Remote Healthcare Monitoring Based on Fuzzy-Assisted Machine Learning Framework with Fog-Computing System

Using recent information technology developments, remote patient monitoring (RPM) delivers healthcare to patients outside traditional care facilities. Sensitivity information about physical and mental health may be gathered using networked sensors on the body or implanted in the home. Health care may be revolutionized if data is gathered consistently, shared, and mined effectively. The most difficult part of managing diabetes is thereby keeping track of blood sugar levels all the time. The wrong medication may be administered if glucose levels are the sole factor considered rather than other factors such as ECG and physical activity. This research proposes a fog-computing assisted remote healthcare monitoring (FC-RHM) system to improve illness forecasting accuracy. This method relies on fuzzy systems, which estimate the minimum computing resources required to deal with cloud and fog predictions. Fuzzy-aided fog-cloud delivery is used to collect requests for healthcare access. The study suggested that machine learning using Long Short-Term Memory (LSTM) is utilized to classify the data. FC-RHM's numerical result is primarily utilized to verify the improved expansion ratio, delay time, detection accuracy, system stability ratio, and reaction time compared to prior methods.