Image Based Classification of COVID-19 Infection using an Ensemble of Machine Learning Classifiers and Deep Learning Techniques

Lingampally Shalini, Sunilkumar Manvi, Bryan Gardiner, Naveen Chandra Gowda

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

Abstract

From the inception of the Coronavirus illness (Covid-19), it has had a major impact on multiple areas in society, not least including the healthcare system and the downfall of the global economy. Researchers, medical professionals, and specialists continue to work towards new techniques to identify Covid-19 more quickly, such as developing mechanisms that can detect Covid-19 automatically. In this paper, an automated detection mechanism for identifying Covid-19 patients using a patient’s chest X-ray images is proposed. The developed system uses both a CNN (convolutional neural network) and an ensemble of a set of classifiers. The CNN is used for feature extraction in the training and input image data whereas a variety of other selected classifiers are used for effective prediction. Some of the binary ML (machine learning) classifiers are used for the identification of Covid-19 based on the retrieved characteristics. Later these results are grouped to create a pool of ensemble of classifiers to assure superior results considering various datasets of different-sized image data with varying resolutions. The performance analysis is discussed identifying improved performance over previous schemes using deep learning, with 99.17% accuracy, 99.19% precision, 99.17% recall, and 99.43% F1 score. The system’s high value in the automated detection of Covid-19 is maintained due to its quick identification and low false-negative rate.
Original languageEnglish
Title of host publicationInternational Conference on Data Science, Agents and Artificial Intelligence
ISBN (Electronic)979-8-3503-3383-1
Publication statusPublished online - 10 Dec 2022
EventInternational Conference on Data Science, Agents and Artificial Intelligence - Chennai, India
Duration: 10 Dec 202212 Dec 2022

Conference

ConferenceInternational Conference on Data Science, Agents and Artificial Intelligence
Period10/12/2212/12/22

Keywords

  • Healthcare system
  • Covid-19
  • Convolutional neural network
  • Machine learning
  • Ensemble of classifiers

Fingerprint

Dive into the research topics of 'Image Based Classification of COVID-19 Infection using an Ensemble of Machine Learning Classifiers and Deep Learning Techniques'. Together they form a unique fingerprint.

Cite this