Travel time prediction with machine learning: competition of linear regression, multivariate regression, random forest and deep neural network

rezaee, zahra; Aghamohammadi, Hossein; Vahidnia, Mohammad H; Azizi, Zahra; Behzadi, Saeed

doi:10.61186/jgst.14.2.1

[Home ] [Archive]

[ فارسی ]

Journal of Geomatics Science and Technology

Main Menu

Home

Browse

Journal Info

Guide for Authors

Submit Manuscript

Articles archive

For Reviewers

Contact us

Site Facilities

Reviewers

Search in website

Receive site information

Volume 14, Issue 2 (12-2024)

JGST 2024, 14(2): 1-18

Back to browse issues page

Travel time prediction with machine learning: competition of linear regression, multivariate regression, random forest and deep neural network

Zahra Rezaee

, Hossein Aghamohammadi ^*

, Mohammad H Vahidnia

, Zahra Azizi

, Saeed Behzadi

Abstract: (270 Views)

Accurate travel time prediction is one of the important issues in the field of traffic and transportation that can significantly affect the daily life of people and organizations. In this research, four different machine learning methods including linear regression, multivariate regression, random forest and deep artificial neural network were trained to predict travel time. The purpose of this research is to predict travel time for use in intelligent traffic systems and to use and compare several new methods, including deep neural network and random forest regression, as well as considering new parameters in the computations such as weather conditions, traffic flow, travel time, and accidents and the traffic locking points compared to other studies are the innovation and comprehensiveness of this study compared to other studies. In the design and implementation of this research, real traffic data taken from Google map was used and analyzed. This data includes information such as traffic conditions, season, time of day, weather conditions, and route characteristics. The results of this research show that the deep neural network (DNN) model with R2 equal to 0.833 has a very good performance among the investigated models. This model explains 0.833% of the variance of the data and the distribution of the residuals in it is relatively central with a mean of zero and a distribution close to normal. The linear regression model with R2 equal to 0.615 has a poorer performance than DNN and explains 0.615% of the data variance. But the random regression model with R2 equal to 0.955 has one of the best performances in competition with DNN and explains 0.955% of the data variance. MSE and RMSE parameters were also used to evaluate the performance of the models, and as a result, a multidimensional comparison was made between the models, and the random forest model resulted in the lowest error values. Since in the collected traffic data, traffic accidents and consequently traffic locking points are also used in the models, and considering that the random forest model is more effectively adapted to the data despite the presence of noise and anomaly, the R2 value of this model is higher than R2 of Deep neural networks, due to the overfitting nature of Deep Learning methods.

Article number: 1

Keywords: Travel Time, Linear Regression, Multivariate Regression, Random Forest, Deep Learning

Full-Text [PDF 1585 kb] (161 Downloads)

Type of Study: Research | Subject: GIS
Received: 2024/07/18

References

1. Sheng Z, Lv Z, Li J, Xu Z. Deep spatial-temporal travel time prediction model based on trajectory feature. Computers and Electrical Engineering. 2023 Sep 1;110:108868. [DOI:10.1016/j.compeleceng.2023.108868]

2. Abdollahi M, Khaleghi T, Yang K. An integrated feature learning approach using deep learning for travel time prediction. Expert Systems with Applications. 2020 Jan 1;139:112864. [DOI:10.1016/j.eswa.2019.112864]

3. Bai M, Lin Y, Ma M, Wang P. Travel-time prediction methods: a review. InSmart Computing and Communication: Third International Conference, SmartCom 2018, Tokyo, Japan, December 10-12, 2018, Proceedings 3 2018 (pp. 67-77). Springer International Publishing. [DOI:10.1007/978-3-030-05755-8_7]

4. Fani, Amir Hossein, Naseri, Hamed, Golro, Amir. Modeling the travel time of urban roads using linear regression and time series methods. Traffic engineering, 1400; 1400(85): 21-30 (In Persian)

5. Zhao M, Zhang X, Appiah J, Fontaine MD. Travel Time Reliability Prediction Using Random Forests. Transportation Research Record. 2024 Mar;2678(3) [DOI:10.1177/03611981231182146]

6. Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamaría J, Fadhel MA, Al-Amidie M, Farhan L. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of big Data. 2021 Dec;8:1-74. [DOI:10.1186/s40537-021-00444-8]

7. Talaei Khoei T, Ould Slimane H, Kaabouch N. Deep learning: Systematic review, models, challenges, and research directions. Neural Computing and Applications. 2023 Nov;35(31):23103-24. [DOI:10.1007/s00521-023-08957-4]

