Smart City Gnosys
Smart city article details
| Title | Da-Rnn-Based Bus Arrival Time Prediction Model |
|---|---|
| ID_Doc | 17087 |
| Authors | Li Z. |
| Year | 2024 |
| Published | International Journal of Intelligent Transportation Systems Research, 22, 3 |
| DOI | http://dx.doi.org/10.1007/s13177-024-00422-3 |
| Abstract | Accurate prediction of bus arrival time is crucial for constructing smart cities and intelligent transportation systems. Objectivity and clarity must be maintained throughout to ensure efficient operation. Therefore, it is essential to achieve precise bus arrival time prediction. A recurrent neural network prediction model employing a dual-stage attention mechanism is proposed. The model was constructed based on bidirectional long and short-term memory networks, and arrival time predictions incorporate both dynamic and static factors of bus travel. The model utilized an advanced seagull optimization algorithm to optimize the model parameters, enhanced model iteration and population richness by incorporating the sine-cosine operator and adaptive parameters, and ultimately validated model performance through simulation experiments. The experimental results showed that the prediction error of the benchmark model is 324s and that of the normal peak is 87s. Considering the dynamic and static factors, the prediction error of the model was 6s ~ 8s. The minimum values of mean absolute percentage error, root mean square error and mean absolute error of the model were 0.07, 11.28 and 9.22, respectively. The experimental results demonstrated that the minimum error of the model exhibits the highest prediction accuracy, substantiating the model’s potential for accurate prediction. Furthermore, the model’s performance is effectively safeguarded from the impact of peak time. In addition, the model is feasible in practical application. © The Author(s), under exclusive licence to Intelligent Transportation Systems Japan 2024. |
| Author Keywords | Arrival time; Dual-stage attention mechanism; Prediction; Public transportation; Recurrent neural network; Seagull optimization algorithm |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
26414  | 0.886 | Qiu T.; Lam C.-T.; Liu B.; Ng B.K.; Yuan X.; Im S.K. | Fen-Mrmgcn: A Frontend-Enhanced Network Based On Multi-Relational Modeling Gcn For Bus Arrival Time Prediction | IEEE Access, 13 (2025) |
| 2448 | 0.872 | Zeng L.; He G.; Han Q.; Ye L.; Li F.; Chen L. | A Lstm Based Bus Arrival Time Prediction Method | Proceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019 (2019) |
| 13156 | 0.871 | Larsen G.H.; Yoshioka L.R.; Marte C.L. | Bus Travel Times Prediction Based On Real-Time Traffic Data Forecast Using Artificial Neural Networks | 2nd International Conference on Electrical, Communication and Computer Engineering, ICECCE 2020 (2020) |
| 1591 | 0.866 | Ashwini B.P.; Sumathi R.; Sudhira H.S. | A Dynamic Model For Bus Arrival Time Estimation Based On Spatial Patterns Using Machine Learning | International Journal of Engineering Trends and Technology, 70, 9 (2022) |
| 30953 | 0.853 | Cao S.; Thamrin S.A.; Chen A.L.P. | Improving The Quality Of Public Transportation By Dynamically Adjusting The Bus Departure Time | Proceedings of the ACM Symposium on Applied Computing (2023) |