A Novel Covid-19 Detection System Based on PSO and Hybrid Feature Using Support Vector Machines

The world first met the coronavirus (COVID-19) in Wuhan, China December 2019. It has continued to increase its influence from encounter until today. detection of this virus, which caused death many, is great importance There are many approaches disease. One most effective these COVID-19 disease using chest X-Ray images. In paper, an intelligent system was proposed classify normal, pneumonia patients and composed four stage. At first, all images dataset were pre-processed. Then for feature extraction uniform Local Binary Pattern (LBP) DenseNet201 deep learning models used. Particle swarm optimization (PSO) algorithm used select features. determined features classified by support vector machine (SVM). Accuracy AUC parameters as performance criteria. Evaluated accuracy values 99.9%, 1.00, respectively. model codes made publicly available at: https://github.com/mfatiho/covid-detection-chest-xray