Predicting the Spread of Covid Disease Based on Chest X-Ray Images Using Convolutional Neural Network with Improved Accuracy

The major intent of this article is to forecast the spread of corona disease based on x-ray images with an improved accuracy rate by using a Convolutional Neural Network (CNN) in comparison with the Naive Bayes (NB) Classifier. Materials & Methods: The data set in this paper utilizes the publicly available Kaggle corona data set. The sample size for identifying the corona based on thorax x-ray images with the improved precision rate was sample 1000 (Group 1=500 and Group 2=500) and the alpha and beta values of 0.06,0.3 are used for calculating G-power 0.7 with a confidence interval at 95%. Predicting the spread of corona disease based on thorax x-ray images with improved accuracy rate is performed by Convolutional Neural Network (CNN) whereas the number of samples in Naive Bayes (N=10). Results: The CNN classifier has a 95.686640 high accuracy rate while compared to the accuracy rate of Naive Bayes (NB) is 91.251527. The study has a significance value of p<0.05 i.e. p=0.0271. Conclusion: Convolutional Neural Network (CNN) provides better outcomes in accuracy rate when compared to Naive Bayes (NB) for forecasting the spread of corona disease based-on thorax X-ray images.