An Covid-19 Disease Prediction and Analysis Using Sprint Algorithm in Machine Learning Technique

Abstract

Technology innovation, social media platforms, and online communication play a vital role in balancing human life during the COVID-19 epidemic. Scientists have struggled to predict this disease accurately because of its uniqueness and rapid spread. This is partly caused by variations in human behavior and environmental elements that affect the spread of diseases. However, it spread untruths and misinformation about the disease and the vaccine.The accuracy in determining the covid-19 patients, real news, and fake news becomes very challenging due to widespread and enormous data generation. In our research, we proposed an improved SPRINT algorithm for classifying the correct and incorrect predictions in terms of accuracy.The Histogram and the attribute table are two data structures that the enhanced SPRINT method specifies. The three components of the property sheet are the indexing of attribute value, class identification, and data records. The proposed algorithm is executed in MATLAB code to generate the training model. The accuracy of the proposed system is evaluated with the AdaBoost algorithm with the Random Forest model [16] and with machine learning methods SVM and KNN [17]. The improved SPRINT algorithm shows better results on all the performance metrics than the others. The accuracy obtained by the proposed improved SPRINT algorithm is 99.5% which is far better than the others.