Abstract: This paper focuses on a self-sufficient UAV-supported monitoring system that can be used to improve smart campus security through real-time crowd analytics and anomaly detection. The system combines a quadrotor drone with a Pixhawk flight controller, a u-blox M10 GPS module, and a stabilized HD camera with the YOLOv8 deep learning model for human detection. It detects unusual activities such as crowd rushes, unauthorized presence, and abnormal dispersion. GPS-based geofencing is used to control patrols within specific areas, while aerial video is streamed to an edge AI processing unit. In trials, over 92% detection accuracy was achieved with highly responsive alerts. The system is modular, scalable, and adaptable to other enclosed environments, providing proactive situational awareness.
immersive discovery of viability as a new direction in the development of intelligent scientific environments within the framework of Vitology. The proposed approach combines immersive technologies, artificial intelligence, digital twins, interactive simulation, multidimensional…
Code and result data accompanying a manuscript on AI-driven anomaly detection and post-quantum-secured recovery for the Internet of Medical Things (IoMT), currently under peer review. Includes the leakage-audited anomaly detector, the digital-twin-gated recovery simulation with c…
Surveillance anomaly detection systems built around a single monolithic deep network are difficult to interpret, brittle to distribution shift, and offer operators no rationale on which to act. This paper presents VisionGuard, an explainable deep learning framework that reorganiz…
Testing the Transition from AI Advantage to Practical Dependence: A Minimal Knowledge-Work Pilot Protocol presents a preregistration-ready experimental design for testing two early mechanisms through which a local generative-AI advantage might contribute to practical dependence i…
Blockchain-integrated deep learning intrusion detection systems for the Internet of Things have attracted growing research attention, yet the relationship between detection depth and blockchain trust scope in these architectures has not been examined systematically. This analysis…