Computer Tomography Image Based Interconnected Antecedence Clustering Model Using Deep Convolution Neural Network for Prediction of COVID-19

The sudden appearance of the COVID-19 pandemic as a major health threat is a serious concern for global health professionals. The world's most pressing problem has now been revealed to be a deadly virus. Because of the limited supply of test kits and the need to screen and diagnose patients quickly, a self-operating detection strategy is required for the detection of COVID-19 infections and disorders. SARS-CoV-2 can be adequately screened to lessen the impact on healthcare systems. Models that incorporate a multitude of factors can predict the likelihood of infection. Deep convolutional neural networks (DCNN) use a fullresolution Convolutional network to partition the effected region for easier identification and classification. Use of an existing patient dataset with trained and tested samples for
recognition, segmentation and classification is used to evaluate the proposed model. For clinicians worldwide, especially those in countries with little resources in the healthcare sector, new technologies are being developed. Computer Tomography (CT) testing results can be improved by using larger datasets from outside the field. There is a considerable possibility that CT scan interpretation could benefit from knowledge gained from out-ofthe-field training. In order to accurately classify and predict COVID-19 from CT scans, an effective Interconnected Antecedence Clustering Model employing DCNN (IACM-DCNN)
is proposed in this research. There are a number of datasets taken into account by the proposed model, including https://andrewmvd.kaggle.com/datasets and https://mosmed.ai/datasets and https://github.com/UCSDAI4H/COVID-CT/tree/master.
When compared to current models, the proposed model's detection accuracy is better.