A Healthcare System for COVID19 Classification Using Multi-Type Classical Features Selection

The coronavirus (COVID19), also known as the novel coronavirus, first appeared in December 2019 Wuhan, China. After that, it quickly spread throughout world and became a disease. It has significantly impacted our everyday lives, national international economies, public health. However, early diagnosis is critical for prompt treatment reducing trauma healthcare system. Clinical radiologists primarily use chest X-rays, computerized tomography (CT) scans to test pneumonia infection. We used Chest CT predict COVID19 healthy this study. proposed joint framework prediction based on classical feature fusion PSO-based optimization. begin by extracting standard features such discrete wavelet transforms (DWT), cosine (DCT), dominant rotated local binary patterns (DRLBP). In addition, we extracted Shanon Entropy Kurtosis features. following step, Max-Covariance-based maximization approach proposed. fused are optimized preliminary phase using Particle Swarm Optimization (PSO) ELM fitness function. For final prediction, PSO obtain robust features, which then implanted Support Vector Data Description (SVDD) classifier. experiment carried out available Scans from patients. These images Radiopaedia website. scheme, selection process accuracy 88.6% 93.1%, respectively. A detailed analysis conducted, supports system efficiency.