基于优化极限学习机的公交行程时间预测方法

doi:10.16088/j.issn.1001-6600.2020073102

摘要/Abstract

摘要： 为提高城市公交车辆行程时间的预测精度,在分析历史数据和交通流变化特性基础上,提出了一种基于人工蜂群优化的极限学习机的组合预测模型(artificial bee colony-extreme learning machine, ABC-ELM)。首先,基于GPS等数据提取站间距离、时间周期及天气情况等动静态特征因素;其次,推算出公交车辆的站点停靠时间;接着,将人工蜂群优化算法(artificial bee colony algorithm, ABC)嵌入到传统极限学习机算法(extreme learning machine, ELM)中,以解决其在行程时间预测中收敛速度慢、初始权值和阈值选择困难的问题;最后,基于ABC-ELM算法预测公交车辆在目标路段的行程时间。以深圳市620路公交车的真实运营数据为基础进行方法验证。结果表明:与广泛采用的BP神经网络、SVM和ELM相比,本文方法在不同道路环境中均能保持较低的预测误差(RMSE误差:高峰/平峰为11.91/8.72,工作日/非工作日为11.46/9.54,晴天/雨天为10.83/12.31;决定系数R²:高峰/平峰为0.87/0.92,工作日/非工作日为0.83/0.88,晴天/雨天为0.89/0.85),鲁棒性较强,更适用于复杂城市道路环境中的干线公交车辆的行程时间预测。

关键词: 城市交通, 公交车辆, 行程时间预测, 极限学习机, 人工蜂群算法

Abstract: In order to improve the prediction accuracy of bus travel time, a combined prediction model based on artificial bee colony optimization and extreme learning machine (artificial bee colony-extreme learning machine, ABC-ELM) are proposed after analyzing historical data and the characteristics of traffic flow. First, dynamic and static characteristics like distance between stations, time period and weather conditions are extracted by using IC card and GPS data; after that the dwell time of the station is calculated. Then, the artificial bee colony optimization algorithm (ABC) is embedded in the traditional extreme learning machine algorithm (ELM) to solve the problem of slow convergence speed and difficulty in selecting initial weights and thresholds ELM in bus travel time prediction. Finally, the travel time of the bus on target road section is predicted by using the ABC-ELM algorithm. The model is verified based on the real operating data of Shenzhen Bus 620. The results show that, compared with the widely used BP neural network, SVM and ELM, the method proposed in this paper can maintain lower prediction errors in different road environments and has strong robustness (the RMSE error in peak/off-peak hour is 11.91/8.72, in workday/non-work day is 11.46/9.54,in sunny/rainy day is 10.83/12.31; the coefficient of determination R² in peak/off-peak hour is 0.87/0.92 in workday/non-work day is 0.83/0.88, in sunny/rainy day is 0.89/0.85), which makes it more suitable for travel time prediction in complex urban road environment and for main line bus.

Key words: urban traffic, public bus, travel time prediction, extreme learning machine, artificial bee colony algorithm

中图分类号:

U491.17

许伦辉, 苏楠, 骈宇庄, 林培群. 基于优化极限学习机的公交行程时间预测方法[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 64-77.

XU Lunhui, SU Nan, PIAN Yuzhuang, LIN Peiqun. Bus Travel Time Prediction Based on Extreme Learning Machine Optimized by Artificial Bee Colony Algorithm[J]. Journal of Guangxi Normal University(Natural Science Edition), 2021, 39(5): 64-77.

