为提升交通流量预测的准确性和效率,研究基于神经网络的大数据分析在智慧交通中的应用.首先深入探讨智慧交通系统的整体架构,其次研究基于层归一化的循环神经网络(Recurrent Neural Network,RNN)优化方法,最后进行实验分析.实验结果表明,所提方法的均方根误差(Root Mean Squared Error,RMSE)和平均绝对误差(Mean Absolute Error,MAE)明显优于传统标准RNN方法.
Application of Big Data Analysis Based on Neural Network in Smart Transportation
To improve the accuracy and efficiency of traffic flow prediction,the application of big data analysis based on neural networks in smart transportation is studied.Firstly,we will delve into the overall architecture of smart transportation systems.Secondly,we will study the optimization method of Recurrent Neural Network(RNN)based on layer normalization.Finally,conduct experimental analysis.The experimental results show that the Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)of the proposed method are significantly better than traditional standard RNN methods.