Risk Analysis of Autonomous Vehicle Accidents Using Bayesian Simulation with Statistical and Visual Data
DOI:
https://doi.org/10.35870/ijsecs.v5i3.5781Keywords:
Bayesian CNN, Collision Risk, Autonomous Vehicles, Monte Carlo Dropout, Probabilistic ModelingAbstract
Autonomous vehicles (AVs) are an emerging innovation in intelligent transportation systems, yet traffic accidents remain a critical concern due to environmental uncertainty and sensor limitations. This study aims to analyze collision risk levels in autonomous vehicles using a Bayesian Convolutional Neural Network (Bayesian CNN) integrated with the Monte Carlo Dropout (MC Dropout) technique. The model was trained on 11,000 visual datasets from the Central Bureau of Statistics (BPS) and synthetic data representing diverse road conditions. The Bayesian inference framework enables dynamic and adaptive risk prediction by continuously updating posterior probabilities based on sensor input changes. Simulation experiments were conducted using a Python-based interactive interface (pygame) to visualize vehicle movements and real-time collision probabilities. Results show that 48% of test scenarios were classified as very low risk (0–10%), 28% as low (11–30%), 16% as medium (31–60%), and 8% as high (61–80%). The model achieved a reduction in loss value from 0.43 to 0.08 and maintained 76% of simulations within low and very low risk categories, confirming system stability and reliable convergence. The findings demonstrate that the Bayesian CNN model effectively captures uncertainty and provides adaptive, probabilistic predictions, supporting safer and more intelligent autonomous vehicle operations.
Downloads
References
Abdullah, S. N., Gusti, S. K., Wulandari, F., & Syafria, F. (2023). Klasifikasi tingkat keparahan korban kecelakaan lalu lintas menggunakan Naïve Bayes. Progresif: Jurnal Ilmiah Komputer, 19(2), 858–866. https://progresif.stmik-banjarbaru.ac.id
Ardi, R. N. (2022). Kendaraan Otonom atau AV: Kajian Kebijakan dan Teknologi. Universitas Negeri Surabaya, 5(2), 110-125.
Fauzan, M. D. A., Hardhienata, S., & Suriansyah, M. I. (2025). Implementasi logika fuzzy pada pengaturan jarak dan kecepatan mobil otonom dengan Arduino. TeknoIS: Jurnal Ilmiah Teknologi Informasi dan Sains, 15(1), 1–13. https://teknois.unbin.ac.id/JBS/
Galil, I., & El-Yaniv, R. (2021). Disrupting deep uncertainty estimation without harming accuracy. Advances in Neural Information Processing Systems, 1–12. https://arxiv.org/abs/2105.14945
Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., et al. (2023). A survey of uncertainty in deep neural networks. Artificial Intelligence Review, 56(S1), 1513–1589. https://doi.org/10.1007/s10462-022-10333-1
Michelmore, R., Smith, A., Ghadimi, A., Posner, I., & Gal, Y. (2022). Uncertainty estimation for autonomous driving: A review. IEEE Transactions on Intelligent Transportation Systems, 23(5), 3908–3927. https://doi.org/10.1109/TITS.2021.3097950
Guo, Z., Li, Y., & Liu, S. (2024). Bayesian deep learning for autonomous driving risk assessment: A comprehensive review. IEEE Transactions on Intelligent Vehicles, 9(1), 44–62. https://doi.org/10.1109/TIV.2023.3298712
Junita, A., Kenedi, J., & Jalili, I. (2025). Peran Satlantas dalam menekan kecelakaan jalan raya: Analisis dari perspektif fiqh siyasah. Journal of Law and Legal System, 1(2), 104–110.
Kurniadi, U., Ramadhan, R., & Yusuf, A. (2023). Autonomous vehicles and legal challenges: Navigating between technology and criminal liability. Journal of Technology Law Review, 2(3), 37–55.