参考文献

[1] 胡郁葱,宫曼琳,谢昳辰,等. 网络预约出租汽车营运模式的四方博弈模型[J]. 公路交通科技, 2020, 37(2):130-136.
[2] YU H Y,CHEN D G,WU Z H,et al. Headway-based bus bunching prediction using transit smart card data[J]. Transportation Research Part C:Emerging Technologies,2016,72:45-59. DOI:10.1016/j.trc.2016.09.007.
[3] HE P L,JIANG G Y,LAM S K,et al. Travel-time prediction of bus journey with multiple bus trips[J]. IEEE Transactions on Intelligent Transportation Systems,2019,20(11):4192-4205. DOI:10.1109/TITS.2018.2883342.
[4] MA J M,CHAN J,RISTANOSKI G,et al. Bus travel time prediction with real-time traffic information[J]. Transportation Research Part C:Emerging Technologies,2019,105:536-549. DOI:10.1016/j.trc.2019.06.008.
[5] KUMAR B A,VANAJAKSHI L,SUBRAMANIAN S C. Bus travel time prediction using a time-space discretization approach[J]. Transportation Research Part C:Emerging Technologies,2017,79:308-332. DOI:10.1016/j.trc.2017.04.002.
[6] 李华民,吴俊美,孙棣华,等. 基于RFID电子车牌数据的公交行程时间预测方法[J]. 中国公路学报,2019,32(8):165-173,182. DOI:10.19721/j.cnki.1001-7372.2019.08.015.
[7] 宋现敏,刘明鑫,马林,等. 基于极限学习机的公交行程时间预测方法[J]. 交通运输系统工程与信息,2018,18(5):136-142,150. DOI:10.16097/j.cnki.1009-6744.2018.05.020.
[8] 刘迎,过秀成,周润瑄,等. 基于多源数据融合的干线公交车辆行程时间预测[J]. 交通运输系统工程与信息,2019,19(4):124-129,148. DOI:10.16097/j.cnki.1009-6744.2019.04.018.
[9] 苗旭,王忠宇,吴兵,等. 考虑前序路段状态的公交到站时间双层BPNN预测模型[J]. 交通运输系统工程与信息,2020,20(2):127-133. DOI:10.16097/j.cnki.1009-6744.2020.02.019.
[10] BAI C,PENG Z R,LU Q C,et al. Dynamic bus travel time prediction models on road with multiple bus routes[J]. Computational Intelligence and Neuroscience,2015,2015:432389. DOI:10.1155/2015/432389.
[11] JEONG R,RILETT R. Bus arrival time prediction using artificial neural network model[C] // Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems. Piscataway,NJ:IEEE,2004:988-993. DOI:10.1109/ITSC.2004.1399041.
[12] KVIESIS A,ZACEPINS A,KOMASILOVS V,et al. Bus arrival time prediction with limited data set using regression models[C] // Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems- Volume 1: RESIST. Francisco:Science and Technology Publications,2018:643-647. DOI:10.5220/0006816306430647.
[13] 周雪梅,杨晓光,王磊. 公交车辆行程时间预测方法研究[J]. 交通与计算机,2002,20(6):12-14. DOI:10.3963/j.issn.1674-4861.2002.06.004.
[14] YU H Y,WU Z H,CHEN D W,et al. Probabilistic prediction of bus headway using relevance vector machine regression[J]. IEEE Transactions on Intelligent Transportation Systems,2017,18(7):1772-1781. DOI:10.1109/TITS.2016.2620483.
[15] YU B,LAM W H K,TAM M L. Bus arrival time prediction at bus stop with multiple routes[J]. Transportation Research Part C:Emerging Technologies,2011,19(6):1157-1170. DOI:10.1016/j.trc.2011.01.003.
[16] KARABOGA D,AKAY B,OZTURK C. Artificial bee colony (ABC) optimization algorithm for training feed-forward neural networks[C] // 2007 Modeling Decisions for Artificial Intelligence 4th International Conference. Berlin:Springer,2007:318-329. DOI:10.1007/978-3-540-73729-2_30.
[17] SHALABY A,FARHAN A. Prediction model of bus arrival and departure times using AVL and APC data[J]. Journal of Public Transportation,2004,7(1):41-61. DOI:10.5038/2375-0901.7.1.3.
[18] HUANG Z L,XU L H,LIN Y J,et al. Citywide metro-to-bus transfer behavior identification based on combined data from smart cards and GPS[J]. Applied Sciences,2019,9(17):3597. DOI:10.3390/app9173597.
[19] HUANG Z L, XU L H, LIN Y J. Multi-stage pedestrian positioning using filtered WiFi scanner data in an urban road environment[J]. Sensors, 2020, 20(11):3259. DOI:10.3390/s20113259.
[20] WU P,HUANG Z L,PIAN Y Z,et al. A combined deep learning method with attention-based LSTM model for short-term traffic speed forecasting[J]. Journal of Advanced Transportation, 2020, 2020:8863724. DOI:10.1155/2020/8863724.
[21] 王芳杰,王福建,王雨晨,等. 基于LightGBM算法的公交行程时间预测[J].交通运输系统工程与信息,2019,19(2):116-121. DOI:10.16097/j.cnki.1009-6744.2019.02.017.
[22] 韩勇,周林,高鹏,等. 基于BP神经网络的公交动态行程时间预测方法研究[J].中国海洋大学学报(自然科学版),2020,50(2):142-154. DOI:10.16441/j.cnki.hdxb.20180285.
[23] HUANG G B,ZHU Q Y,SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing,2006,70(1/2/3):489-501. DOI:10.1016/j.neucom.2005.12.126.
[24] KARABOGA D,BASTURK B. A powerful and efficient algorithm for numerical function optimization:artificial bee colony (ABC) algorithm[J]. Journal of global optimization,2007,39:459-471. DOI:10.1007/s10898-007-9149-x.
[25] 彭新建,翁小雄. 基于萤火虫算法优化BP神经网络的公交行程时间预测[J].广西师范大学学报(自然科学版),2017,35(1):28-36. DOI:10.16088/j.issn.1001-6600.2017.01.005.
[26] 尹安藤. 基于公交GPS和IC卡数据的公交OD推算[D]. 哈尔滨:哈尔滨工业大学,2017.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed