Subject Area

Computer and Control Systems Engineering

Article Type

Original Study


A virus called COVID-19 has caused devastation throughout the world and is still putting people's lives in jeopardy. It is important to identify COVID-19 patients as soon as possible so that they can be treated and kept from spreading. A new framework for recognizing COVID-19-infected individuals would be provided in this study. The patient’s recognition framework (PRF) is a term used to describe a method for detecting patients. The PRF consists of three stages, which are: the pre-processing stage (P2S), the feature selection stage (FS2), and the classification stage (CS). The P2S extracts a collection of features from CT chest scan images for a variety of people, some of whom are infected with COVID-19 and others who are not. FS2 selects only the most beneficial characteristics when detecting COVID-19 patients from P2S by using the enhanced moth flame optimization (EMFO) approach as a wrapper method. The CS employs the support vector machine (SVM) classifier to accurately detect COVID-19-contaminated individuals with the shortest possible time cost, relying on EMFO's significant features. According to analytical outcomes, the PRF strategy exceeds contemporary techniques in terms of efficiency. PRF achieves the highest accuracy, precision, and recall. Besides, it achieves the lowest error, with values equal to 98%, 93%, 92%, and 2%, respectively.


COVID-19, Moth Flame Optimization, Feature Selections, Rough set

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Included in

Engineering Commons