Short-term Traffic Flow Prediction at Urban Intersections Based on Quantile Regression and Bayesian Networks
Main Article Content
Keywords
traffic flow forecasting, quantile regression, Bayesian networks, abnormal fluctuations, peak traffic
Abstract
With the advancement of urbanization, intersections—key nodes in road networks—frequently become hotspots for traffic congestion and accidents. Their multi-phase signal control, lane turning diversion, and upstream-downstream interaction lead to traffic flow with complex spatiotemporal correlations and nonlinear fluctuations. This study proposes a hybrid model integrating quantile regression and Bayesian networks to enhance prediction accuracy and robustness under complex conditions. Raw data from Wuchang District’s traffic monitoring system undergo cleaning, missing-value imputation, and normalization. Quantile regression models fit 0.1, 0.5, and 0.9 quantiles to capture low, medium, and high traffic states, reflecting predictive distributions. Simultaneously, a Bayesian network analyzes causal relationships between external factors (weather, holidays, accidents) and traffic flow, quantifying influences via conditional probabilities. The two components are integrated into a framework accounting for both flow distribution and external disturbances. Methodologically, quantile regression provides preliminary estimates, which are dynamically adjusted by the Bayesian network’s conditional probabilities to address anomalous fluctuations. Experimental results show the hybrid model outperforms traditional linear regression and time-series models in handling fluctuations, especially during peak periods, improving forecasting precision and robustness while supporting traffic management decisions in complex scenarios.
References
- [1] National Bureau of Statistics. China Statistical Yearbook 2022 [M]. Beijing: China Statistics Press, 2022: 945.
- [2] Central Committee of the Communist Party of China and the State Council. Outline for Building a Transport Power [J]. Journal of Waterway and Harbor, 2019, 40(06): 628.
- [3] Wang X M. Dynamic Real-time Feedback Control of Traffic Signals in Urban Oversaturated Road Networks [D]. Dalian: Dalian Maritime University, 2018.
- [4] Xiang J P. Research on Regional Balanced Control Methods and Applications of Urban Road Traffic Signals [D]. Hefei: University of Science and Technology of China, 2018.
- [5] Wei F, Li X, Guo Y, et al. Flow Direction Level Traffic Flow Prediction Based on a GCN-LSTM Combined Model [J]. Intelligent Automation & Soft Computing, 2023, 37(2): 2001–2018.
- [6] Zhang J F. Research on Short-term Traffic Flow Prediction Methods at Urban Intersections [D]. Kunming: Kunming University of Science and Technology, 2018.
- [7] Fan Y Y. Review of the Development and Prospect of Intelligent Transportation Systems [J]. Xinjiang Transportation Science & Technology, 2014, (4): 90-96.
- [8] Shi Y F. Research on Traffic Flow Optimization Control Strategies Under Vehicle-infrastructure Cooperation [D]. Jinan: Shandong University, 2017.
- [9] Tian X J. Research on Traffic Signal Control Optimization Methods Under Unsaturated Conditions [D]. Changchun: Jilin University, 2018.
- [10] Williams B M. Multivariate vehicular traffic flow prediction: evaluation of ARIMAX modeling [J]. Transportation Research Record: Journal of the Transportation Research Board, 2001, 01-3488: 194–200.
- [11] Sun H, Liu H X, Xiao H, et al. Short term traffic forecasting using the local linear regression model[C]. In 82nd Annual Meeting of the Transportation Research Board, Washington, DC, 2003.
- [12] Wang Y, Papageorgiou M. Real-time freeway traffic state estimation based on extended Kalman filter: a general approach [J]. Transportation Research Part B: Methodological, 2005, 39(2): 141-167.
- [13] Chandra S R, Al-Deek H. Predictions of freeway traffic speeds and volumes using vector autoregressive models [J]. Journal of Intelligent Transportation Systems, 2009, 13(2): 53–72.
- [14] Selvaraj Vasantha Kumar. Traffic flow prediction using kalman filtering technique[C]. 10th International Scientific Conference Transbaltica 2017: Transportation Science and Technology. Procedia Engineering, 2017, 187: 582 – 587.
- [15] Marković H, Dalbelo Bašić B, Gold H, et al. GPS data-based non-parametric regression for predicting travel times in urban traffic networks [J]. Promet–Traffic & Transportation, 2010, 22 (1): 1-13.
- [16] Habtemichael F G, Cetin M. Short-term traffic flow rate forecasting based on identifying similar traffic patterns [J]. Transportation Research Part C: Emerging Technologies, 2016, 66: 61-78.
- [17] Chan K Y, Dillon T, Chang E, et al. Prediction of short-term traffic variables using intelligent swarm-based neural networks [J]. IEEE Transactions on Control Systems Technology, 2013, 21(1): 263–274.
