Short-term prediction of traffic state: Statistical approach versus machine learning approach

Document Type : Article

Authors

School of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, P.O. Box 14115-111, Iran

Abstract

Traffic short-term prediction helps intelligent transportation systems manage future travel demand. The objective of this paper is to predict the traffic state for Karaj to Chaloos, a suburban road in Iran. For this, two approaches, statistical and machine learning are investigated. We evaluate the performance of the multinomial logit model, the support vector machine, and the deep neural network as two machine learning techniques. The principal component analysis is used to reduce the dimension of the data in order to use the MNL model. SVM and DNN predict traffic state using both primary and reduced datasets (ALL and PCA). MNL can be used not only to compare the accuracy of models but also to estimate their explanatory power. SVM employing primarily datasets outperforms other models by 79% accuracy. Next, the prediction accuracy for SVM-PCA, MNL, DNN-PCA, and DNN-ALL are equal to 78%, 73%, 68%, and 67%. SVM-ALL has better performance for predicting light, heavy, and blockage states, while the semi-heavy state is predicted more accurately by MNL. Using the PCA dataset increases the accuracy of DNN but decreases SVM accuracy by 1%. More precision is achieved for the first three months of testing compared to the second three months.

Keywords

References

  1. References:

    1. Pan, T.L., Sumalee, A., Zhong, R.X., et al. “Short-term traffic state prediction based on temporal–spatial correlation”, IEEE trans. Intell. Transp. Syst., 14(3), pp. 1242-1254 (2013).
    2. Lee, W.H., Tseng, S.S. and Shieh, W.Y. “Collaborative real-time traffic information generation and sharing framework for the intelligent transportation system”, Inf. Sci., 180(1), pp. 62-70 (2010).
    3. Long, J., Gao, Z., Orenstein, P. et al. “Control strategies for dispersing incident-based traffic jams in two-way grid networks”, IEEE trans. Intell. Transp. Syst., 13(2), pp. 469-481 (2011).
    4. A. Rasaizadi A. Ardestani S.E. Seyedabrishami, “Traffic management via traffic parameters prediction by using machine learning algorithms”, Int. J. Hum. Cap. Urban Manag. , 6(1) pp. 57-68 (2021).
    5. Ishak, S. and Al-Deek, H.,. “Statistical evaluation of interstate 4 traffic prediction system”, Transp. Res. Rec., 1856(1), pp. 16-24 (2003).
    6. Liu, Q., Cai, Y., Jiang, H., et al. “Traffic state prediction using ISOMAP manifold learning”, Physica A, 506, pp. 532-541 (2018).
    7. Golshani, N., Shabanpour, R., Mahmoudifard, S. M., et al. “Modeling travel mode and timing decisions: Comparison of artificial neural networks and copula-based joint model”, Travel. Behav. Soc., 10, pp. 21-32 (2018).
    8. Vlahogianni, E.I., Golias, J.C. and Karlaftis, M.G., “Short‐term traffic forecasting: Overview of objectives and methods”, Transp. Rev., 24(5), pp. 533-557 (2004).
    9. Tang, J., Zheng, L., Han, C., et al. “Statistical and machine-learning methods for clearance time prediction of road incidents: A methodology review”, Anal. Methods Accid. Res. , 27, pp. 100123 (2020).
    10. Khanzode, K.C.A. and Sarode, R.D., “Advantages and Disadvantages of Artificial Intelligence and Machine Learning: A Literature Review”, Int. J. Lib. Inf. Sci. (IJLIS), 9(1), pp. 3 (2020).
    11. Loyola-Gonzalez, O. “Black-box vs. white-box: Understanding their advantages and weaknesses from a practical point of view”, IEEE Access, 7, pp. 154096-154113 (2019).
    12. Xu, D.W., Wang, Y.D., Jia, L.M., et al. “Real-time road traffic state prediction based on ARIMA and Kalman filter”, Front. Inf. Technol. Electron. Eng. , 18(2), pp. 287-302 (2017).
