Classification of COVID-19 from Chest X-Ray Images Using Deep Learning Techniques
Résumé
Abstract COVID-19 is an outbreak and pandemic disease transmitted through the air and by physical contact. The aim of this study was to develop an automatic classification of COVID-19 from digital medical of chest X-ray images using deep learning techniques. The techniques that were used in this study are, image preprocessing, data augmentation, and data preparation. Proposed Convolutional Neural network Model and Two pretrained Convolutional Neural network, which are VGG16, and Inception, were selected and fine-tuned with data augmentation to carry out 2-class classification tasks using chest X-ray images. From this, 80% of the images are used for training and the rest for testing the model. The features extracted are fit into the neural network with 500 epochs, 80/20 splitting ratio, and 0.001 learning rate. Convolutional Neural network model achieved with the Inception-V3 of 98.16% average training accuracy as compared to VGG16 with 93.65% and proposed convolutional neural network classifier with 73.85%. The experimental result showed that the overall Inception-V3 classifier yielded the highest performance evaluation of 95.4% accuracy as compared to VGG16 (with 93.08%) and Convolutional Neural network proposed model classifier (with 55%). The future work will look into the problem the number of images and the bigger the number of the images is, the better the model is trained from scratch.
Citer ce document
Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)
Accès au document
Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter
Voir l'article sur le site de la revueLicence et provenance
Licence : CC BY
Notice moissonnée depuis OpenAlex le 09/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →