Deep Learning Crime Monitoring and Alerting System using Hybrid Feature Engineering technique with IoT Technology

This paper presents a Deep Learning-based Crime Monitoring and Alerting System that integrates IoT technology with a Hybrid Feature Engineering technique using Vision Transformer and Bidirectional Gated Recurrent Units. The system employs IoT devices, such as surveillance cameras, motion sensors, and microphones, to collect real-time environmental data. The HFE technique extracts spatial and temporal features, where ViT captures intricate spatial patterns from visual data, while BiGRU analyses time series sensor data to detect sequential anomalies indicative of criminal activities. By combining these deep learning models, the system identifies suspicious behaviours like unauthorized access, physical altercations, or disturbances with high accuracy and triggers immediate alerts to law enforcement for timely intervention. The integration of ViT for spatial feature extraction and BiGRU for temporal modelling enhances crime detection with minimal human intervention. This approach demonstrates the potential of IoT and Deep Learning to improve public safety, making crime monitoring more efficient, adaptive, and responsive.