Stationary Wavelet Entropy and Cat Swarm Optimization to Detect COVID-19

Accurate and efficient approaches are urgently needed to cope with the rapid spread of COVID-19 worldwide. A novel approach is presented in this paper, which combines Stationary Wavelet Entropy (SWE) and Cat Swarm Optimization (CSO) to enhance the precision and effectiveness of COVID-19 detection. SWE, a signal processing technique, extracts informative features from medical data. At the same time, CSO, a bio-inspired optimization algorithm, is used to fine-tune the parameters of a feed-forward neural network. Integrating these two techniques within our methodology addresses the complex and evolving nature of COVID-19 detection tasks. SWE efficiently captures irregularities and patterns in medical data, providing valuable inputs to the neural network, while CSO automates parameter tuning, optimizing the network’s performance. Experimental results demonstrate the efficacy of our approach, showcasing its ability to accurately identify COVID-19 cases in diverse medical datasets. The synergy between SWE and CSO offers a promising avenue for enhancing COVID-19 detection, contributing to the global effort to combat the pandemic.