8. Rasa Izadi, Abrishmi, Seyyed Ehsan. Forecasting the traffic situation with machine learning algorithms for short-term and medium-term time horizons. Amirkabir Civil Engineering Journal. 2022 Jun 22;54(4):1503-20 (In Persian)

9. Wen Y, Wu R, Zhou Z, Zhang S, Yang S, Wallington TJ, Shen W, Tan Q, Deng Y, Wu Y. A data-driven method of traffic emissions mapping with land use random forest models. Applied Energy. 2022 Jan 1;305:117916. [DOI:10.1016/j.apenergy.2021.117916]

10. Tedjopurnomo DA, Bao Z, Zheng B, Choudhury FM, Qin AK. A survey on modern deep neural network for traffic prediction: Trends, methods and challenges. IEEE Transactions on Knowledge and Data Engineering. 2020 Jun 9;34(4):1544-61.

11. Peng H, Du B, Liu M, Liu M, Ji S, Wang S, Zhang X, He L. Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Information Sciences. 2021 Nov 1;578:401-16 [DOI:10.1016/j.ins.2021.07.007]

12. Sayed SA, Abdel-Hamid Y, Hefny HA. Artificial intelligence-based traffic flow prediction: a comprehensive review. Journal of Electrical Systems and Information Technology. 2023 Mar 9;10(1):13. [DOI:10.1186/s43067-023-00081-6]

13. Yassin SS, Pooja. Road accident prediction and model interpretation using a hybrid K-means and random forest algorithm approach. SN Applied Sciences. 2020 Sep;2:1-3. [DOI:10.1007/s42452-020-3125-1]

14. Abdullah SM, Periyasamy M, Kamaludeen NA, Towfek SK, Marappan R, Kidambi Raju S, Alharbi AH, Khafaga DS. Optimizing traffic flow in smart cities: Soft GRU-based recurrent neural networks for enhanced congestion prediction using deep learning. Sustainability. 2023 Mar 29;15(7):5949. [DOI:10.3390/su15075949]

15. Yan, M., et al. (2022). "Deep learning in traffic flow forecasting: A review of methodologies and applications." Transportation Research Part C: Emerging Technologies, 135, 103567.

16. Chen, C.M., Liang, C.C., Chu, C.P., 2020a. Long-term travel time prediction using gradient boosting. Journal of Intelligent Transportation Systems 24, 109-124. [DOI:10.1080/15472450.2018.1542304]

17. Li, H., Wang, Q., Xiong, W., 2021b. New model of travel-time prediction considering weather conditions: Case study of urban expressway. Journal of Transportation Engineering, Part A: Systems 147, 04020161. [DOI:10.1061/JTEPBS.0000491]

18. Muhammad I, Yan Z. SUPERVISED MACHINE LEARNING APPROACHES: A SURVEY. ICTACT Journal on Soft Computing. 2015 Apr 1;5(3).

19. Shaygan M, Meese C, Li W, Zhao XG, Nejad M. Traffic prediction using artificial intelligence: Review of recent advances and emerging opportunities. Transportation research part C: emerging technologies. 2022 Dec 1;145:103921. [DOI:10.1016/j.trc.2022.103921]

20. Aliahmadi A, Jafari-Eskandari M, Mozafari A, Nozari H. Comparing linear regression and artificial neural networks to forecast total productivity growth in Iran. International Journal of Information, Business and Management. 2016 Feb 1;8(1):93.

21. Wu HC. Fuzzy estimates of regression parameters in linear regression models for imprecise input and output data. Computational Statistics & Data Analysis. 2003 Feb 28;42(1-2):203-17 [DOI:10.1016/S0167-9473(02)00116-0]

22. Liaw A, Wiener M. Classification and regression by randomForest. R news. 2002 Dec 3;2(3):18-22.

23. Schonlau M, Zou RY. The random forest algorithm for statistical learning. The Stata Journal. 2020 Mar;20(1):3-29. [DOI:10.1177/1536867X20909688]

24. Bratsas C, Koupidis K, Salanova JM, Giannakopoulos K, Kaloudis A, Aifadopoulou G. A comparison of machine learning methods for the prediction of traffic speed in urban places. Sustainability. 2019 Dec 23;12(1):142. [DOI:10.3390/su12010142]

25. Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M, Chica-Rivas MJ. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geology Reviews. 2015 Dec 1;71:804-18. [DOI:10.1016/j.oregeorev.2015.01.001]

