|Table of Contents|

[1] ZHANG Bing, WU Shuang, LIU Ying, NI Xunyou, et al. Bus arrival interval prediction model based on gated recurrent unit network [J]. Journal of Southeast University (English Edition), 2025, 41 (2): 226-234. [doi:10.3969/j.issn.1003-7985.2025.02.012]
Copy

Bus arrival interval prediction model based on gated recurrent unit network()
基于门控循环单元网络的公交到站区间预测模型
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
41
Issue:
2025 2
Page:
226-234
Research Field:
Traffic and Transportation Engineering
Publishing date:
2025-06-17

Info

Title:
Bus arrival interval prediction model based on gated recurrent unit network
基于门控循环单元网络的公交到站区间预测模型
Author(s):
ZHANG Bing1, WU Shuang1, LIU Ying2, NI Xunyou1, LIU Kexin1
1.School of Transportation Engineering, East China Jiaotong University, Nanchang 330013, China
2.Jiangxi Comprehensive Transportation Development Research Center, Nanchang 330036, China
张兵1, 吴双1, 刘颖2, 倪训友1, 刘苛心1
1.华东交通大学交通运输工程学院，南昌 330013
2.江西省综合交通运输发展研究中心，南昌 330036
Keywords:
public transportation;  gated recurrent unit network;  attention mechanism;  lower upper bound estimation
公共交通; 门控循环单元网络; 注意力机制; 区间上下限法
PACS:
U491.17
DOI:
10.3969/j.issn.1003-7985.2025.02.012
Abstract:
By analyzing the bus operation environment and accounting for prediction uncertainties, a bus arrival interval prediction model was developed utilizing a gated recurrent unit (GRU) neural network. To reduce the impact of irrelevant data and boost prediction accuracy, an attention mechanism was integrated into the point model to concentrate on important input sequence information. Based on the point predictions, the lower upper bound estimation (LUBE) method was used, providing a range for the bus interval times predicted by the model. The model was validated using data from 169 bus routes in Nanchang, Jiangxi Province. The results indicated that the attention-GRU model outperformed neural network, long short-term memory and GRU models. Compared with the Bootstrap method, the LUBE method has a narrower average interval width. The coverage width-based criterion (CWC) was reduced by 8.1%, 2.2%, and 5.7% at confidence levels of 85%, 90%, and 95%, respectively, during the off-peak period, and by 23.2%, 26.9%, and 27.3% at confidence levels of 85%, 90%, and 95%, respectively, during the peak period. Therefore, it can accurately describe the fluctuation range in bus arrival times with higher accuracy and stability.
通过分析公交运行环境，考虑模型预测的不确定性，提出了一种基于门控循环单元（GRU）神经网络的公交到站区间预测模型。首先引入注意力机制，聚焦于输入序列中的关键信息，减少冗余信息的干扰，提高模型的整体预测性能。然后，在点预测的基础上，采用区间上下限（LUBE）法进行公交到站时间的区间预测，以确定模型预测的区间范围。最后，采用江西省南昌市169路的数据对所提模型进行实例验证。结果表明，Attention‑GRU模型的均方根误差及平均绝对误差均优于循环神经网络、长短期记忆网络及门控循环单元网络。相较于Bootstrap方法，LUBE法具有更窄的区间平均宽度，覆盖宽度标准（CWC）在平峰期置信水平为85%、90%、95%时分别降低8.1%、2.2%、5.7%，在高峰期置信水平为85%、90%、95%时分别降低23.2%、26.9%、27.3%，说明其能精确描述公交到站时间的波动范围，具有更高的准确性和稳定性。

References:

