COVID-19 Data Analytics Using Extended Convolutional Technique

Abstract

Health care system, lifestyle, Industrial growth, economy and livelihood of human-beings worldwide effected due to triggered global pandemic by COVID-19 virus originated and first reported from Wuhan city, Republic Country of China. COVID cases are difficult to predict and detect on its early stages due to that its spread and mortality is uncontrollable. RT-PCR (Reverse Transcription Polymerase Chain Reaction) is still first and foremost diagnostic methodology accepted worldwide, hence it creates a scope of new diagnostic tools and techniques of detection approach which can produce effective and faster results compared to its predecessor. Innovational through current studies that complements to the existence of COVID-19 to findings in Chest X-ray snap shots, the proposed research’s method makes use of present deep getting to know models (U-Net and ResNet) to method those snap shots and classify them as the positive patient or the negative patient of COVID-19. The proposed technique entails the pre-treatment phase through dissection of lung, getting rid of the environment which does now no longer provide applicable facts and can provide influenced consequences; then after this, preliminary degree comes up with the category version educated below the switch mastering system; and in conclusion, consequences are evaluated and interpreted through warmth maps visualization. The proposed research method completed a detection accuracy of COVID-19 round 99%.