Classification of covid patient image dataset using modified deep convolutional neural network system

Manjunathan Alagarsamy (K. Ramakrishnan College of Technology Trichy)
Karthikram Anbalagan (Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology)
Yuvaraja Thangavel (Kongunadu College of Engineering and Technology)
Jeevitha Sakkarai (Kalasalingam Academy of Research and Education)
Jenopaul Pauliah (Adi Shankara Institute of Engineering and Technology)
Kannadhasan Suriyan (Cheran College of Engineering)

Bulletin of Electrical Engineering and Informatics
Vol 11, No 4: August 2022

The number of people infected with the corona virus is steadily rising. Even after being treated and returned to normality, many who were impacted are still suffering from a variety of health problems. We suggest a new, more effective approach to dealing with this issue, as well as putting in place preventative measures to prevent the spread of disease. The modified convolutional neural networks (M-CNN) architecture is modified deepCNN architecture. Using existingcorona virus disease 2019(COVID-19) computerizedtomographyscan (CT scan) images, this suggested approach intends to develop a deep model for screening and forecasting the risk of disease propagation. The suggested model was trained using 1000 scan pictures from various sources, yielding a prediction accuracy of 93 percent, which is much greater than previous methods.