[1]ACHAR A, NATARAJAN A, REGIKUMAR R, et al. Predicting public transit arrival: A nonlinear approach[J]. Transportation Research Part C: Emerging Technologies, 2022, 144: 103875.
[2]LAI Y W, EASA S, SUN D Z, et al. Bus arrival time prediction using wavelet neural network trained by improved particle swarm optimization[J]. Journal of Advanced Transportation, 2020, 2020: 7672847.
[3]LEE C, YOON Y. A novel bus arrival time prediction method based on spatio-temporal flow centrality analysis and deep learning[J]. Electronics, 2022, 11(12): 1875.
[4]HUA X D, YANG J Q, WANG W, et al. Combined prediction model of bus arrival time based on data fusion[J]. Journal of Highway and Transportation Research and Development, 2019, 36(2): 112-120. (in Chinese)
[5]HUANG Y S, HAN L. Short-term passenger flow prediction at bus stations based on improved extreme learning machine[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(4): 115-123. (in Chinese)
[6]LAI Y W, WANG Y M. Bus arrival time CEEMD-LSTM prediction model using AVL data[J]. Journal of Fuzhou University (Natural Science Edition), 2023,51(6):819-826. (in Chinese)
[7]CHEN J, CHEN X H. Travel time prediction model of freeway based on gradient boosting decision tree [J]. Journal of Southeast University(English Edition),2019,35(3):393-398.
[8]HUANG Y P, CHEN C, SU Z C, et al. Bus arrival time prediction and reliability analysis: An experimental comparison of functional data analysis and Bayesian support vector regression[J]. Applied Soft Computing, 2021, 111: 107663.
[9]ACHAR A, BHARATHI D, KUMAR B A, et al. Bus arrival time prediction: A spatial Kalman filter approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(3): 1298-1307.
[10]KUANG X Y, LUO H C, ZHONG R, et al. Prediction model of bus arrival time based on CS-SNN[J]. Transducer and Microsystem Technologies, 2021, 40(3): 30-33. (in Chinese)
[11]XU W X, SHEN Y D. Bus travel time prediction based on Attention-LSTM neural network[J]. Modern Electronic Technology, 2022, 45(3): 83-87. (in Chinese)
[12]ASHWINI B P, SUMATHI R, SUDHIRA H S. Bus travel time prediction: A comparative study of linear and non-linear machine learning models[J]. Journal of Physics: Conference Series, 2022, 2161(1): 012053.
[13]WANG Z Y, LI P G, YANG H, et al. Road travel time prediction model based on improved spatiotemporal graph convolutional network [J]. Journal of Southeast University (Natural Science), 2024, 54(4):1022-1029. (in Chinese)
[14]LIU Z Z. Research on prediction method of bus arrival time based on combined model of GRU and Kalman filtering[J]. China-Arab States Science and Technology Forum, 2022(9): 100-104. (in Chinese)
[15]PATTANAMEKAR P, PARK D, RILETT L R, et al. Dynamic and stochastic shortest path in transportation networks with two components of travel time uncertainty[J]. Transportation Research Part C: Emerging Technologies, 2003, 11(5): 331-354.
[16]MAZLOUMI E, ROSE G, CURRIE G, et al. Prediction intervals to account for uncertainties in neural network predictions: Methodology and application in bus travel time prediction[J]. Engineering Applications of Artificial Intelligence, 2011, 24(3): 534-542.
[17]ZHAO W X, WANG G J, WANG Z, et al. A uncertainty visual analytics approach for bus travel time[J]. Visual Informatics, 2022, 6(4): 1-11.
[18]SHEN J, ZHAO J D, GAO Y, et al. Probabilistic interval prediction of metro-to-bus transfer passenger flow in the trip chain [J]. Journal of Southeast University (English Edition), 2022, 38(4):408-417.
[19]ZHANG C, LIN G Q, KUANG Y. Short-term photovoltaic output interval prediction based on MEEMD-QUATRE-BILSTM[J]. Acta Energiae Solaris Sinica, 2023, 44(11): 40-54. (in Chinese)
[20]CUI X W, YU X Y, NIU D X. The ultra-short-term wind power point-interval forecasting model based on improved variational mode decomposition and bidirectional gated recurrent unit improved by improved sparrow search algorithm and attention mechanism[J]. Energy, 2024, 288: 129714.
[21]SUN P Q, LIU Z K, WANG J Z, et al. Interval forecasting for wind speed using a combination model based on multiobjective artificial hummingbird algorithm[J]. Applied Soft Computing, 2024, 150: 111090.
[22]KHOSRAVI A, NAHAVANDI S, CREIGHTON D, et al. Lower upper bound estimation method for construction of neural network-based prediction intervals[J]. IEEE Transactions on Neural Networks, 2011, 22(3): 337-346.
[23]ZHANG B, ZHOU D D, SUN J, et al. Bus arrival time prediction model based on bidirectional long short-term memory network [J]. Transportation System Engineering and Information,2023,23(2):148-160. (in Chinese)
[24]China National Meteorological Information Center. China meteorological data network [EB/OL]. (2021-10-20)[2024-06-29]. https://data.cma.cn/.
[25]LI R R, JIN Y. A wind speed interval prediction system based on multi-objective optimization for machine learning method[J]. Applied Energy, 2018, 228: 2207-2220.

Memo

Memo:
Received 2024-08-05,Revised 2024-09-28.
Biography:Zhang Bing (1981—), male, doctor, professor, zhangbing @ecjtu.edu.cn.
Foundation items:The National Natural Science Foundation of China (No. 52162042), General Science and Technology Project of Jiangxi Provincial Department of Transportation (No. 2024YB039).
Citation:ZHANG Bing,WU Shuang,LIU Ying,et al.Bus arrival interval prediction model based on gated recurrent unit network[J].Journal of Southeast University (English Edition),2025,41(2):226-234.DOI:10.3969/j.issn.1003-7985.2025.02.012.DOI:10.3969/j.issn.1003-7985.2025.02.012
Last Update: 2025-06-20