Light Deep Learning Model Architecture for Chest X-ray based Covid-19 Detection

Sumari, P.; Syed, S. J.; Sheng, L. H.

Covid-19 is a serious public health problem worldwide. To date, it has spanned worldwide with 12.8 million infected and 566, 909 confirm death. Covid-19 screening is indeed an important task and has to be done quickly as possible to many people so that early treatment can be done. The current world RT-PCR standard screening for Covid-19 detection no longer can cope to the demand of large world population. There is a need of other quick diagnosis procedure such as to use chest x-ray images and light computing algorithm to accelerate the covid-19 screening. This paper proposes Covid-19 detection based on chest X-ray image with a light computer processing. The proposed work introduces the combination of Gray Level Co-occurrence Matrix (GLCM) and Convolutional Neural Network (CNN) methods to detect Covid-19 symptom. The light version is coming from GLCM simplicity and convolutional neural network (CNN) single layer. It is fast and suitable method for places where computing resources are minimal. With light processing component, the proposed work gives the highest classification performance with 97.06% accuracy compared to other similar works. © 2021 IEEE.