基于过程神经元网络与遗传算法的交通流预测

高速公路变通量预测对于高速公路建设和管理具有重要的指导作用。针对传统预测方法准确性低、预测时间长等问题,建立了遗传过程神经元网络优化模型,该模型既利用遗传算法全局搜索、快速收敛的优点,又利用过程神经元网络非线性描述、自学习自适应的优点,并以实际道路为例进行计算机仿真,实证分析的结果表明,该方法能够有效提高交通量的预测精度。

Traffic Flow Prediction Based on Process Neural Network and Genetic Algorithm

The expressway traffic forecast can guide the expressway construction and management.Traditional prediction method has such disadvantages as low accuracy and efficiency.Therefore,a genetic process neural network optimization model was put forward in this paper to deal with this problem.It not only takes the advantages of the genetic algorithm which are global search and rapid convergence,but also those of the neural network which are nonlinearly describing,self learning and self adapting.It was applied to a real expressway to make the computer simulation.The results show that the method can effectively improve the accuracy of traffic forecast.