 s内命中百分率达到 96.79%.
Abstract:
To explore a reliable dwell time prediction technology through experiments, the physical process of bus rapid transit(BRT)when it stays at the stops is analyzed. Both the longitudinal correlation and nonlinear effects from other traffic subsystems are included in this process. Therefore, the dwell time can be divided into the linear and nonlinear parts. Accordingly, autoregressive integrated moving average(ARIMA)model and support vector machine(SVM)are adopted to predict these two parts, and the final prediction results are produced by combining the two parts. Thus, the hybrid dwell time prediction method for BRT is established. The dwell time and the relative data gained at two stops in BRT Line 2 in Changzhou are modeled. The results indicate that the hybrid prediction method is effective. Compared with the single ARIMA and SVM models, the hybrid prediction method has a sharp decline of the mean absolute error(MAPE)and the mean square error(MSE). Also, the target percent whose prediction error is less than 1 s significantly increases. Furthermore, the MAPE, MSE and the target percent can reach 0.62%, 4.05 s2 and 96.79%, respectively, when training data is enough.

参考文献/References:

[1] 杨震,王炜,陈淑燕,等. 干线公交绿波通行控制中公交专用相位的设置方法[J]. 东南大学学报(自然科学版),2014,44(4):854-858. DOI: 10.3969/j.issn.1001-0505.2014.04.031.
  Yang Zhen, Wang Wei, Chen Shuyan, et al. Setting methods of bus exclusive phase in bus green-wave control of urban arterial[J]. Journal of Southeast University(Natural Science Edition), 2014,44(4):854-858. DOI: 10.3969/j.issn.1001-0505.2014.04.031.(in Chinese)
[2] Li J, Wang W, van Zuylen H J, et al. Predictive strategy for transit signal priority at fixed-time signalized intersections [J]. Transportation Research Record: Journal of the Transportation Research Board, 2012, 2311: 124-131.
[3] Ma W J, Yang X G. Efficiency analysis of transit signal priority strategies on isolated intersection [J]. Journal of System Simulation, 2008, 20(12): 3309-3313.
[4] He Q, Head K L, Ding J. PAMSCOD: Platoon-based arterial multi-modal signal control with online data[J].Transportation Research Part C: Emerging Technologies, 2012, 20(1):164-184. DOI:10.1016/j.trc.2011.05.007.
[5] Kim W, Rilett L R. Improved transit signal priority system for networks with nearside bus stops [J]. Transportation Research Record: Journal of the Transportation Research Board, 2005, 1925: 205-214. DOI:10.3141/1925-21.
