Turkish Journal of Computer and Mathematics Education
Journal license

Journal

Turkish Journal of Computer and Mathematics Education


Volume
& Issue

Volume 10, Issue 3


Published
on


Pages

955-961


DOI

Article

The Evolutionary Machine Learning Modelto Detect the COVID 19 Infections due in Medical Images.


Authors

Susheel George Joseph Affiliation:
Associate Professor, Department of Computer Applications, Kristu Jyoti College of Management and Technology, Changanassery, Kerala, India
and Jaibir Singh Affiliation:
Associate Professor, Department of Computer science and Engineering, O.P.J.S. University, Churu, Rajasthan


Abstract

In processing Computer Tomography (CT) medical images, some of the image processing works use evolutionary algorithms. Evolutionary algorithms are the part of evolutionary computing and they are considered as metaheuristic optimization algorithm. Meta-heuristic is a heuristic designed to find, generate, or select a heuristic (partial search algorithm) or higher-level procedure which provides an adequate solution to an optimization problem, especially with incomplete or imperfect information or limited computation capacity. Metaheuristics can be used to a variety of problems especially matching or searching that may make relatively few assumptions about the optimization problem being solved. CT scan medical images can be examined to check whether the patient is infected due to COVID 19. Here three different evolutionary algorithms are used in various steps for the medical image processing. Initially the Cuckoo search algorithm is used to monitor a Kapur/Otsu image thresholding and then a segmentation algorithm to extract the pneumonia infection. An improved marine predator algorithm is used for X-Ray image segmentation.


Keywords

Machine Learning, COVID 19, Cuckoo Search, Segmentation Algorithm, Marine predator algorithm, image processing, evolutionary algorithms


Citation

Joseph, S. G. & Singh, J. (2019). The evolutionary machine learning modelto detect the COVID 19 infections due in medical images. Turkish Journal of Computer and Mathematics Education, 10(3), 955–961.

Published by: Engineering Journals

Engineering Journals Logo