    13. Seyedabrishami, S. and Izadi, A.R., “A Copula-Based Joint Model to Capture the Interaction between Mode and Departure Time Choices in Urban Trips”, Transp. Res. Rec., 41, pp. 722-730 (2019).
    14. Lopez-Martin, M., Carro, B. and Sanchez-Esguevillas, “A., Neural network architecture based on gradient boosting for IoT traffic prediction”, Future Gener. Comput. Syst., 100, pp. 656-673 (2019).
    15. Luo, C., Huang, C., Cao, J.,  et al. “Short-term traffic flow prediction based on least square support vector machine with hybrid optimization algorithm”, Neural Process. Lett., 50(3), pp. 2305-2322 (2019).
    16. Li, L., Dai, S., Cao, Z., et al., “Using improved gradient-boosted decision tree algorithm based on Kalman filter (GBDT-KF) in time series prediction”, J. Supercomput., pp. 1-14 (2020).
    17. Yu, H., Ji, N., Ren, Y. et al. “A special event-based K-nearest neighbor model for short-term traffic state prediction”, IEEE Access, 7, pp. 81717-81729 (2019).
    18. Hardy, M. and Reynolds, J., “Incorporating categorical information into regression models: The utility of dummy variables”, Handbook of data analysis, pp. 229-255 (2004).
    19. Juhos, I., Makra, L. and Tóth, B., “Forecasting of traffic origin NO and NO2 concentrations by Support Vector Machines and neural networks using Principal Component Analysis”, Simul. Model. Pract. Theory., 16(9), pp.1488-1502 (2008).
    20. Moons, E., Wets, G., and Aerts, M. “Nonlinear models for determining mode choice”, Portuguese Conference on Artificial Intelligence (2007).
    21. Xie, C., Lu, J., and P., E. “Work travel mode choice modeling with data mining: decision trees and neural networks”, Transp. Res. Rec., 1854(1), pp. 50-61 (2003).
    22. Wang, S., and Zhao, J. “An Empirical Study of Using Deep Neural Network to Analyze Travel Mode Choice with Interpretable Economic Information”, Transp. Res. Rec., (2019).
    23. Nassiri, H., and Mohamadian Amiri, A. “Prediction of roadway accident frequencies: Count regressions versus machine learning models”, Sci. Iran., 21(2), pp. 263-275 (2014).
    24. Zhao, X., Yan, X., Yu, A., et al. “Prediction and behavioral analysis of travel mode choice: A comparison of machine learning and logit models”, Travel. Behav. Soc., 20, pp. 22-35 (2020).
    25. Abasahl, F., Kelarestaghi, K. B., and Ermagun, “A. Gender gap generators for bicycle mode choice in Baltimore college campuses”, Travel. Behav. Soc., 11, pp. 78-85 (2018).
    26. Rasaizadi, A., and Kermanshah, M. “Mode choice and number of non-work stops during the commute: Application of a copula-based joint model”, Sci. Iran., 25(3), pp. 1039-1047 (2018).
    27. Karlaftis, Ma, G, and Vlahogianni, E. I. “Statistical methods versus neural networks in transportation research: Differences, similarities and some insights”, Transp. Res. Part C Emerg. Technol., 19(3), pp. 387-399 (2011).
    28. Lee, D., Derrible, S., and Pereira, F. C. “Comparison of four types of artificial neural network and a multinomial logit model for travel mode choice modeling”, Transp. Res. Rec., 2672(49), pp. 101-112 (2018).
    29. Cheng, L., Chen, X., De Vos, J., et al. “Applying a random forest method approach to model travel mode choice behavior”, Travel. Behav. Soc., 14, pp. 1-10 (2019).
    30. Wang, F., and Ross, C. L. “Machine learning travel mode choices: Comparing the performance of an extreme gradient boosting model with a multinomial logit model”, Transp. Res. Rec., 2672(47), pp. 35-45 (2018).
    31. Hensher, D. A., and Ton, T T. “A comparison of the predictive potential of artificial neural networks and nested logit models for commuter mode choice”, TRANSPORT RES E-LOG, 36(3), pp. 155-172 (2000).
