Akademik Veri Yönetim Sistemi
JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, cilt.26, sa.2, ss.541-551, 2023 (ESCI)
The number of coronavirus patients around the world is increasing day by day. Although more than one year has passed since the emergence of the disease, statistics show that the peak number of patients have not reached yet. The spread of the increase in the number of patients over time is important to prevent hospital occupancy rates from hitting dangerous levels. For this reason, people carrying the virus should be diagnosed quickly and isolated from society until the disease is over. In this study, a comprehensive artificial neural network-based model has been proposed for rapid disease diagnosis using X-ray images. Using the damage created by the coronavirus in the lung tissues, the diagnosis can be made within seconds. The model subject to study improves and augments X-ray images by pre-processing. After training is performed using DenseNet201, ResNeXt-101(32x8d), VGG-19bn and Wide-ResNet101-2 networks, Covid-19 positive or negative diagnosis is provided from the image. The best result obtained in the is achieved network with an overall rate of 94.79%.