Short-Term Traffic Congestion Forecasting Using Hybrid Metaheuristics and Rule-Based Methods: A Comparative Study
In this paper, a comparative study between a hybrid technique that combines a Genetic Algorithm with a Cross Entropy method to optimize Fuzzy Rule-Based Systems, and literature techniques is presented. These techniques are applied to traffic congestion datasets in order to determine their performance in this area. Different types of datasets have been chosen. The used time horizons are 5, 15 and 30 min. Results show that the hybrid technique improves those results obtained by the techniques of the state of the art. In this way, the performed experimentation shows the competitiveness of the proposal in this area of application.
KeywordsGenetic algorithms Cross entropy Classification Machine learning Hybrid optimization Fuzzy rule-based systems Intelligent transportation systems
Authors work was supported by TIMON Project. This project has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No. 636220.
- 2.European Commission: Special Eurobarometer 422a, Quality of Transport (2014)Google Scholar
- 4.Frank, E., Witten, I.H.: Generating accurate rule sets without global optimization. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 144–151 (1998)Google Scholar
- 6.Han, Y., Xing, B., Yao, J., Liu, J.: Optimal model of regional traffic signal control under mixed traffic flow condition. Jiaotong Yunshu Gongcheng Xuebao/J. Traffic Transp. Eng. 15(1), 119–126 (2015)Google Scholar
- 7.Hernández, S.A., Leguizamón, G., Mezura-Montes, E.: Hybridization of differential evolution using hill climbing to solve constrained optimization problems. Revista Iberoamericana de Inteligencia Artificial 16(52), 3–15 (2013)Google Scholar
- 16.Olivares-Mendez, M.A., Fu, C., Kannan, S., Voos, H., Campoy, P.: Using the cross-entropy method for control optimization: a case study of see-and-avoid on unmanned aerial vehicles, pp. 1183–1189 (2014)Google Scholar
- 19.Qiu, Y.: Vehicle routing problem with weight coefficients and stochastic demands based on the cross-entropy method, pp. 159–162 (2009)Google Scholar
- 23.Zhou, M., Bi, S., Dong, C., He, C.: Regenerative braking system for electric vehicles based on genetic algorithm fuzzy logic control. ICIC Express Lett. Part B: Appl. 5(3), 689–695 (2014)Google Scholar