Integration of Fog-Cloud-IoT for Smart Health Care System using Machine Learning Algorithm for Monitoring of Patients

Abstract

The complexity of healthcare systems has posed a significant challenge globally, leading to an increase in morbidity and mortality rates, particularly among elderly patients. The risk of data processing errors rises with the multiple connections of edge devices in hospital environments. The quality of healthcare services has been greatly improved by the integration of technologies like the Internet of Things (IoT), which is facilitated by fog and cloud computing. By tackling the difficulties present in intricate healthcare systems, these developments increase the efficacy, dependability, and efficiency of healthcare delivery. This study explores the difficulties posed by cloud and fog computing in intelligent healthcare systems and suggests an ensemble-based learning strategy for edge device data segregation. The suggested approach maximizes the layered architecture of edge devices for real-time data processing by utilizing a stacking-based ensemble classifier. With an emphasis on enhancing Quality of Service (QoS), the algorithm's performance is assessed using the FogSim simulator, taking into account variables like energy usage and mobility in healthcare settings. The findings show that the suggested method improves system reliability and detection accuracy for intricate traffic nodes.