CONFERENCE / ICCAIS-2026

Campus security has become a critical concern due to increasing of threats such as unauthorized access, abnormal activities, and emergency incidents. Conventional surveillance systems rely heavily on the manual monitoring and lack of automated threat analysis capabilities. This paper will presents a machine learning–driven campus security system integrated with Internet of Things (IoT) technologies for a real-time monitoring and intelligent incident detection. The proposed hybrid framework combines the Convolutional Neural Networks (CNN) for visual surveillance analytics, machine learning–based intrusion detection for access monitoring, and IoT-enabled sensing for contextual event analysis. Continuous video streams and sensor data are processed by using intelligent models to classify activities as normal or suspicious. Automated alert mechanisms enables the rapid emergency response. Experimental evaluation will be done by using the performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis demonstrate in improving the detection efficiency, reduced false alarms, and faster response compared to traditional systems.