Autonomous Vehicle Safety Prediction Using Machine Learning Techniques
Main Article Content
Abstract
Autonomous Vehicles (AVs) offer promise of mobilizing the world, optimizing traffic flow and safety. However, maintaining safety for pedestrians in the presence of AVs is challenging. The proposed work demonstrates that using machine learning (ML) techniques can improve pedestrian safety in cases where AVs are present. The BDD100K dataset, which includes a variety of driving scenarios under varying lighting, traffic, and weather situations, is the basis for the suggested method in this paper, which is a Deep Neural Network (DNN) for predicting the safety of autonomous vehicles. Preprocessing the dataset using picture inspection, irrelevant class removal, image scaling, data augmentation, one-hot encoding, Min-Max normalization, and data balancing using SMOTE improves prediction performance. After training on 80% of the data, the suggested DNN is tested on 20%. The proposed model achieves empirically better results than CNN, MLP, and ResNet18 in terms of ACC, PRE, REC, and F1 score (F1), with a total of 95.9%. For smarter, safer transportation networks, the suggested method is a solid option for predicting the safety of autonomous vehicles.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. Authors retain the copyright of their work and grant the Journal of Global Research in Multidisciplinary Studies (JGRMS) the right of first publication. This license permits unrestricted use, distribution, adaptation, and reproduction in any medium or format, provided the original author(s), source, and publication are properly credited. Users may copy, redistribute, remix, transform, and build upon the published material for any purpose, including commercial use, in accordance with the terms of the CC BY 4.0 License.
How to Cite
References
[1] H. K. Yadav, “Design and Implement Machine Learning Based Predictive Analytics for Road Safety and Accident Prevention,” in 2026 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE, Mar. 2026, pp. 1–6. doi: 10.1109/IATMSI68868.2026.11465965.
[2] S. Kumara and H. P. Cyril, “Deep Learning-Based Intrusion Detection and Cybersecurity Framework for Connected Vehicle CAN Bus Communication Networks,” in 2026 14th International Symposium on Digital Forensics and Security (ISDFS), Boston, MA, USA: IEEE, Mar. 2026, pp. 1–6. doi: 10.1109/ISDFS69419.2026.11459074.
[3] L. Kalidoss, S. Thouti, R. Arunachalam, and P. Ramamurthy, “An efficient model of enhanced optimization and dilated-GRU based secured multi-access edge computing with blockchain for VANET sector,” Expert Syst. Appl., vol. 260, p. 125275, Jan. 2025, doi: 10.1016/j.eswa.2024.125275.
[4] C. Zhu, Y. Bouteraa, M. Khishe, D. Martín, F. Hernando-Gallego, and T. Vaiyapuri, “Enhancing unmanned marine vehicle path planning: A fractal-enhanced chaotic grey wolf and differential evolution approach,” Knowledge-Based Syst., vol. 317, p. 113481, May 2025, doi: 10.1016/j.knosys.2025.113481.
[5] M. Alruwail, K. Djemame, and L. Zhang, “Prediction of Power to Autonomous Vehicles Using Machine Learning Techniques,” in 2024 11th International Conference on Wireless Networks and Mobile Communications (WINCOM), IEEE, Jul. 2024, pp. 1–7. doi: 10.1109/WINCOM62286.2024.10657654.
[6] Govardhan Reddy Kothinti Aptiv, “Enhancing Machine Learning Safety in Autonomous Vehicles: Practical Strategies and Solutions for improved Reliability,” vol. 15, no. 4, pp. 753–763, 2024.
[7] B. Jeganathan, “AI-Powered Ergonomics: Enhancing Workplace Safety through Posture Detection,” Int. J. Res. Sci. Innov., vol. XII, no. II, pp. 410–429, Mar. 2025, doi: 10.51244/IJRSI.2025.12020037.
[8] V. Methuku, S. Kamatala, P. Naayini, and P. R. Vontela, “From Ethical Principles to Technical Safeguards: A Unified Framework for Safe and Human-Centered Artificial Intelligence,” Am. Int. J. Comput. Sci. Technol., vol. 4, no. 5, pp. 26–34, Sep. 2022, doi: 10.63282/3117-5481/AIJCST-V4I5P103.
[9] A. G. P. S. A. D. Poovaiah, “Electrical Power Theft Detection and Meter Reading by using IoT and Wireless Technology,” Int. J. Sci. Res. Dev., vol. 4, no. 5, pp. 2321–0613, July, 2016.
[10] J. Arróspide, L. Salgado, and M. Camplani, “Image-based on-road vehicle detection using cost-effective Histograms of Oriented Gradients,” J. Vis. Commun. Image Represent., vol. 24, no. 7, pp. 1182–1190, Oct. 2013, doi: 10.1016/j.jvcir.2013.08.001.
[11] Y. Cai, Z. Liu, X. Sun, L. Chen, H. Wang, and Y. Zhang, “Vehicle Detection Based on Deep Dual-Vehicle Deformable Part Models,” J. Sensors, vol. 2017, pp. 1–10, 2017, doi: 10.1155/2017/5627281.
[12] S. Singamsetty, “AI-powered Satellite Image Processing for Global Air Traffic Surveillance Techniques Using NCNN–EGSA Optimization Techniques,” in Machine Learning Based Air Traffic Surveillance System Using Image Processing, Emerald Publishing Limited, 2026, pp. 179–197. doi: 10.1108/978-1-80592-062-520251010.
