Resumen
In recent years, the rapid growth of vehicles has imposed a significant burden on urban road resources. To alleviate urban traffic congestion in intelligent transportation systems (ITS), real-time and accurate traffic flow prediction has emerged as an effective approach. However, selecting relevant parameters from traffic flow information and adjusting hyperparameters in intelligent algorithms to achieve high prediction accuracy is a time-consuming process, posing practical challenges in dynamically changing traffic conditions. To address these challenges, this paper introduces a novel prediction architecture called Multiple Variables Heuristic Selection Long Short-Term Memory (MVHS-LSTM). The key innovation lies in its ability to select informative parameters, eliminating unnecessary factors to reduce computational costs while achieving a balance between prediction performance and computing efficiency. The MVHS-LSTM model employs the Ordinary Least Squares (OLS) method to intelligently reduce factors and optimize cost efficiency. Additionally, it dynamically selects hyperparameters through a heuristic iteration process involving epoch, learning rate, and window length, ensuring adaptability and improved accuracy. Extensive simulations were conducted using real traffic flow data from Shanghai to evaluate the enhanced performance of MVHS-LSTM. The prediction results were compared with those of the ARIMA, SVM, and PSO-LSTM models, demonstrating the innovative capabilities and advantages of the proposed model.