基于神经网络的停车需求预测模型及应用

结合停车需求特点分析了停车需求影响因素,提出了基于主成分分析的BP神经网络停车需求预测模型,该模型主要是通过对城市中心区停车需求的经济、土地、交通的特征分析,利用主成分分析法,明确了影响停车需求的主成分,简化了神经网络的输入样本,消除了网络输入之间的相关性,提高了网络的性能,实现了公共停车需求的准确预测。

Parking Demand Forecasting Model and Its Application Based on Neural Network

In this paper,a forecasting model based on principal component analysis and BP neural network was proposed after the factors influencing parking demand were analyzed according to its characteristics.This model realizes the accurate prediction of public parking demand through the following steps.First,it analyzed the features of economy,land,and traffic for parking demand central city.Second,it determined the main components of impact parking demand by using principal component analysis.The second step simplifies the neural network＇s input data,eliminates the correlations between inputs and improves the performance of the network.