| Summary: | The increase in popularity for wearable technologies has opened the door for an Internet of Things (IoT) solution to healthcare. One of the most prevalent healthcare problems today is the poor survival rate of out-of-hospital sudden cardiac arrests. Not only that, most of the conventional device are also wired and unfriendly device. Most of the people nowadays have no alert and better awareness about their health condition. The objective of this study is to present a multisensory system using IoT that can collect physical activity heart rates and body temperatures that can alert about their health condition. For this study, we implemented an embedded sensory system with a Low Energy Bluetooth communication module to discreetly collect electrocardiogram and body temperature data using a smartphone in a common environment. To identify approaching heart illness using Machine learning techniques, a preliminary design of a cloud-based heart disease prediction system was developed. An effective machine learning approach created from a separate examination of many machine learning algorithms in WEKA should be applied for the correct identification of heart disease. Random Forest algorithm be used in this study which is got the best performance with 83% accuracy then the other algorithms in WEKA. This algorithm was applied in the Python using Google Colab to make prediction of the sudden cardiac arrest. As the result, to make a prediction user need to set their data health in the Python using Random Forest algorithm to detect either they have a heart disease or not.
|
|---|