Main Article Content
In today's world, healthcare facilities are a major problem, particularly in underdeveloped nations where rural areas lack access to high-quality hospitals and medical specialists. Soft computing has improved health in the same way that it has benefited other sectors of life. Smart healthcare applications rely heavily on wearable technologies. The technique of detecting and analyzing physiological data from healthcare sensor devices is critical in smart healthcare. Fog computing is used to reduce the delay imposed by cloud computing by analyzing physiological data. However, in a fog environment, latency for emergency health status and overloading become major difficulties for smart healthcare. This study addresses these issues by proposing a unique Fog enabled Intelligence Clinical Decision Support System (FICDSS) health architecture for physiological parameter detection that enhances therapeutic and diagnostic efficiency in the health area. Sensor layer, edge layer, fog layer, and cloud layer are the four layers that make up the entire system. Data from patients' wearable or non-wearable devices is sent over an interface to an edge layer with a microcontroller system in the first layer. The edge layer's goal is to collect, process, and transfer data to the fog layer for intelligent computing. We introduced the Fuzzy Logic Inference System (FLIS), which determines the user's health condition using temporal changes in data gathered from devices deployed at the edge layer to forecast the user's health state in real time. The FLIS system takes context information from the sensor as input (in crisp form), and the fuzzification module turns the input into a fuzzy linguistic variable, which is then provided to the patient or doctor as an output. The fog layer detects the user's health state based on health parameter attributes. Finally, response and real time data from sensors is observed at cloud layer. Both cloud and fog layers take rapid response based on the user's health state. A comprehensive simulation in the MATLAB tool is used to build and evaluate the suggested fuzzy logic inference system. In terms of latency, execution time, and detection accuracy, it performs better.