IOT Enabled Heart Disease Detection System Using KNN

Ankur Utsav, Shreeya Mohanty, Kumar Bishwajeet, Tanay Kumar

Abstract: Many people around the world suffer from heart disease, which is a critical health issue. Early identification of disease is important in order to save many lives. Internet of things (IoT) technology is being developed in conjunction with the healthcare industry. IoT sensor data collected through IoT devices may contain more noise and missing values than data collected from traditional datasets.In order to remotely anticipate and monitor patients with heart disease, technological assistance or clinic professionals is needed. This model is developed with the help of classification algorithms, as they play an important role in predicting.Different classification techniques, including Random Forest, Support Vector Machine (SVM), K-nearest Neighbors (KNN), and Decision Tree, are used to create the model. The classifiers are trained and tested using the Cleveland data repository. As part of our research, we have also sought to find correlations between the different attributes of the dataset using standard machine learning methods and then used them effectively to predict chances of heart disease. In this research work, we have used a benchmark dataset of Cleveland Dataset, which consists of 14 different parameters. KNN has the best accuracy of all classifiers assessed using performance metrics. The KNN model may be utilized in healthcare, which is essential in the field of cardiology to accurately and practically diagnose cardiac disorders.The goal of this study is to create a model for anticipating cardiac illness using machine learning methods from IoT sensor devices, which has so far yielded a prediction accuracy that is satisfactory.