Pradityarahman, Y., Hestiwi, D. I., Al-Mustaqim, F., & Hakim, M. L. (2021). Prototype smart autonomous car berbasis deep learning dengan sistem pencegah kecelakaan. Jurnal Edukasi Elektro, 5(2), 91–97. https://doi.org/10.26740/jee.v5n2.p91-97
Rasdiyanti, A. D. (2024). Autonomous vehicle (AV) sebagai transportasi publik: Kebijakan dan tantangan. Jurnal Aristo, 12(2), 452–474. https://doi.org/10.24269/ars.v12i2.1234
Rizki, N. A., Syaripuddin, & Wahyuningsih, S. (2023). Model multinomial Bayesian network pada data simulasi curah hujan. Statistika, 12(2), 61–75.
Setiaji, Y., Miransyahputra, M. R., & Nazaruddin, Y. Y. (2021). Analisis metoda estimasi peta kedalaman dari citra RGB 2D untuk penerapan teknik persepsi pada kendaraan otonom. Jurnal Otomasi, Kontrol & Instrumentasi, 13(2), 65–71. https://doi.org/10.1155/2021/5542137
Tyralis, H., & Papacharalampous, G. (2024). A review of predictive uncertainty estimation with machine learning. Artificial Intelligence Review, 5(7), 94-110. https://doi.org/10.1007/s10462-022-10396-0
Sinulingga, R. F., Suprapto, B. Y., Al Hafiz, D. M., Ardandy, F. A., Jonathan, J., & Dwijayanti, S. (2025). Speed control of an autonomous electric vehicle using sensor fusion approach. Jurnal Nasional Teknik Elektro, 14(1), 1-7. https://doi.org/10.25077/jnte.v14n1.1165.2025
Simanjuntak, W. (2023). Perancangan dan evaluasi sistem kendali adaptif berbasis kecerdasan buatan untuk kendaraan otonom elektrik. Universitas Medan Area, 1(1), 1-12. https://coursework.uma.ac.id/index.php/elektro/article/view/617
Ikbal, M., & Saputra, R. A. (2024). Pengenalan rambu lalu lintas menggunakan YOLO. Jurnal Informatika, 8(2), 204-212. http://dx.doi.org/10.31000/jika.v8i2.10609
Toney, G., Sethi, G., Bhargava, C., Vaz, A. C., & Hegde, N. T. (2025). Sensor fusion and predictive control for adaptive vehicle. Journal Robotic and Controls, 6(5), 17-25. https://doi.org/10.18196/jrc.v6i5.26740
Ardi, R. N., & Susilowati, I. F. (2023). Perbandingan hukum terkait penggunaan fitur otonom. Jurnal Hukum, 10(3), 10-18. https://doi.org/10.2674/novum.v0i0.47251
Zhang, Y., Wang, Q., & Zhao, H. (2025). A survey on machine learning approaches for uncertainty quantification of engineering systems. Journal of Uncertainty Quantification, 13(1), 11–46. https://doi.org/10.1137/uq2025001
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Yesy Simanjuntak, Rani Indah Sari, Peter Tymoty Hutabarat, Suvriadi Panggabean
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Copyright Retention and Open Access License
Authors retain copyright of their work and grant the journal non-exclusive right of first publication under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license allows unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
2. Rights Granted Under CC BY 4.0
Under this license, readers are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, including commercial use
- No additional restrictions — the licensor cannot revoke these freedoms as long as license terms are followed
3. Attribution Requirements
All uses must include:
- Proper citation of the original work
- Link to the Creative Commons license
- Indication if changes were made to the original work
- No suggestion that the licensor endorses the user or their use
4. Additional Distribution Rights
Authors may:
- Deposit the published version in institutional repositories
- Share through academic social networks
- Include in books, monographs, or other publications
- Post on personal or institutional websites
Requirement: All additional distributions must maintain the CC BY 4.0 license and proper attribution.
5. Self-Archiving and Pre-Print Sharing
Authors are encouraged to:
- Share pre-prints and post-prints online
- Deposit in subject-specific repositories (e.g., arXiv, bioRxiv)
- Engage in scholarly communication throughout the publication process
6. Open Access Commitment
This journal provides immediate open access to all content, supporting the global exchange of knowledge without financial, legal, or technical barriers.
