Smart Health Monitoring for Predicting Heart Disease using IoT-Fog-Cloud Computing Model

Real‑time monitoring of heart health with IoT devices runs into two big problems when it depends only on a distant cloud: slow response times and high energy use. To fix this, the study looks at a three‑layer IoT‑Fog‑Cloud system that moves computing power closer to the user. It proposes an Optimized Naïve Bayes Random Forest (ONBRF) model that works well on this distributed setup. The researchers used heart‑related data gathered in Gombe State, Nigeria. They trained and tested both machine‑learning and deep‑learning models to predict heart‑disease risk instantly. The fog layer sits between the sensors and the cloud; it cleans and analyzes data on‑site, which cuts down the amount of

data sent to the cloud and reduces network delay. The evaluation measures several key numbers: energy consumption, precision, accuracy, recall, F1 score, and AUC. For B.Tech students, this framework offers a hands‑on guide for building distributed IoT apps. It shows how to split work among edge devices, fog nodes, and a central cloud to get both fast computation and accurate predictions.

Message: Hi FE, I need help with “Smart Health Monitoring for Predicting Heart Disease using IoT-Fog-Cloud Computing Model” in “Cloud Computing & IoT”