Accurate traffic analysis and prediction are crucial for smart transportation as urban traffic flow is random and influenced by multiple factors. Existing models typically use shallow prediction techniques, resulting in unsatisfactory accuracy when considering external factors such as weather. This study proposes an improved LSTM model with an attention mechanism for short-term traffic flow prediction while considering weather factors. Our model learns the importance of each past value to the current value from past long sequences of traffic data, extracting more valuable features. Our experiments on a PeMS traffic data set show that the proposed model outperforms the original LSTM model, reducing its MAPE by 23.36% and demonstrating its effectiveness in improving traffic flow prediction accuracy.
Improved LSTM model for short-term traffic flow prediction with weather consideration
Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023) ; 2023 ; Hangzhou, China
Proc. SPIE ; 12790
07.09.2023
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Improved LSTM model for short-term traffic flow prediction with weather consideration
British Library Conference Proceedings | 2023
|Short-term traffic flow prediction method based on improved LSTM
Europäisches Patentamt | 2021
|Short-Term Traffic Flow Prediction: Using LSTM
IEEE | 2020
|LSTM short-term traffic flow prediction method based on improved PSO algorithm
Europäisches Patentamt | 2021
|