26. Menze BH, Kelm BM, Masuch R, Himmelreich U, Bachert P, Petrich W, Hamprecht FA. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC bioinformatics. 2009 Dec;10:1-6. [DOI:10.1186/1471-2105-10-213]

27. Rithani M, Kumar RP, Doss S. A review on big data based on deep neural network approaches. Artificial Intelligence Review. 2023 Dec;56(12):14765-801. [DOI:10.1007/s10462-023-10512-5]

28. Kiliçarslan S, Celik M. RSigELU: A nonlinear activation function for deep neural networks. Expert Systems with Applications. 2021 Jul 15;174:114805. [DOI:10.1016/j.eswa.2021.114805]

29. B. Azman, S. Hussain, N. Azmi, M. Ghani and N. Norlen, Prediction of distant recurrence in breast cancer using a deep neural network, Rev. int. métodos numér. Cálc. diseño ing. (2022). Vol. 38, (1), https://www.scipedia.com/public/Azman_et_al_2021a [DOI:10.23967/j.rimni.2022.03.006]

30. Dhruv P, Naskar S. Image classification using convolutional neural network (CNN) and recurrent neural network (RNN): A review. Machine learning and information processing: proceedings of ICMLIP 2019. 2020:367-81. [DOI:10.1007/978-981-15-1884-3_34]

31. Lee K, Eo M, Jung E, Yoon Y, Rhee W. Short-term traffic prediction with deep neural networks: A survey. IEEE Access. 2021 Apr 5;9:54739-56. [DOI:10.1109/ACCESS.2021.3071174]

32. Khajeh Hosseini M, Talebpour A. Traffic prediction using time-space diagram: a convolutional neural network approach. Transportation Research Record. 2019 Jul;2673(7):425-35. [DOI:10.1177/0361198119841291]

33. Jiang W, Luo J. Graph neural network for traffic forecasting: A survey. Expert systems with applications. 2022 Nov 30;207:117921. [DOI:10.1016/j.eswa.2022.117921]

34. Trapsilawati F, Wijayanto T, Jourdy ES. Human-computer trust in navigation systems: Google maps vs Waze. Communications in Science and Technology. 2019 Jul 14;4(1):38-43. [DOI:10.21924/cst.4.1.2019.112]

35. Jiber M, Lamouik I, Ali Y, Sabri MA. Traffic flow prediction using neural network. In2018 International Conference on Intelligent Systems and Computer Vision (ISCV) 2018 Apr 2 (pp. 1-4). [DOI:10.1109/ISACV.2018.8354066]

36. Serin F, Alisan Y, Kece A. Hybrid time series forecasting methods for travel time prediction. Physica A: Statistical Mechanics and its Applications. 2021 [DOI:10.1016/j.physa.2021.126134]

37. Narayanan S, Chaniotakis E, Antoniou C. Factors affecting traffic flow efficiency implications of connected and autonomous vehicles: A review and policy recommendations. Advances in Transport Policy and Planning. 2020 Jan 1;5:1-50. [DOI:10.1016/bs.atpp.2020.02.004]

38. Das D. Exploring the linkage between human factors and road geometric elements influencing the road traffic accidents on the national roads of South Africa. InCanadian Society of Civil Engineering Annual Conference 2021 May 26 (pp. 15-29). Singapore: Springer Nature Singapore. [DOI:10.1007/978-981-19-1065-4_2]

39. https://ucivil.ir/%D8%A2%D8%B4%D9%86%D8%A7%DB%8C%DB%8C-%D8%A8%D8%A7-%D8%AD%D8%AC%D9%85-%D8%AA%D8%B1%D8%A7%D9%81%DB%8C%DA%A9-%D8%AE%DB%8C%D8%A7%D8%A8%D8%A7%D9%86-%D8%A8%D9%87-%D9%87%D9%85%D8%B1%D8%A7%D9%87-%D9%85%D8%AB/

40. Kim C, Park YS, Sang S. Spatial and temporal analysis of urban traffic volume. InESRI International User Conference, San Diego, CA. Accessed October 2008 Aug (Vol. 10, p. 2013).

41. https://www.google.com/maps

Send email to the article author

Add your comments about this article

‎ 10.61186/jgst.14.2.1

Mendeley

Zotero

RefWorks

rezaee Z, Aghamohammadi H, Vahidnia M H, Azizi Z, Behzadi S. Travel time prediction with machine learning: competition of linear regression, multivariate regression, random forest and deep neural network. JGST 2024; 14 (2) : 1
URL: http://jgst.issgeac.ir/article-1-1197-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 14, Issue 2 (12-2024)

Back to browse issues page