遗传优化支持向量机的交通流量预测模型

Traffic Flow Forecasting Model by Support Vector Machine Optimized by Genetic Algorithm

交通流量预测是智能交通管理领域的一个重要热点,结合交通流量的变化特点,针对支持向量机的参数优化问题,设计了基于遗传算法优化支持向量机的交通流量预测模型。在分析当前交通流量预测的研究现状基础上,指出传统模型存在的局限性;采用遗传算法对支持向量机的的参数进行优化,并通过混沌理论对交流流量的原始数据行相空间重构,建立交通流量预测模型;采用仿真实验测试该模型的有效性和优越性。实验结果表明,遗传算法优化支持向量机可以跟踪交通流量复杂的变化特点,获得了理想的交通流量预测结果,而且交流流量的预测误差要明显小其它模型,具有更高的应用价值。

Traffic flow forecasting is an important topic in the field of intelligent traffic management. Combined with the charac- teristics of traffic flow, aiming at parameter optimization of support vector machine, this paper designs traffic flow prediction model by using support vector machine which is improved by genetic algorithm. Firstly, the current studies of traffic flow fore- cast is analyzed, the paper points out the limitations of the traditional models, then uses genetic algorithm to optimize the pa- rameters of support vector machine, and the phase space of original data of the traffic is reconstructed by chaos theory, a traffic flow volume forecasting model is estabtished. The superiority and effectiveness of the model are verified by the experimental simulation. The experimental results show that the genetic algorithm optimizes support vector machine, and it can track the changes of complex traffic flow, traffic flow prediction results are ideal, and the prediction error is significantly smaller than other communication flow models.