A Deep Learning-Based Intelligent Road Safety Framework Using Multi-Source Traffic, Weather, and Accident Data
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V7I3P103Keywords:
Intelligent Transportation Systems (ITS), Road Safety, Accident Prediction, Deep Learning, CNN–LSTM, Explainable Artificial Intelligence (XAI), SHAP, Multi-Source Data Fusion, Traffic Analytics, Weather Analytics, Smart TransportationAbstract
Road traffic accidents remain a major public safety challenge worldwide, resulting in substantial human and economic losses. Existing road safety systems primarily rely on historical accident records and often fail to provide proactive risk prediction under dynamic traffic and environmental conditions. This paper proposes a deep learning-based intelligent road safety framework that integrates heterogeneous data sources, including traffic flow, weather conditions, historical accident records, road geometry, temporal traffic patterns, and geographic information, to predict accident risks in real time. The proposed framework employs a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture to capture both spatial and temporal dependencies within multi-source transportation data. To improve model interpretability and support reliable decision-making, Explainable Artificial Intelligence (XAI) using SHapley Additive exPlanations (SHAP) is incorporated to identify the most influential factors contributing to accident occurrence. The framework generates dynamic road risk scores and identifies accident-prone road segments, enabling proactive traffic management, optimized emergency response, and data-driven infrastructure planning. Experimental evaluation using publicly available traffic, weather, and accident datasets demonstrates that the proposed model outperforms conventional machine learning approaches, including Random Forest, Support Vector Machine, and XGBoost, in terms of prediction accuracy, robustness, and interpretability. The proposed framework provides a scalable and practical solution for next-generation Intelligent Transportation Systems (ITS), contributing to safer, more efficient, and resilient smart transportation networks.
References
[1] O. Gurrapu and J. V. Suman, "A Machine Learning Framework for Fault Detection in IoT Enabled Smart Sensor Networks," 2025 Global Conference on Information Technology and Communication Networks (GITCON), Belagavi, India, 2025, pp. 1-6, doi: 10.1109/GITCON65266.2025.11377003.
[2] O. Gurrapu and S. S. E. Padmarao, "Real-Time Fault Detection in Ocean Observing Platforms," 2026 7th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI), Goathgaun, Nepal, 2026, pp. 446-452,
[3] World Health Organization, Global Status Report on Road Safety 2023. Geneva, Switzerland: WHO, 2023.
[4] A. Esteva, A. Robicquet, B. Ramsundar et al., "A guide to deep learning in healthcare," Nature Medicine, vol. 25, no. 1, pp. 24–29, Jan. 2019.
[5] V. Painuly, O. Gurrapu, W. H. Jebaselvi, U. Abdalov, Y. Noushad and V. C. Gandhi, "AI-Enhanced Collision Detection for Autonomous Drones Using LiDAR and Neural Network," 2025 Second International Conference on Networks and Soft Computing (ICNSoC), Vadlamudi, India, 2025, pp. 564-568
[6] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
[7] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[8] [5] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2012, pp. 1097–1105.
[10] C. Molnar, Interpretable Machine Learning, 2nd ed. Munich, Germany, 2022.
[11] [8] S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774.
[12] H. Wang, Z. Li, X. Zhang, and Y. Wang, "Deep learning-based traffic accident prediction: A survey," IEEE Access, vol. 10, pp. 112315–112338, 2022.
[13] J. Guo, Y. Huang, and L. Li, "Traffic accident prediction using deep neural networks with multi-source traffic data," IEEE Access, vol. 9, pp. 135724–135736, 2021.
[14] Z. Zheng, P. Wang, and X. Liu, "Traffic flow prediction using hybrid CNN-LSTM deep learning networks," IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 6, pp. 3456–3467, Jun. 2021.
[15] Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, "Traffic flow prediction with big data: A deep learning approach," IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 2, pp. 865–873, Apr. 2015.
[16] X. Ma, Z. Tao, Y. Wang, H. Yu, and Y. Wang, "Long short-term memory neural network for traffic speed prediction," in Proc. IEEE Int. Conf. Intelligent Transportation Systems (ITSC), 2015, pp. 1276–1280.
[17] H. Shi, G. Qin, Y. Xu, and J. Zhang, "A hybrid CNN-LSTM framework for road traffic prediction using spatiotemporal features," Expert Systems with Applications, vol. 188, Art. no. 116020, 2022.
[18] M. Abadi et al., "TensorFlow: Large-scale machine learning on heterogeneous systems," Google Research, 2016.
[19] F. Pedregosa et al., "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[20] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proc. Int. Conf. Learning Representations (ICLR), 2015.
[21] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 785–794.
[22] L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[23] C. Cortes and V. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.
[24] J. Doe and A. Smith, "Multi-source data fusion for intelligent transportation systems: A review," IEEE Access, vol. 11, pp. 45210–45235, 2023.
[25] X. Liu, H. Wang, and Y. Zhang, "Road accident severity prediction using explainable artificial intelligence," IEEE Access, vol. 11, pp. 78543–78558, 2023.
[26] M. H. Dixon, P. Jones, and R. White, "Weather-aware traffic accident prediction using deep neural networks," Transportation Research Part C, vol. 148, Art. no. 104067, 2023.
[27] S. Zhao, Y. Chen, and X. Wu, "Spatiotemporal graph neural networks for traffic forecasting: A survey," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 2, pp. 1123–1142, 2024.
[28] J. Zhang, Y. Li, and H. Chen, "Explainable artificial intelligence for intelligent transportation systems: Recent advances and future directions," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 5, pp. 4215–4232, 2024.
[29] O. Gurrapu and P. Kaluvala, "Deep Learning-based Object identification in Ocean Environment by Convolutional Neural models," 2025 International Conference on NexGen Networks and Cybernetics (IC2NC), Erode, India, 2025, pp.
[30] R. Sivaranjani, B. S. Priya, O. Gurrapu, P. Kadiri, N. S. Chandana and J. V. Suman, "Image Classification using Quantum Convolutional Neural Network (QCNN)," 2025 International Conference on Metaverse and Current Trends in Computing (ICMCTC), Subang Jaya, Malaysia, 2025, pp. 1-6.