[13] W. Chen, Y. Qiao, and Y. Li, “Inception-SSD: An improved single shot detector for vehicle detection,” J. Ambient Intell. Humaniz. Comput., vol. 13, no. 11, pp. 5047–5053, Nov. 2022, doi: 10.1007/s12652-020-02085-w.
[14] S. Jaradat, T. I. Alhadidi, H. I. Ashqar, A. Hossain, and M. Elhenawy, “Exploring Traffic Crash Narratives in Jordan Using Text Mining Analytics,” in 2024 IEEE 3rd International Conference on Computing and Machine Intelligence (ICMI), IEEE, Apr. 2024, pp. 1–6. doi: 10.1109/ICMI60790.2024.10586010.
[15] N. O. Khanfar, M. Elhenawy, H. I. Ashqar, Q. Hussain, and W. K. M. Alhajyaseen, “Driving behavior classification at signalized intersections using vehicle kinematics: Application of unsupervised machine learning,” Int. J. Inj. Contr. Saf. Promot., vol. 30, no. 1, pp. 34–44, Jan. 2023, doi: 10.1080/17457300.2022.2103573.
[16] S. Grigorescu, B. Trasnea, T. Cocias, and G. Macesanu, “A survey of deep learning techniques for autonomous driving,” J. F. Robot., vol. 37, no. 3, pp. 362–386, Apr. 2020, doi: 10.1002/rob.21918.
[17] R. Shafique, F. Rustam, S. Murtala, A. D. Jurcut, and G. S. Choi, “Advancing Autonomous Vehicle Safety: Machine Learning to Predict Sensor-Related Accident Severity,” IEEE Access, vol. 12, pp. 25933–25948, 2024, doi: 10.1109/ACCESS.2024.3366990.
[18] R. rao Thallada, N. Alapati, and K. Nallabothu, “Explainable AI-Driven Predictive Risk Management Framework for Enterprise GRC Platforms,” Apr. 09, 2026. doi: 10.21203/rs.3.rs-9328473/v1.
[19] I. M. Putri, “ASUHAN KEPERAWATAN PADA TN.SI DENGAN CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) DI RUANG RAWAT INAP A RSUD KANJURUAN KEPANJEN,” Undergrad. thesis, Univ. Muhammadiyah Malang., 2023.
[20] A. Dixit, R. Kumar Chidambaram, and Z. Allam, “Safety and Risk Analysis of Autonomous Vehicles Using Computer Vision and Neural Networks,” Vehicles, vol. 3, no. 3, pp. 595–617, 2021, doi: 10.3390/vehicles3030036.
[21] Y. Rao et al., “Enhancing privacy protection for vehicle trajectory prediction using differential privacy and federated learning,” in 2025 IEEE 5th International Conference on Computer Communication and Artificial Intelligence (CCAI), IEEE, May 2025, pp. 931–935. doi: 10.1109/CCAI65422.2025.11189850.
[22] T. Shanmugam, A. Munusamy, M. A. Sadiq, and A. K. Sivaraman, “Integrating Advanced Machine Learning, Sensor Fusion, and Control Systems to Enhance Autonomous Vehicle Safety and Performance,” in 2024 IEEE Conference on Engineering Informatics (ICEI), IEEE, Nov. 2024, pp. 1–6. doi: 10.1109/ICEI64305.2024.10912173.
[23] S. Sathy, P. Sankaranarayanan, A. Ramanujam, and R. Jayaprakash, “ManeuverNet - A Deep Learning Model For Vehicle Maneuver Prediction,” in 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring), IEEE, Jun. 2024, pp. 1–7. doi: 10.1109/VTC2024-Spring62846.2024.10683142.
[24] U. V. Krishna, S. Sudhakaran, S. Sanju, E. Vignesh, and R. Kaladevi, “Accident Prediction and Analysis using Machine Learning models,” in 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA), IEEE, Mar. 2023, pp. 37–40. doi: 10.1109/ICIDCA56705.2023.10099532.
[25] T. Augustine and S. Shukla, “Road Accident Prediction using Machine Learning Approaches,” in 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), 2022, pp. 808–811. doi: 10.1109/ICACITE53722.2022.9823499.
[26] I. El Mallahi, A. Dlia, J. Riffi, M. A. Mahraz, and H. Tairi, “Prediction of Traffic Accidents using Random Forest Model,” in 2022 International Conference on Intelligent Systems and Computer Vision (ISCV), IEEE, May 2022, pp. 1–7. doi: 10.1109/ISCV54655.2022.9806099.
[27] N. Adik, “The Rise of Open and Free Networks: A Community-Driven Paradigm for Decentralized Connectivity,” in 2025 IEEE First International Conference on Innovations in Engineering and Next-Generation Technologies for Sustainability (ICINVENTS), Coimbatore, India: IEEE, 2025, pp. 1–9, November. doi: 10.1109/ICINVENTS64613.2025.11402224.
[28] M. Haris and A. Glowacz, “RETRACTED: Road Object Detection: A Comparative Study of Deep Learning-Based Algorithms,” Electronics, vol. 10, no. 16, p. 1932, Aug. 2021, doi: 10.3390/electronics10161932.
[29] M. Alqarqaz, M. Bani Younes, and R. Qaddoura, “An Object Classification Approach for Autonomous Vehicles Using Machine Learning Techniques,” World Electr. Veh. J., vol. 14, no. 2, p. 41, Feb. 2023, doi: 10.3390/wevj14020041.
[30] C. P. Razeena and P. Simon, “Deep Learning based Automated Braking Decision-making for Advanced Driver Assistance System,” Procedia Comput. Sci., vol. 258, pp. 552–562, 2025, doi: 10.1016/j.procs.2025.04.290.