machine learning algorithms to prevent the spread of infectious diseases based on effective features in the diagnosis of Covid-19

This study aimed to develop IoT-based machine learning algorithms care and improvement while detecting and predicting real-time epidemics.The target disease is COVID-19 due to its importance and epidemic.The research method is based on design science. The research approach is forward-looking, so the mechanism of disease transmission and its effective characteristics enable us to make predictions about the disease and thus design disease control strategies and health care.The research was carried out in a seven-step process. IoT features were extracted in the present study with experts' opinions. The features obtained in the experiment of two different algorithms, "k nearest neighbor" and "decision tree," were created on the data to determine the best model.After selecting the best depth validation of the model were performed by confusion matrix analysis.The results of running k-nearest neighborhood and Decision Tree algorithms for the prediction of COVID-19 indicated an accuracy of > 98%. Higher sensitivity (99%) was obtained in the Decision Tree algorithm, which is very important diagnosing COVID-19 and indicates the minimum number of false negatives in the test results.