A Comprehensive Review on COVID-19 Detection Based on Cough Sounds, Symptoms, CXR, and CT Images

The worldwide spread of the coronavirus illness has led to the requirement of creating machine-based technologies to identify the diseases. The worldwide pandemic caused by new coronaviruses has resulted in a significant loss of life and necessitates the development of several affordable diagnostic methods to detect the presence of COVID-19 infection. Thankfully, the current era of advanced technology, including transfer learning (TL) approaches, has improved several areas of human health and enabled the identification of chronic and communicable diseases. There is a need for thorough investigation in order to combat the transmission of this alarming virus via the use of evidence-based intelligence models and implementation of preventive measures. The present systematic review focuses on the examination of TL and fuzzy ensemble techniques that have been described in the literature pertaining to strategies for detecting COVID-19. Multiple studies have used cough sounds, CT scans, X-ray images, and symptoms information to identify cases of COVID-19. The application of DL/ML, TL, fuzzy ensemble, and fuzzy inference approaches for COVID-19 identification is discussed in this paper.