基于改进支持向量机的交通流量预测算法研究

Traffic Flow Prediction Algorithm Based On Improved Support Vector Machine

城市交通流具有复杂性、时变性和随机性,如何实时准确的预测交通流量是实现智能交通诱导及控制的前提。结合交通流的时间序列特性,提出基于改进支持向量机的交通流预测算法,该算法能够克服神经网络预测的不足,对支持向量机算法在嵌入维数、核函数和参数选择上进行了改进.实验仿真结果表明,该算法具有很好的预测精度和适用性。

With the complexity, time variation and probability of urban traffic flow, how to predict traffic flow by real-time and accuracy is very important to the intelligent traffic guidance, control, and management. With the combination of time series of traffic flow, a traffic flow prediction algorithm based on improved support vector machine was given. The algorithm could overcome the shortcoming of neural network prediction, and improve the support vector machine on embedding dimension, kernel function, and parameter selection. The experiment simulation results show that this algorithm is of high precision and applicability.