DOI: 10.5937/jaes0-40553
This is an open access article distributed under the CC BY 4.0
Volume 21 article 1077 pages: 346-352
This research employs a series of machine learning methods to predict the direction of lane change. The response is a binary variable indicating changing the lane to the left or to the right. The employed methods include Decision Tree, Discriminant Analysis, Naïve Bayes, Support Vector Machine, k-Nearest Neighbour and Ensemble. The results are compared to the conventional logistic regression method. Both performance criteria and computational times are reported for comparison purposes. A design of experiments is run to test 25 classification methods at ratios of 25%, 50%, and 75% right to left lane change data. Furthermore, samples are validated by cross and holdback validation methods. RUSBoosted trees, an ensemble method, shows improvement over logistic regression. This research provides valuable insights on lane change behaviour, including trajectories and driving styles, which falls into the field of microscopic lane change study.
1. Ardakani, M. K., and J. Yang. (2016). Generalized Gipps-type vehicle-following models. Journal of Transportation Engineering Part A, 143 (3): 04016011.https://doi.org/10.1061/JTEPBS.0000022
2. Wang, Y. (2017). Modeling and Simulation of Aggressive Lane-Changing Behavior for Highway Driver Training. 2017 3rd IEEE Internaitonal Conference on Computer and Communications (pp. 2894-2898). Chengdu: IEEE
3. Ardakani, M. K., Yang, j., and Sun, L., (2017). Stimulus response driving behavior: An improved general motor vehicle-following model, Advances in Transportation Studies, no. 39, pp. 23–36
4. Gu, X., Yu, J., Han, Y., Han, M., & Wei, L. (2019). Vehicle Lane Chnage Decision Model Based on Random Forest. 2019 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS), (pp. 115-120). Shenyang, China
5. Toledo, T. a. (2009). State Dependence in Lane-Changing Models. Transportation Research Record: Journal of the Transporation Research Board, 2124(1), 81-88
6. Sun, D. a., and Elefteriadou L., (2012). Lane‐Changing Behavior on Urban Streets: An “In‐Vehicle” Field Experiment‐Based Study. Computer-Aided Civil and Infrastructure Engineering, 27(7), 525-542
7. Ekbatani Keyvan, M. V. (2016). Categorization of the Lane Change Decision Process on Freeways, Transportation Research Part C: Emerging Technologies, 69, 515-526
8. Ren, G., Zhang, Y., Liu, H., Zhang, K., & Hu, Y. (2019). A New Lane-Changing Model with Consideration of Driving Style. International Journal of Intelligent Transportation Systems Research, 17, 181-189
9. Pang, M.-Y. (2019). Trajectory Data Based Clustering and Feature Analysis of Vehicle Lane-Changing Behavior. 2019 4th International Conference on Electromechanical Control Technology and Transportation (ICECTT) (pp. 229-233). Guilin: IEEE
10. De Zepeda, M. V., Meng, F., Su, J., Zeng, X.-J., & Wang, Q. (2021). Dynamic Clustering Analysis for Driving Styles Identification. Engineering Applications of Artificial Intelligence, 97
11. Yang Yang, Kun He, Yun-peng Wang, Zhen-zhou Yuan, Yong-hao Yin, Man-ze Guo, (2022a). Identification of dynamic traffic crash risk for cross-area freeways based on statistical and machine learning methods, Physica A: Statistical Mechanics and its Applications, Volume 595, 127083
12. Yang Yang, Kun Wang, Zhenzhou Yuan, Dan Liu, (2022b). "Predicting Freeway Traffic Crash Severity Using XGBoost-Bayesian Network Model with Consideration of Features Interaction", Journal of Advanced Transportation, vol. 2022, Article ID 4257865, 16, https://doi.org/10.1155/2022/4257865
13. Krüger, Martin, Anne Stockem Novo, Till Nattermann, Torsten Bertram, (2019). Probabilistic Lane Change Prediction using Gaussian Process Neural Networks. In 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019, Auckland, New Zealand, October 27-30, 2019. pages 3651-3656, IEEE
14. Next Generation Simulation (NGSIM). (2020, November 2). Retrieved from Federal Highway Administration: https://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm
15. Ardakani, M.K., (2016). The impacts of errors in factor levels on robust parameter design optimization, Quality and Reliability Engineering International 32 (5), 1929-1944
16. Ardakani, M.K., Wulff S.S., (2013). An overview of optimization formulations for multiresponse surface problems, Quality and Reliability Engineering International 29 (1), 3-16
17. Cross-Validation. (2021). Retrieved from Mathworks(r): https://www.mathworks.com/discovery/cross-validation.html#:~:text=Cross-Validation%20with%20MATLAB%20MATLAB%20%C2%AE%20supports%20cross-validation%20and,app%20for%20training%2C%20validating%2C%20and%20tuning%20classification%20models
18. The MathWorks, Inc. (2020). MATLAB Statistics and Machine Learning Toolbox User Guide. Natick, MA: The MathWorks, Inc.
19. Bera, B., Saha, S., & Bhattacharjee, S. (2020). Forect Cover Dynamics (1998 to 2019) and Prediction of Deforestation Probability using Binary Logistic Regression Model of Silabati Watershed, India. Trees, Forests and People, 2
20. Rahman, H. A., Wah, Y. B., & Huat, O. S. (2021). Predictive Performance of Logstic Regression for Imbalanced Data with Categorical Covariate. Pertanika Journal of Science & Technology, 29(1), 181-197
21. Seiffert, C., Khoshgoftaar, T. M., Van Hulse, J., & Napolitano, A. (2009). RUSBoost: A Hybrid Approach to Alleviating Class Imbalance. IEEE Transacation on Systems, Man, and Cybernetics, 40(1), 185-197