A multi-dimensional convolutional neural network for automatic covid 19 positive detection from chest x ray images with improved accuracy over CNN

The objective of the study is to detect the covid-19 positive patient with the help of Chest X-ray image dataset by using machine learning based on Multi-dimensional Convolutional Neural Network Algorithm. To achieve accuracy a novel augmented dataset classification is used. Accuracy and Loss of Covid-19 detection are Performed from kaggle library. Dataset of 2400 chest image dataset with total sample size 30. The two groups Multi-dimensional Convolutional Neural Network(N=15) and Convolutional Neural Network(N=15). The study proved that Multi-dimensional Convolutional Neural Network achieved better accuracy as 99.66% which is higher, compared to Convolutional Neural Network accuracy as 99.13%. Finally, Multi-dimensional CNN appears significantly better than CNN. The two algorithm Multi-dimensional CNN and CNN are statistically satisfied with the independent sample T-test value(p<0.001) with confidence level of 95%. Study shows Multidimensional CNN seems better (Std. Error Mean= 1.96525) than CNN(Std. Error Mean= 6.13974).