Efficient Generative transfer learning framework for the detection of COVID-19
- Sri Sivasubramaniya Nadar College of Engineering
{bhuvanaj, mirnalineett, bharathib}@ssn.edu.in, infantsneha17059@cse.ssn.edu.in
Abstract
Deep learning plays a major role in detecting the presence of Coron-avirus 2019 (COVID-19) and demands huge data. Availability of annotated data is a hurdle in using Deep learning technique. To enhance the accuracy of detection Deep Convolutional Generative Adversarial Network (DCGAN) is used to generate synthetic data. Densenet-201 is identified as the deep learning framework to de-tect COVID-19 from X-ray images. In this research, to validate the effectiveness of the Densenet-201, we explored conventional machine learning approaches such as SVM, Random Forest and Convolutional Neural Network (CNN). The feature map for training the machine learning approaches are extracted using Densenet-201 as feature extractor. The results show that Densenet-201 as feature representation with SVM is performing well in detecting COVID-19 with high accuracy. More-over we experimented the proposed methodology without using DCGAN as well. DenseNet-201 based approach is capable of detecting the presence of COVID-19 with high accuracy. Experiments demonstrated that the proposed transfer learning approach based on DenseNet-201 along with DCGAN based augmentation outper-forms the State of the art approaches like ResNet50, CNN, and VGG-16.
Key words
COVID-19, Densenet-201, DCGAN, Disease Classification, Data Augmentation, Deep learning
Digital Object Identifier (DOI)
https://doi.org/10.2298/CSIS220207033B
Publication information
Volume 19, Issue 3 (September 2022)
Year of Publication: 2022
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium
Full text
Available in PDF
Portable Document Format
How to cite
Bhuvana, J., Mirnalinee, T. T., Bharathi, B., Sneha, I.: Efficient Generative transfer learning framework for the detection of COVID-19. Computer Science and Information Systems, Vol. 19, No. 3, 1241-1259. (2022), https://doi.org/10.2298/CSIS220207033B