基于随机灰色蚁群神经网络的近期公交客流预测

为了科学准确地预测近期公交客流量,根据近期公交客流量预测受到多因素影响以及非线性的特点,利用随机灰色变量描述预测系统的不确定性,建立了随机灰色预测模型以及基于蚁群算法的递归神经网络模型,在此基础上,提出了一种基于随机灰色蚁群神经网络的近期公交客流量预测方法。最后以铜陵市为例,对模型的预测精度和有效性进行了分析。结果表明,基于蚁群算法的递归神经网络模型的预测精度不但高于其他单一预测模型,而且明显优于其他传统组合预测模型,能很好地反映事物发展的规律,能够指导公交经营管理者近期的决策行为,有效地改善了预测精度。

Forecasting of short-term urban public transit volume based on random gray ant colony neural network

In order to forecast the short-term public transit volume accurately, according to characteristic of multiple factor and nolinear on volume forecasting of the short-term public transit volume, and uncertainty of forecasting system by representing of stochastic gray variable, it projected models of random gray and recurrent neural network based ant colony optimization algorithm, on that basis, this paper applied a model to forecast volume of the short-term public transit volume based on random gray ant colony neural network.Finally it carried out a case study to forecast for Tongling, and analysed forecasting accuracy and validity of this model. From the test results, it shows that random gray and recurrent neural network based ant colony optimization algorithm not only greater than other single forecasting model, but also superior to other combined forecasting model, and can reflect commendably the law of object development, and can help operators and managers to make decisions and can improve forecast accuracy effectively.