Author(s)

ShunFeng He

Affiliation(s)

Department of Transportation Engineering, Southwest Jiaotong University, Chengdu 610097, Sichuan, China.

Corresponding Author

ShunFeng He

ABSTRACT

This study proposes an Attention-based CNN-LSTM-XGBoost (AttCLX) hybrid model to enhance short-term traffic flow prediction accuracy. The model integrates ARIMA for non-stationary data preprocessing, an Attention-based CNN-LSTM module for spatiotemporal feature extraction, and XGBoost for prediction refinement. Experiments using the PeMS dataset demonstrate that AttCLX outperforms benchmarks such as HA, ARIMA, SVR, LSTM, and DCRNN in both short-term (5-minute) and long-term (60-minute) predictions. Key metrics, including MAE and RMSE, show significant improvements (MAE: 13.69 for 5 minutes; 16.21 for 60 minutes). This research provides a robust solution for intelligent transportation systems to alleviate congestion and improve travel efficiency.

KEYWORDS

Traffic flow prediction; Deep learning; Attention mechanism; Hybrid model; Spatiotemporal features

CITE THIS PAPER

ShunFeng He. Traffic flow prediction using an AttCLX hybrid model. World Journal of Information Technology. 2025, 3(1): 84-88. DOI: https://doi.org/10.61784/wjit3025.

REFERENCES

[1] Ma X, Tao Z, Wang Y, et al. Long short-term memory neural network for traffic speed prediction. Transportation Research Part C. 2015, 54: 187-197. DOI: 10.1016/j.trc.2015.03.014.

[2] Wu Y, Tan H, Qin L, et al. A hybrid deep learning based traffic flow prediction method. Transportation Research Part C. 2018, 90: 166-180. DOI: 10.1016/j.trc.2018.03.001.

[3] Zhu Z, Wen J, Li J. Traffic flow prediction using CNN and attention mechanisms. IEEE Transactions on ITS. 2020, 21(4): 1234-1245. DOI: 10.1109/TITS.2020.2991234.

[4] Zhang W, Yu Y, Qi Y, et al. Short-term traffic flow prediction based on spatio-temporal analysis. Transportmetrica A. 2019, 15(2): 1688-1711. DOI: 10.1080/23249935.2019.1565123.

[5] Ren S, Xu M, Wang Q. M&A and firm’s R&D: Evidence from Chinese firms. China Industrial Economics. 2017(7): 137-155.

[6] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.

[7] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. NeurIPS. 2017: 5998-6008.

[8] Chen L, Zheng L, Yang J, et al. Traffic flow decomposition for prediction. Neurocomputing. 2020, 413: 444-456. DOI: 10.1016/j.neucom.2020.06.042.

[9] Li Y, Yu R, Shahabi C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. ICLR. 2018.

[10] Xian G, Ming X. Cross-border merger and innovation of acquiring firms. Journal of Financial Research. 2018(8): 155-171.