Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
3 results
Search Results
Item Restricted AI-Driven Abnormal Behaviour Detection within Crowds(Sheffield Hallam University, 2025-01-08) Alsiraji, Mohammed; Wang, JingThe detection of abnormal behaviour in crowded areas is crucial given the reliance on video surveillance for public safety. By monitoring automated Video Anomaly De- tection (VAD) systems, authorities can manage crowds and intervene swiftly when accidents occur, particularly in congested regions such as city centres or stadiums. This study presents a graph-based learning framework leveraging Graph Neural Net- works (GNNs) and Multi-Layer Perceptrons (MLPs) for spatial-temporal feature extraction and anomaly detection. The approach constructs a graph where edges represent velocity similarities between objects in the scene, while nodes are enriched with features capturing the direction and magnitude of individual movements. The feature captures trajectory-based similarities and spatial-temporal attributes, en- abling effective graph construction for anomaly detection. The model integrates Graph Attention Networks (GATs) to encode the graph structure, creating latent embeddings that capture both local and global relationships between people, and the MLP decoder reconstructs the velocity relationships. This autoencoder (AE) struc- ture can identify anomalies by comparing the true movement with the reconstructed one, anomaly is detected when the reconstruction error is higher than the threshold. We conducted experiments on UCSD Pedestrians and UMN datasets, to evaluate the model. Demonstrating the successful use of similarities as graph features for GNNs to generate logical embeddings of a crowd movement, and highlighting the impact of the time windows on anomaly detection precision as reflected in F1 scores. The Area Under the Curve (AUC) metric shows stability, highlighting the model’s balanced performance. Qualitative analysis of the UMN dataset illustrates the model’s ability to align detection with visual anomalies. Overall, this study highlights the precision of the proposed graph-based anomaly detection framework in understanding crowd movement behaviours in crowd management surveillance systems.38 0Item Restricted Role of Risk Assessment and Management in Crowd Control in the Context of Cultural Events in Saudi Arabia(University of Surrey, 2024-10) Chadhary, Abeer; Chen, JasonAs Saudi Arabia transitions towards a diversified economy under Vision 2030, cultural events have become a cornerstone of its tourism strategy. However, the rapid expansion of these events introduces unique challenges, particularly in crowd management and risk assessment. This study explores the current practices, barriers, and opportunities for enhancing safety measures during cultural events in Saudi Arabia. Using a combination of theoretical frameworks—such as Classic Risk Theory and the Technology Acceptance Model (TAM)—and data collected through an online survey of event organizers, the research identifies critical risks, including overcrowding, adverse weather, and resource limitations. Findings reveal that while event organizers recognize the value of adopting advanced technologies like real-time tracking and drones, factors such as training gaps and financial constraints hinder their implementation. Additionally, the study highlights the disconnect between existing crowd management protocols and the dynamic needs of large-scale events. By providing actionable recommendations, including leveraging innovative technologies and improving stakeholder collaboration, this research aims to contribute to safer, more efficient cultural events in Saudi Arabia. Ultimately, it underscores the need for continual improvement in risk management strategies to align with the Kingdom's ambitious cultural and economic goals.26 0Item Restricted Analysing Crowd Behaviour and Management at Music Festivals Case Study MDLBEAST Soundstorm Festivals in Saudi Arabia(Saudi Digital Library., 2023-10-30) Alaskar, Munirah; Williams, MichaelThis dissertation invistigates crowd behaviour and management at Soundstorm Music Festivals in Saudi Arabia, spotlighting the importance of effective strategies for safety and enriched festival experiences in the evolving Middle Eastern festival culture. Utilising a mixed-methods approach, the study scrutinizes crowd dynamics in Soundstorm 2022 and its progression since inception. Through quantitative surveys and qualitative interviews with attendees and organisers, it uncovers insights into crowd behaviour, and the impact of crowd management initiatives. The study explores technology's role, demonstrated by real-time CCTV monitoring and mobile applications in modern crowd management. It fills a notable research gap in crowd management within the Middle Eastern music festival context, shedding light on the advancements in Soundstorm 2022's crowd management and persistent gender-based safety concerns. The RESPECT initiative by MDLBEAST and the MDLBEAST App signify progress, yet gaps in awareness and effectiveness of these measures indicate areas for further improvement to ensure a safer and more enjoyable festival ambiance. This dissertation not only contributes to the broader dialogue on safety and attendee experience in large-scale events but sets a precedent for subsequent research in this realm.31 0