Khanam, Sadia, Chalak Qazani, Mohamad Reza, Mondal, Subrota Kumar, Kabir, H.M. Dipu, Sabyasachi, Abadhan S., Asadi, Houshyar, Kumar, Keshav, Tabarsinezhad, Farzin, Mohamed, Shady, Khorsavi, Abbas, and Nahavandi, Saeid (2022) CoV-TI-Net: Transferred Initialization with Modified End Layer for COVID-19 Diagnosis. In: Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics. pp. 2237-2243. From: SMC 2022: IEEE International Conference on Systems, Man, and Cybernetics, 9-12 October 2022, Prague, Czech Republic.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

This paper proposes transferred initialization with modified fully connected layers for COVID-19 diagnosis. Convolutional neural networks (CNN) achieved a remarkable result in image classification. However, training a high-performing model is a very complicated and time-consuming process because of the complexity of image recognition applications. On the other hand, transfer learning is a relatively new learning method that has been employed in many sectors to achieve good performance with fewer computations. In this research, the PyTorch pre-trained models (VGG19_bn and WideResNet -101) are applied in the MNIST dataset for the first time as initialization and with modified fully connected layers. The employed PyTorch pre-trained models were previously trained in ImageNet. The proposed model is developed and verified in the Kaggle notebook, and it reached the outstanding accuracy of 99.77% without taking a huge computational time during the training process of the network. We also applied the same methodology to the SIIM-FISABIO-RSNA COVID-19 Detection dataset and achieved 80.01% accuracy. In contrast, the previous methods need a huge compactional time during the training process to reach a high-performing model. Codes are available at the following link: github.com/dipuk0506/Spina1Net

Item ID:	87054
Item Type:	Conference Item (Research - E1)
ISBN:	978-1-6654-5258-8
Copyright Information:	© 2022 IEEE
Date Deposited:	27 Oct 2025 23:25
FoR Codes:	46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461103 Deep learning @ 70% 42 HEALTH SCIENCES > 4206 Public health > 420603 Health promotion @ 30%
SEO Codes:	28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280112 Expanding knowledge in the health sciences @ 40% 22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220403 Artificial intelligence @ 60%
	More Statistics