    32. Holanda F., and Maia, J. E. B. “Network traffic prediction using PCA and K-means”, 2010 IEEE Network Operations and Management Symposium-NOMS 2010 (2010).
    33. Jin, X., Zhang, Y., and Yao, D. “Simultaneously prediction of network traffic flow based on PCA-SVR”, International Symposium on Neural Networks (2007).
    34. Jin, X., Zhang, Y., Li, L., et al., “Robust PCA-based abnormal traffic flow pattern isolation and loop detector fault detection”, Tsinghua Sci. Technol., 13(6), pp. 829-835 (2008).
    35. Ferreira, Y. M., Lucas R. J., Eduardo P., et al. “Applying a Multilayer Perceptron for Traffic Flow Prediction to Empower a Smart Ecosystem”, International Conference on Computational Science and Its Applications (2019).
    36. Wu, Y., Tan, H., Qin, L., et al. “A hybrid deep learning based traffic flow prediction method and its understanding”, Transp. Res. Part C Emerg. Technol., 90, pp. 166-180 (2018).
    37. LeCun, Y., Bengio, Y., Hinton, G. “Deep learning”, Nature, 521(7553), pp. 436-444 (2015).
    38. Yuan, G., Li, T., and Hu, W. “A conjugate gradient algorithm for large-scale nonlinear equations and image restoration problems”, Appl. Numer. Math., 147, pp. 129-141 (2020).
    39. Seyedabrishami, S. E., Izadi, A. R., Rayaprolu, H. S., et al. “Car ownership: A joint model for number of cars and fuel types”, Transp. Res. Rec., 41, pp. 572-576 (2019).
    40. Jafari Shahdani F, Rasaizadi A, Seyedabrishami S. “The interaction between activity choice and duration: Application of Copula-based and Nested-logit models”. Sci. Iran. (2020).
    41. Ben-Akiva, Mm. E, Lerman, S. R., and Lerman, S. R. “Discrete choice analysis: theory and application to travel demand”, 9, MIT press (1985).
    42. Nash, J. C. “On best practice optimization methods in R”,   J. Stat. Softw., 60(2), pp. 1-14 (2014).
    43. Iranitalab, A., and  Khattak, A. “Comparison of four statistical and machine learning methods for crash severity prediction”, Accid. Anal. Prev., 108, pp. 27-36 (2017).
    44. Kabli, A., Bhowmik, T., and Eluru, N. “A multivariate approach for modeling driver injury severity by body region”, Anal. Methods Accid. Res. , 28, pp. 100129 (2020).
    45. Keya, N., Anowar, S., Bhowmik, T., et al. “A joint framework for modeling freight mode and destination choice: Application to the US commodity flow survey data”, TRANSPORT RES E-LOG, 146, pp. 102208 (2021).
    46. Wang, K., Bhowmik, T., Yasmin, S., et al. “Multivariate copula temporal modeling of intersection crash consequence metrics: a joint estimation of injury severity, crash type, vehicle damage and driver error”, Accid. Anal. Prev., 125, pp. 188-197 (2019).
    47. Zhang, J., Li, Z., Pu, Z., et al. “Comparing prediction performance for crash injury severity among various machine learning and statistical methods”, IEEE Access, 6, pp. 60079-60087 (2018).
    48. Wang, X., An, K., Tang, L., et al. “Short term prediction of freeway exiting volume based on SVM and KNN”, Int. J. Trans. Sci. Tech., 4(3), pp. 337-352 (2015).
    49. Han, S., Qubo, C., and Meng, H. “Parameter selection in SVM with RBF kernel function”, World Automation Congress 2012 (2012).
    50. Skrandies, W. “Data reduction of multichannel fields: global field power and principal component analysis”, Brain Topogr., 2(1-2), pp. 73-80 (1989).
    51. Aguilera, A., and Escabias, M. “Solving multicollinearity in functional multinomial logit models for nominal and ordinal responses”, Func. Oper. Stat., pp. 7-13, Springer (2008).
    52. Du, K., and Swamy, M. “Principal component analysis”, Neural Netw. Stat. Lear., pp. 373-425, Springer (2019).
Scientia Iranica
Volume 29, Issue 3
Transactions on Civil Engineering (A)
May and June 2022
Pages 1095-1106

Files

Share

How to cite

Statistics