The Diagnosis of COVID-19 Through X-Ray Images via Transfer Learning Pipeline

Amiir Haamzah Mohamed Ismail, Muhammad Amirul Abdullah, Ismail Mohd Khairuddin, Wan Hasbullah Mohd Isa, Mohd Azraai Mohd Razman, Jessnor Arif Mat Jizat, Anwar P. P. Abdul Majeed*

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

1 Citation (Scopus)

Abstract

Transfer Learning (TL) opens new possibilities of detection of disease through radiography as compared to conventional machine learning as well as deep learning methods. The extraction of features through pre-trained Convolutional Neural Networks (CNN) and the tuning of the fully connected layers of the CNN model is the core for the development of a transfer learning pipeline. The present study investigates the diagnosis of COVID-19 through X-ray images by means of three TL models, namely Inception V3, VGG-16, and the VGG-19 for feature extraction along with heuristically fine-tuned fully connected layers. It was demonstrated through this preliminary work that both the VGG-16 and VGG-19 tuned pipelines could achieve a train and test classification accuracies of 99.8% and 94%, respectively.

Original languageEnglish
Title of host publicationAdvances in Robotics, Automation and Data Analytics - Selected Papers from iCITES 2020
EditorsJessnor Arif Mat Jizat, Ismail Mohd Khairuddin, Mohd Azraai Mohd Razman, Ahmad Fakhri Ab. Nasir, Mohamad Shaiful Abdul Karim, Abdul Aziz Jaafar, Lim Wei Hong, Anwar P. Abdul Majeed, Pengcheng Liu, Hyun Myung, Han-Lim Choi, Gian-Antonio Susto
PublisherSpringer Science and Business Media Deutschland GmbH
Pages378-384
Number of pages7
ISBN (Print)9783030709167
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event2nd International Conference on Innovative Technology, Engineering and Sciences, iCITES 2020 - Pekan, Malaysia
Duration: 22 Dec 202022 Dec 2020

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1350 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference2nd International Conference on Innovative Technology, Engineering and Sciences, iCITES 2020
Country/TerritoryMalaysia
CityPekan
Period22/12/2022/12/20

Keywords

  • COVID-19
  • Inception v3
  • Transfer learning
  • VGG-16
  • VGG-19
  • X-ray Images

Fingerprint

Dive into the research topics of 'The Diagnosis of COVID-19 Through X-Ray Images via Transfer Learning Pipeline'. Together they form a unique fingerprint.

Cite this