Traffic flow time series prediction based on statistics learning theory
暂无分享,去创建一个
For intelligent transportation systems, a new traffic flow time series prognostication is proposed in this paper. Compared with classical methods, support vector machine has a good generalize ability for limited training samples, which has a characteristic of rapid convergence and avoiding the local minimum. At the end of this paper, the simulation experiment for the traffic flow of one practice crossing proves the validity and efficiency and high application value in traffic flow prediction.
[1] Vladimir Vapnik,et al. An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.
[2] Jiao Licheng,et al. Classification mechanism of support vector machines , 2000, WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000.