The prediction of holiday's traffic has the characteristics of small historical sample size and strong nonlinear, which result in low prediction accuracy. Genetic algorithm (GA) is adopted in this paper to optimize the support vector regression machine (SVR) to forecast the busy traffic of Xinjiang in holidays and compared with the traditional SVR and the BP neural network. The result shows that the GA-SVR has a higher forecast precision and a less time-consuming, which is an effective method of busy traffic prediction. © 2012 Springer-Verlag GmbH.
CITATION STYLE
Guo, M. L., Li, D. J., Du, C. B., Jia, Z. H., Qin, X. Z., Chen, L., … Li, H. (2012). Prediction of the busy traffic in holidays based on GA-SVR. In Advances in Intelligent and Soft Computing (Vol. 169 AISC, pp. 577–582). https://doi.org/10.1007/978-3-642-30223-7_91
Mendeley helps you to discover research relevant for your work.