Research on data prediction based on smart transportation spatial model
SHAO Hongqing
GAO Jianfeng
DU Yu
Abstract：Smart traffic monitoring systems can monitor road network operations in real-time and respond quickly to sudden road events,but they have limitations in traffic flow prediction.To address this,this study uses the bat algorithm(BA)to optimize the hyperparameters of the long short-term memory network(LSTM),constructing a traffic flow prediction model based on improved LSTM.Experimental results show that the improved model has a lower mean absolute error(MAE)of 22.54 and a lower root mean square error(RMSE)of 35.16 compared to the traditional LSTM model.The application of this model can enhance traffic flow prediction accuracy and provide a technical basis for decision-making support in smart traffic systems.
Keywords：intelligent transportationdata predictiontraffic flowlong short term memory network
Publication Date：2025-03-25
Pages：3( 34-36 )