[6] Dai G Y, Wang H, Wang W. Signal optimization and coordination for bus progression based on MAXBAND[J]. KSCE Journal of Civil Engineering, 2015, 20(2):890-898. DOI:10.1007/s12205-015-1516-4.
[7] Yang M, Sun G, Wang W, et al. Evaluation of the pre-detective signal priority for bus rapid transit: Coordinating the primary and secondary intersections [J/OL]. Transport, 2015. DOI:10.3846/16484142. 2015.1004556.
[8] 李进燕, 朱征宇, 刘琳, 等. 基于简化路网模型的卡尔曼滤波多步行程时间预测方法[J]. 系统工程理论与实践, 2013, 33(5): 1289-1297. DOI:10.3969/j.issn.1000-6788.2013.05.026.
  Li Jinyan,Zhu Zhengyu,Liu Lin,et al. Multi-step Kalman filtering travel time estimation method based on simplified road network model [J]. System Engneering—Theory & Practice, 2013, 33(5): 1289-1297. DOI:10.3969/j.issn.1000-6788.2013.05.026.(in Chinese)
[9] Kisgyörgy L, Rilett L R. Travel time prediction by advanced neural network [J]. Periodica Polytechnica Civil Engineering, 2002, 46(1): 15-32.
[10] Shalaby A, Farhan A. Bus travel time prediction model for dynamic operations control and passenger information systems [C/OL]//TRB 82nd Annual Meeting. Washington, DC, 2003. http://www.civ.utoronto.ca/sect/traeng/its/downloads/civ1507-pubtran/lecture8-traveltimepred.pdf.
[11] 胡华, 高云峰, 刘志钢. 基于AVL数据的公交到站时间实时预测模型[J]. 重庆交通大学学报(自然科学版), 2012, 31(5):1014-1017, 1041. DOI:10.3969/j.issn.1674-0696.2012.05.23.
  Hu Hua, Gao Yunfeng, Liu Zhigang. Dynamic prediction model of bus arrival time based on AVL data[J]. Journal of Chongqing Jiaotong University(Natural Sciences), 2012, 31(5):1014-1017,1041. DOI:10.3969/j.issn.1674-0696.2012.05.23.(in Chinese)
[12] 黄宇, 张庆. 基于排队论的公交进站影响分析[J]. 交通运输系统工程与信息, 2010, 11(sup 1): 68-73.
  Huang Yu, Zhang Qing. Analysis of the influence to the buses entering stops based on queuing theory [J]. Journal of Transportation Systems Engineering and Information Technology, 2010, 11(sup1): 68-73.(in Chinese)
[13] 谭满春, 冯荦斌, 徐建闽. 基于ARIMA与人工神经网络组合模型的交通流预测[J]. 中国公路学报,2007, 20(4):118-121. DOI:10.3321/j.issn:1001-7372.2007.04.021.
  Tan Manchun, Feng Luobin, Xu Jianmin. Traffic flow prediction based on hybrid ARIMA and ANN model[J]. China Journal of Highway and Transport, 2007, 20(4):118-121. DOI:10.3321/j.issn:1001-7372.2007.04.021.(in Chinese)
[14] 姚智胜, 邵春福, 高永亮. 基于支持向量回归机的交通状态短时预测方法研究[J]. 北京交通大学学报, 2006, 30(3):19-22. DOI:10.3969/j.issn.1673-0291.2006.03.005.
  Yao Zhisheng, Shao Chunfu, Gao Yongliang. Research on methods of short-term traffic forecasting based on support vector regression[J]. Journal of Beijing Jiaotong University, 2006, 30(3):19-22. DOI:10.3969/j.issn.1673-0291.2006.03.005.(in Chinese)

