COVID-19 Screening Based on Application of Neural Network Classification of Exhale Spectra

This article describes the use of convolutional neural networks to screening first stage of the COVID on exhale spectra. A distinctive feature is the use of the glow-dicharge optical spectroscopy. The hypothesis put forward about the use of spectra images, and not the spectra themselves, for classification was confirmed. Accuracy was 87 %. However, accuracy is affected by obtaining stable exhale spectra. The impact on the spectrum of concomitant diseases, smoking, pregnancy is not fully understood. However, CNN can be used to diagnose COVID with an acceptable level of accuracy. The results described in the work are the initial stage of research. © 2022 IEEE.