IRO Journals
Recent Research Reviews Journal

Simulation-Based Stampede Prevention with Machine Learning and Explainable AI

Open Access
Published: 18 June, 2026
Pages: 156-169
  • Hariharan M. , Hariharan M.
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
  • Asik Ahmed A. , Asik Ahmed A.
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
  • Badri Narayana V. , Badri Narayana V.
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
  • Mukilan S. , Mukilan S.
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
  • Boobala Muralitharan D. Boobala Muralitharan D.
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
    Department of Computer Science and Engineering, Saranathan College of Engineering, Tiruchirappalli, India
view PDF
view PDF

How to Cite

M., Hariharan, Asik Ahmed A., Badri Narayana V., Mukilan S., and Boobala Muralitharan D. 2026. “Simulation-Based Stampede Prevention With Machine Learning and Explainable AI”. Recent Research Reviews Journal 5 (1): 156-69. https://doi.org/10.36548/rrrj.2026.1.010.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Crowd Risk Assessment
Pedestrian Simulation
Stampede Prevention
Machine Learning
Explainable AI
Proactive Crowd Management

Abstract

Large scale events held outdoors present a significant threat to public safety owing to excessive crowd density and insufficient pre-event risk assessment mechanisms. In this study, we propose a simulation-assisted crowd safety framework using pedestrian dynamics modeling, ensemble learning, and Explainable Artificial Intelligence (XAI). We have built digital event venues where pedestrian movement has been simulated considering various arrival rates and other environmental conditions. Features related to crowd dynamics such as density, average velocity, turbulence, and crowd pressure are analyzed from simulations based on around 20,000 scenarios in order to predict risks. XGBoost and LightGBM algorithms are utilized to calculate the continuous score representing the risk of stampedes while SHAP explanations give insightful understanding of the underlying cause of prediction outcomes. Our experiment proves good predictive performance with extremely high R² values (>0.998) and negligible prediction errors. The result of the explainability analysis suggests that crowd density and crowd pressure play the most important role in the rising risks. The proposed framework can help authorities to identify hot spots and test out new event venue plans.

References

  1. Bodrova, Anna S., Fatema Al Najim, and N. V. Brilliantov. "Lane Formation in an Active Particle Model with Chirality for Pedestrian Traffic." Physica A: Statistical Mechanics and its Applications 2024, vol. 643, 129796.
  2. Li, Kailing, Tiantian Yao, Xue Lin, Xiaoye Lin, and Xiaogang You. "Analysis of the Efficiency of Slope Evacuation for Dense Crowds in Urban Street-Type Public Spaces." Applied Sciences 2025, vol. 15, no. 7, 3568.
  3. Serek, Azamat, Beibut Amirgaliyev, Rita Yi Man Li, Ainur Zhumadillayeva, and Didar Yedilkhan. "Crowd Density Estimation Using Enhanced Multi-Column Convolutional Neural Network and Adaptive Collation." IEEE Access 2025, vol. 13, 146956-146972.
  4. Shah, Afnan A. "Enhancing Hajj and Umrah rituals and crowd management through AI technologies: A Comprehensive Survey of Applications and Future Directions." IEEE Access 2024, vol. 12, 161820-161841.
  5. Tank, Dharmesh, and Sanjay G. Patel. "Deep Learning for Crowd Anomaly Detection: A Hybrid Spatiotemporal Approach for Public Safety." In International Conference on Data Science and Artificial Intelligence, Singapore: Springer Nature Singapore, 2025, 349-359.
  6. Lu, Ying, Jingwen Wang, Weihui Dai, Bingxue Zou, Xiaofang Lu, and Weisheng Hong. "Research on Risk Factors of Human Stampede in Mass Gathering Activities Considering Organizational Patterns." Frontiers in Public Health 2025, vol. 13, 1555735.
  7. Alotaibi, Sultan Refa, Hanan Abdullah Mengash, Mohammed Maray, Faiz Abdullah Alotaibi, Abdulwhab Alkharashi, Ahmad A. Alzahrani, Moneerah Alotaibi, and Mrim M. Alnfiai. "Integrating Explainable Artificial Intelligence with Advanced Deep Learning Model for Crowd Density Estimation in Real-World Surveillance Systems." IEEE Access 2025, vol. 13, 20750-20762.
  8. Khel, Muhammad Haris Kaka, Kushsairy Abdul Kadir, Sheroz Khan, Mnmm Noor, Haidawati Nasir, Nawaf Waqas, and Akbar Khan. "Realtime Crowd Monitoring—Estimating Count, Speed and Direction of People Using Hybridized YOLOv4." IEEE Access 2023, vol. 11, 56368-56379.
  9. Alashban, Adal, Alhanouf Alsadan, Norah F. Alhussainan, and Ridha Ouni. "Single Convolutional Neural Network with Three Layers Model for Crowd Density Estimation." IEEE Access 2022, vol. 10, 63823-63833.
  10. Alafif, Tarik, Mohammad Jassas, Alaa E. Abdel-Hakim, Ghada Alfattni, Hassan Althobaiti, Mohammed Ikram, Amirah Alharbi et al. "Towards an Integrated Intelligent Framework for Crowd Control and Management (IICCM)." IEEE Access 2025, vol. 13, 58559-58575.