相似文献/References:

[1]郝勇生,于向军,赵刚,等.基于改进粒子群算法的球磨机运行优化[J].东南大学学报(自然科学版),2008,38(3):419.[doi:10.3969/j.issn.1001-0505.2008.03.011]
 Hao Yongsheng,Yu Xiangjun,Zhao Gang,et al.Optimization for ball mill operation based on improved particle swarm optimization algorithm[J].Journal of Southeast University (Natural Science Edition),2008,38(3):419.[doi:10.3969/j.issn.1001-0505.2008.03.011]
[2]李晓东,费树岷,张涛.基于奇异值特征和支持向量机的人脸识别[J].东南大学学报(自然科学版),2008,38(6):981.[doi:10.3969/j.issn.1001-0505.2008.06.009]
 Li Xiaodong,Fei Shumin,Zhang Tao.Face recognition based on singular value feature and support vector machines[J].Journal of Southeast University (Natural Science Edition),2008,38(3):981.[doi:10.3969/j.issn.1001-0505.2008.06.009]
[3]靳一,吴乐南,冯熳,等.随机极性MCP-EBPSK传输性能[J].东南大学学报(自然科学版),2012,42(6):1031.[doi:10.3969/j.issn.1001-0505.2012.06.002]
 Jin Yi,Wu Lenan,Feng Man,et al.Transmission performance of MCP-EBPSK with random polar[J].Journal of Southeast University (Natural Science Edition),2012,42(3):1031.[doi:10.3969/j.issn.1001-0505.2012.06.002]
[4]张兵,邓卫.经济圈交通网络SVM评价方法[J].东南大学学报(自然科学版),2012,42(6):1227.[doi:10.3969/j.issn.1001-0505.2012.06.037]
 Zhang Bing,Deng Wei.SVM evaluation method of transportation network in economic circle[J].Journal of Southeast University (Natural Science Edition),2012,42(3):1227.[doi:10.3969/j.issn.1001-0505.2012.06.037]
[5]孙立,潘蕾,沈炯.基于LSSVM-GPC的流化床锅炉多变量协调控制方法[J].东南大学学报(自然科学版),2013,43(2):312.[doi:10.3969/j.issn.1001-0505.2013.02.016]
 Sun Li,Pan Lei,Shen Jiong.Multivariable coordinated control method of FBC boiler based on LSSVM-GPC[J].Journal of Southeast University (Natural Science Edition),2013,43(3):312.[doi:10.3969/j.issn.1001-0505.2013.02.016]
[6]王玉芳,严洪森.基于非线性模糊支持向量机的知识化制造模式与动态环境匹配分类方法[J].东南大学学报(自然科学版),2014,44(5):957.[doi:10.3969/j.issn.1001-0505.2014.05.015]
 Wang Yufang,Yan Hongsen,et al.Classification method of matching knowledgeable manufacturing mode with dynamic environment based on nonlinear fuzzy weight SVM[J].Journal of Southeast University (Natural Science Edition),2014,44(3):957.[doi:10.3969/j.issn.1001-0505.2014.05.015]
[7]黄杰,史啸.一种基于人体裸露皮肤形状的不良图像过滤系统[J].东南大学学报(自然科学版),2014,44(6):1111.[doi:10.3969/j.issn.1001-0505.2014.06.003]
 Huang Jie,Shi Xiao.Pornographic image filtering system based on shape of naked skin[J].Journal of Southeast University (Natural Science Edition),2014,44(3):1111.[doi:10.3969/j.issn.1001-0505.2014.06.003]
[8]郭圣文,池敏越,岑桂英,等.MR影像体素形态学的阿尔茨海默病自动分类方法[J].东南大学学报(自然科学版),2015,45(2):260.[doi:10.3969/j.issn.1001-0505.2015.02.012]
 Guo Shengwen,Chi Minyue,Cen Guiyin,et al.Automatic classification method of Alzheimer’s disease by voxel-based morphometry on MR images[J].Journal of Southeast University (Natural Science Edition),2015,45(3):260.[doi:10.3969/j.issn.1001-0505.2015.02.012]
[9]朱周,路小波,卫朋,等.基于超像素和支持向量机的车辆阴影检测算法[J].东南大学学报(自然科学版),2015,45(3):443.[doi:10.3969/j.issn.1001-0505.2015.03.006]
 Zhu Zhou,Lu Xiaobo,Wei Peng,et al.Vehicle shadow detection algorithm based on superpixel and SVM[J].Journal of Southeast University (Natural Science Edition),2015,45(3):443.[doi:10.3969/j.issn.1001-0505.2015.03.006]
[10]郭圣文,赖春任,汪文胜,等.颞叶癫痫病患者的脑皮层多特征分类[J].东南大学学报(自然科学版),2015,45(6):1057.[doi:10.3969/j.issn.1001-0505.2015.06.006]
 Guo Shengwen,Lai Chunren,Wang WenshengCheng Lina,et al.Classification using multiply cortical features of temporal lobe epilepsy patients[J].Journal of Southeast University (Natural Science Edition),2015,45(3):1057.[doi:10.3969/j.issn.1001-0505.2015.06.006]

备注/Memo

备注/Memo:
收稿日期: 2015-10-26.
作者简介: 杨敏(1981—),男,博士,教授,博士生导师,yangmin@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(51338003, 51378120)、国家重点基础研究发展计划(973计划)资助项目(2012CB725402).
引用本文: 杨敏,丁剑,王炜.基于ARIMA-SVM模型的快速公交停站时间组合预测方法[J].东南大学学报(自然科学版),2016,46(3):651-656. DOI:10.3969/j.issn.1001-0505.2016.03.033.
更新日期/Last Update: 2016-05-20