AI-Based Road Accident Risk Prediction and Driver Safety Assistant with an Automatic Emergency Alert System

We have presented a framework that predicts road risk, watches the driver and reports a crash automatically within a single low-cost pipeline. Tree-ensemble models supply the road-level risk, a landmark-based ratio tracks drowsiness, and a two-condition crash rule with a cancel window keeps false alarms under control. XGBoost gave the best overall performance, with 91.8% accuracy, a macro F1-score of 0.89 and an AUC of 0.95. The next step is a larger field trial, together with a study of how drivers respond to graded warnings.

1. World Health Organization: Global Status Report on Road Safety 2023. WHO, Geneva (2023) 2. Ministry of Road Transport and Highways: Road Accidents in India 2022. Transport Research Wing, Government of India, New Delhi (2023) 3. Moosavi, S., Samavatian, M.H., Parthasarathy, S., Ramnath, R.: A Countrywide Traffic Accident Dataset. arXiv:1906.05409 (2019) 4. Moosavi, S., Samavatian, M.H., Parthasarathy, S., Teodorescu, R., Ramnath, R.: Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights. In: Proc. 27th ACM SIGSPATIAL Int. Conf. on Advances in Geographic Information Systems, pp. 33–42 (2019) 5.             Breiman, L.: Random Forests. Mach. Learn. 45(1), 5–32 (2001) 6. Chen, T., Guestrin, C.: XGBoost: A Scalable Tree Boosting System. In: Proc. 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pp. 785–794 (2016) 7.             Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.-Y.: LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In: Advances in Neural Information Processing Systems 30, pp. 3146–3154 (2017) 8. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: Synthetic Minority Over-sampling Technique. J. Artif. Intell. Res. 16, 321–357 (2002) 9. Soukupová, T., Čech, J.: Real-Time Eye Blink Detection using Facial Landmarks. In: 21st Computer Vision Winter Workshop, Rimske Toplice, Slovenia (2016) 10.           Kazemi, V., Sullivan, J.: One Millisecond Face Alignment with an Ensemble of Regression Trees. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1867–1874 (2014)