Metaheuristic-based approach tooptimizing the weights in the TOPSISmethod for driver candidate performanceassessment
Abstract
Abstract
Introduction/purpose: Traffic safety and reliable driver selection are key components of modern transport systems. The aim of this paper is to improve the evaluation process of candidates performance in driving tests by applying multi-criteria decision-making and metaheuristic optimization. Based on the results obtained using the Vienna Test System, a TOPSIS-based model with adaptive weighting of evaluation criteria is proposed.
Methods: The weights of the TOPSIS method were optimized using three metaheuristic algorithms: Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Bee Colony Optimization (BCO). Two objective functions were used during optimization — AUC and F1-score — to examine their impact on model accuracy and stability. The experimental framework consisted of three parts: (1) comparison of GA, ACO, and BCO performance using AUC as the objective function, (2) analogous comparison using F1-score as the objective function, and (3) cross-comparison between AUC and F1-score optimized models.
Results: The obtained results indicate that both the choice of metaheuristic algorithm and the objective function significantly influence the performance of the TOPSIS method. AUC-based optimization resulted in more stable models and better balance between successful and unsuccessful candidates, while F1-based optimization achieved higher sensitivity and better identification of successful candidates.
Conclusions: Applying metaheuristic algorithms for weight optimization within the TOPSIS framework enables adaptive and more reliable candidate ranking, contributing to the development of intelligent driver selection systems and improved traffic safety. The results confirm that an appropriate choice of optimization algorithm and objective function can significantly enhance model accuracy and robustness.
References
Dorigo, M. & Gambardella, L.M. 1997. Ant colony system: a cooperative learning approach to the traveling salesman problem, IEEE Transactions on Evolutionary Computation, 1(1), pp. 53–66. Available at: https://doi.org/10.1109/4235.585892
Fawcett, T. 2006. An introduction to ROC analysis. Available at: https://doi.org/10.1016/j.patrec.2005.10.010
Hanley, J.A. & McNeil, B.J. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology, 143(1), pp. 29–36. Available at: https://doi.org/10.1148/radiology.143.1.7063747
Holland, J.H. 1975. Adaptation in Natural and Artificial Systems, Ann Arbor: University of Michigan Press.
Huang, S., Guo, Y., Zhang, X. & Li, J. 2020. Comprehensive evaluation of expressway safety based on AHP–TOPSIS RSR. Physica A: Statistical Mechanics and its Applications, 551, 124–134.
Hwang, C.L. & Yoon, K. 1981. Multiple Attribute Decision Making: Methods and Applications. Berlin: Springer.
Kaça, G., Izmitligil, T., Koyuncu, M. & Amado, S. 2021. How well do the traffic psychological assessment systems predict on-road driving behaviour?, Applied Cognitive Psychology, 35(5), pp.1321–1337. Available at: https://doi.org/10.1002/acp.3867
Karaboga, D. 2005. An idea based on honey bee swarm for numerical optimization, Technical Report TR06, Erciyes University, Turkey.
Kubinger, K.D. 2007. Psychological test calibration using the Rasch model: some critical remarks. Psychology Science, 49(1), pp.49–56. Available at: https://doi.org/10.1207/s15327574ijt0504_3
Masoudi, N., Rezaei, M., Farahbakhsh, M., Zamani-Sani, H., Abdi, S. & Sadeghi-Bazargani, H. 2022. Evaluating the risk of road traffic accidents (RTAs) and the reaction time of individuals with attention deficit disorder (ADD) in the virtual environment: A study protocol using the Sahand driving simulator and the Vienna test system, Medical Journal of Tabriz University of Medical Sciences, 44(5), pp.367–379. Available at: https://doi.org/10.34172/mj.2022.041
Pham, D.T., Ghanbarzadeh, A., Koc, E., Otri, S., Rahim, S. & Zaidi, M. 2006. The bees algorithm — A novel tool for complex optimization problems, in: Proceedings of the 2nd Virtual International Conference on Intelligent Production Machines and Systems (IPROMS 2006), pp. 454–459. Available at: https://doi.org/10.1016/B978-008045157-2/50081-X
Powers, D.M.W. 2011. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation, Journal of Machine Learning Technologies, 2(1), pp. 37–63. Available at: https://doi.org/10.9735/2229-3981
Ren, W., Zhang, X. & Zhao, M. (2021). A comprehensive traffic risk assessment model for urban roads based on entropy–TOPSIS. Safety Science, 138, 105236.
Schuhfried GmbH. 2013. Vienna Test System: User Manual. Mödling, Austria: Schuhfried GmbH. Available at: https://www.schuhfried.com/en/
Sokolova, M. & Lapalme, G. 2009. A systematic analysis of performance measures for classification tasks, Information Processing & Management, 45(4), pp. 427–437. Available at: https://doi.org/10.1016/j.ipm.2009.03.002
Talbi, E.G. 2009. Metaheuristics: From Design to Implementation, Hoboken, New Jersey: Wiley. Available at: https://www.wiley.com/
Tinella, L., Caffò, A.O., Lopez, A., Nardulli, F., Grattagliano, I. & Bosco, A. 2021. Reassessing fitness-to-drive in drinker drivers: The role of cognition and personality, International Journal of Environmental Research and Public Health, 18(23), 12828. Available at: https://doi.org/10.3390/ijerph182312828
Vujadinović, J., Sarić, I. & Nikolić, R. 2025. Assessment of candidates performance in the driving test using the TOPSIS method and its modifications, in: Proceedings of the International Symposium on Operational Research – SIMOPIS 2025, Palić, 7–10. September 2025, pp. 225–230 (in Serbian). Available at: https://www.symopis2025.fon.bg.ac.rs/
Youden, W.J. 1950. Index for rating diagnostic tests, Cancer, 3(1), pp. 32–35. Available at: https://doi.org/10.1002/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3
Copyright (c) 2025 Ивана Сарић, Jasmina Vujadinović, Рале Николић
This work is licensed under a Creative Commons Attribution 4.0 International License.
Proposed Creative Commons Copyright Notices
Proposed Policy for Military Technical Courier (Journals That Offer Open Access)
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).