Title: Analysis of convolutional recurrent neural network classifier for COVID-19 symptoms over computerised tomography images

Authors: Srihari Kannan; N. Yuvaraj; Barzan Abdulazeez Idrees; P. Arulprakash; Vijayakumar Ranganathan; E. Udayakumar; P. Dhinakar

Addresses: SNS College of Technology, Coimbatore, Tamil Nadu, India ' Research and Development, ICT Academy, Chennai, Tamil Nadu, India ' College of Physical Education, University of Duhok, Kurdistan, Iraq ' Department of Computer Science and Engineering, Rathinam Technical Campus, Coimbatore, Tamil Nadu, India ' IBM India, Bangalore, India ' Department of ECE, Kalaignarkarunanidhi Institute of Technology (KIT), Coimbatore, Tamil Nadu, India ' EEE Department, JNN Institute of Engineering, Tiruvallur, Tamil Nadu, India

Abstract: In this paper, a Convolutional Recurrent Neural Network (CRNN) model is designed to classify the patients with COVID-19 infections. The CRNN model is designed to identify the Computerised Tomography (CT) images. The processing of CRNN is modelled with input image processing and feature extraction using CNN and prediction by RNN model that quickens the entire process. The simulation is carried with a set of 226 CT images by varying the training-testing accuracy on a tenfold cross-validation. The accuracy in estimating the image samples is increased with increased training data. The results of the simulation show that the proposed method has higher accuracy and reduced MSE with higher training data than other methods.

Keywords: image classification; convolutional recurrent neural network; tenfold cross validation.

DOI: 10.1504/IJCAT.2021.120453

International Journal of Computer Applications in Technology, 2021 Vol.66 No.3/4, pp.427 - 432

Received: 02 Jul 2020
Accepted: 08 Aug 2020

Published online: 21 Jan 2022 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article