Intelligent Crowd Analysis and Risk Prediction : A Spatial–Temporal and Mathematical Approach

This book presents a comprehensive framework for intelligent crowd analysis and risk prediction using advanced spatial–temporal modeling and mathematical techniques. It explores how data-driven approaches can identify patterns, predict crowd behavior, and assess potential risks in dynamic environments. By integrating analytics, computational models, and real-world applications, the book offers practical insights for researchers, engineers, and decision-makers. It is an essential resource for understanding modern crowd management, enhancing public safety, and developing smart surveillance systems in increasingly complex urban settings.

Sathvik Rangu
B.Tech in Computer Science and Engineering (2022–2026)
Mohan Babu University, Tirupati, India
Sathvik Rangu is a final-year undergraduate researcher in Computer Science and Engineering at Mohan Babu University, Tirupati, with a distinguished academic record (CGPA 9.2/10). His research interests lie at the intersection of computer vision, machine learning, and real-time intelligent systems, with a particular focus on crowd safety and risk detection.
He is the principal architect of the Crowd Stampede Risk Detection System, a computer vision framework designed to estimate crowd density and detect potential stampede risks from live surveillance video streams. The system integrates crowd flow analysis, real-time density estimation, and spatial congestion mapping to provide early warning in high-density public environments. His engineering work on this system directly underpins the research presented in this book. Sathvik is a published IEEE author. His first publication, co-authored with collaborators, presents an Integrated CNN and YOLOv5 Framework for Plant Disease Identification (IEEE, 2025), applying deep learning to agricultural disease classification through image-based analysis. His second work, Early Stampede Risk Estimation Using YOLOv8, was presented at IEEE CCIC 2026 (Paper ID: 1981). This study proposes a spatial–temporal crowd behaviour analysis framework leveraging YOLOv8 for real-time risk monitoring, and forms the core technical contribution upon which this book is based. He can be reached at sathvik.achari.2004@gmail.com and his work is publicly available on GitHub at github.com/Sathvikxr and LinkedIn at linkedin.com/in/sathvik-r.


Siva Kumar Allu
B.Tech in Computer Science (Data Science) | Mohan Babu University, Tirupati
Siva Kumar Allu is an undergraduate student in Computer Science with a specialisation in Data Science at Mohan Babu University, Tirupati. His academic work spans Java, Python, SQL, and web development, with additional exposure to data visualisation tools including Power BI and Tableau. He has also engaged in ongoing practice of data structures and algorithms through competitive programming platforms.

Sura Manoj
B.Tech in Computer Science | Mohan Babu University, Tirupati
Sura Manoj is an undergraduate student in Computer Science at Mohan Babu University, Tirupati, with interests in data science and Python development. His coursework and self-directed projects cover Python, Java, SQL, and basic web technologies. He has completed certifications in Python programming through Cisco NetAcad and in artificial intelligence and deep learning through Infosys. His project work includes a static e-commerce website built with HTML and CSS, and an AI-based facial emotion detection system using a convolutional neural network integrated with a Flask backend. He can be contacted at manojsura9949@gmail.com and his project work is available at github.com/suramanoj.