Search for: All records

The safety and security of educational environments are paramount concerns for communities worldwide. Recent incidents of violence in schools underscore the urgent need for innovative and proactive safety measures that extend beyond traditional reactive approaches. In response to this imperative, we propose an Advanced Federated Learning- Empowered Edge-Cloud Framework for School Safety Prediction and Emergency Alert System, which is a groundbreaking solution designed to address the pressing challenges of ensuring school safety. In a world where educational institutions face escalating threats, this framework leverages the innovative approach of federated learning, enabling real-time threat detection and proactive alert generation while preserving data privacy. Challenges such as delayed response times, false alarms, and limited threat assessment protocols are met head-on through the integration of predictive algorithms, sensors, and edge computing. This transformative system not only revolutionizes security but also prioritizes the psychological well-being of students, staff, and visitors, fostering an environment conducive to learning. Its significance lies in its potential to prevent incidents, minimize harm, and bolster community confidence in school safety measures, ultimately contributing to the well- being and growth of future generations. Through this pioneering work, we aim to redefine school safety paradigms, making educational institutions safer and more secure for all. 

The healthcare industry has experienced a re-markable digital transformation through the adoption of IoT technologies, resulting in a significant increase in the volume and variety of medical data generated. Challenges in processing, analyzing, and sharing healthcare data persist. Traditional cloud computing approaches, while useful for processing healthcare data, have drawbacks, including delays in data transfer, data privacy concerns, and the risk of data unavailability. In this paper, we propose a software-defined 5G and AI-enabled distributed edge-cloud collaboration platform to classify healthcare data at the edge devices, facilitate realtime service delivery, and create AI/ML-based models for identifying patients' potential medical conditions. In our architecture, we have incorporated a federated learning scheme based on homomorphic encryption to provide privacy in data sharing and processing. The proposed framework ensures secure and efficient data communication and processing, ultimately fostering effective collaboration among healthcare institutions. The models will be validated by performing a comparative time analysis, and the interplay between edge and cloud computing will be investigated to support realtime healthcare applications.