Self-aware COVID-19 AI Approach (SIntL-CoV19) by Integrating Infected Scans with Internal Behavioral Analysis

Abstract

In the Artificial intelligence (AI) field, intelligent social awareness is a quantifiable analysis that interacts with humans socially with other infected or non-infected COVID-19 (CoV19) humans. However, less importance is given in this direction. Clinically, there is a need for a social-awareness automated model design to quantify the self-awareness of infected patients and develop a social learning system. In this research paper, a new model of self-aware internal learning coronavirus 19 (SIntL-CoV19) model technique is presented with quantification measures to represent model requirements as an individual self-aware automated detection. Through this model, a human can communicate with the social environment and other humans with an accurate CoV19 infection diagnosis. SIntL-CoV19 model framework for implementation of self-aware architecture with this model is proposed making the diagnosis process compared with the existing architecture. The proposed model achieves improved accuracy Feature Classifier, which outperforms other learning algorithms for CoV19 and normal scans. The data from the investigation show that the proposed SIntL-CoV19 model method might be more effective than other methods.