Covid-19 Detection by Wavelet Entropy and Genetic Algorithm

ABSTRACT

The number of deaths caused by COVID-19 is still rising. People still cannot predict the end of this pandemic. Finding out people who may be infected and then monitoring their vitals is an emergency matter. Using medical images to make a diagnosis can provide more information than nucleic acid tests can provide, such as what period the patient was in and the lesion site. In this paper, we use wavelet entropy combined with genetic algorithm to make detection of COVID-19 through CT images. In this method, we expect to use wavelet entropy to extract signal features and genetic algorithm to find the optimal solution. The K fold cross-validation method does not need a large amount of data to complete the verification, and small data sets can also achieve the effect. In the last section, we compare our results with other methods, including RBFNN, KELM, BA. The accuracy of this method reached 73.45%, which is higher than other methods for comparison. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.