- [18] Yu C Y, Lam K C. Applying multiple kernel learning and support vector machine for solving the multicriteria and nonlinearity problems of traffic flow prediction [J]. Journal of Advanced Transportation, 2014, 48(3): 250–271.
- [19] Kumar K, Parida M, Katiyar V K. Short term traffic flow prediction in heterogeneous condition using artificial neural network [J]. Transport, 2015, 30 (4): 397-405.
- [20] Cai P L, Wang Y P, Lu G Q, et al. A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting [J]. Transportation Research Part C: Emerging Technologies, 2016, 62: 21-34.
- [21] Zeng D, Xu J, Gu J, et al. Short-term traffic flow prediction using hybrid ARIMA and ANN models[C]. 2008 Workshop on Power Electronics and Intelligent Transportation System, Guangzhou, China, 2008: 621-625.
- [22] Zhang Y, Liu Y C. Analysis of peak and non-peak traffic forecasts using combined models [J]. Journal of Advanced Transportation, 2011, 45(1): 21–37.
- [23] Li L H, He S L, Zhang J, et al. Short-term highway traffic flow prediction based on a hybrid strategy considering temporal–spatial information [J]. Journal of Advanced Transportation, 2016, 50: 2029–2040.
- [24] Liu Z, Guo J, Cao J, et al. A hybrid short-term traffic flow forecasting method based on neural networks combined with K-nearest neighbor [J]. Promet–Traffic & Transportation, 2018, 30(4): 445-456.
- [25] Vlahogianni E I, Golias J C, et al. Short-term traffic forecasting: overview of objectives and methods [J]. Transport Reviews, 2004, 24(5): 533-557.
- [26] HOSSEINI H. Traffic flow prediction using MI algorithm and considering noisy and data loss conditions: an application to Minnesota traffic flow prediction[J]. Promet–Traffic & Transportation, 2014, 26(5): 393-403.
- [27] TIAN X, YU D, XING X, et al. Hybrid short-term traffic flow prediction model of intersections based on improved complete ensemble empirical mode decomposition with adaptive noise[J]. Advances in Mechanical Engineering, 2019, 11(4).
- [28] QU W, LI J, YANG L, et al. Short-term intersection traffic flow forecasting[J]. Sustainability, 2020, 12(19): 8158.
- [29] Qu W, Li J, Song W, et al. Entropy-Weight-Method-Based Integrated Models for Short-Term Intersection Traffic Flow Prediction [J]. Entropy, 2022, 24(7): 849.
- [30] Ye B-L, Zhu S, Li L, et al. Short-term traffic flow prediction at isolated intersections based on parallel multi-task Learning [J]. Systems Science & Control Engineering, 2024, 12(1).
- [31] Xiao Y, Yin Y. Hybrid LSTM Neural Network for Short-Term Traffic Flow Prediction [J]. Information, 2019, 10(3): 105.
- [32] Liu S, Lin W T, Wang Y, et al. Convolutional Neural Network-Based Bidirectional Gated Recurrent Unit–Additive Attention Mechanism Hybrid Deep Neural Networks for Short-Term Traffic Flow Prediction [J]. Sustainability, 2024.
- [33] Huang M-L. Intersection traffic flow forecasting based on ν-GSVR with a new hybrid evolutionary Algorithm [J]. Neurocomputing, 2015, 147: 343–349.
- [34] Dai J, Sun M, Shi Q. Short-Term Traffic Volume Prediction Based on Gray Wolf Optimization Algorithm [M]//Smart Innovation, Systems and Technologies. Springer Singapore, 2021: 221–226.
- [35] Wei F, Li X, Guo Y, et al. Flow Direction Level Traffic Flow Prediction Based on a GCN-LSTM Combined Model [J]. Intelligent Automation & Soft Computing, 2023, 37(2): 2001–2018.
- [36] Chen K, Zhao S, Zhang D Y. Short-term Traffic Flow Prediction based on Data-Driven K-nearest neighbour Nonparametric Regression [C]. Journal of Physics: Conference Series, 2019, 1213.
- [37] Qin X, Yin D, Dong X, et al. Passenger flow prediction of scenic spots in Jilin Province based on convolutional neural network and improved quantile regression long short-term memory network[J]. ISPRS International Journal of Geo-Information, 2022, 11(4): 509.
- [38] Liu H, Ren J, Wang Z. Short-term passenger flow prediction strategy of urban rail transit based on ridge regression and LSTM[C]. 2023 IEEE International Conference on Control, Electronics and Computer Technology (ICCECT), 2023: 530-534.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.