Title: Pandemic outbreak prediction with an enhanced parameter optimisation algorithm using machine learning models

Authors: Soni Singh; K.R. Ramkumar; Ashima Kukkar

Addresses: Department of Computer Science and Engineering, Chitkara Institute of Engineering and Technology, Chitkara University, Punjab, India ' Department of Computer Science and Engineering, Chitkara Institute of Engineering and Technology, Chitkara University, Punjab, India ' Department of Computer Science and Engineering, Chitkara Institute of Engineering and Technology, Chitkara University, Punjab, India

Abstract: The outbreak of several pandemics impacts people in different ways. The modelling of disease is essential to measuring the effect of these pandemics. Several statistical and machine learning (ML) models are developed for making predictions but fail to provide better accuracy. To overcome this, an enhanced prediction model is proposed to increase model accuracy. The parameters of the existing ML models are optimised using the ACO algorithm. Various ML techniques are used to predict the outbreak, such as MLP, SVM, and LR. The performance of the model is tested on COVID-19 and Ebola datasets using accuracy and RMSE score. The result shows that the proposed model yields high accuracy concerning the RMSE score for daily prediction. The MLP-ACO shows better results by comparing with other ML models. The prediction results suggest that the ACO algorithm increases the efficiency of existing ML techniques to predict the outbreak in different countries.

Keywords: machine learning techniques; pandemic outbreak; parameter optimisation; ant colony optimisation; ACO; prediction.

DOI: 10.1504/IJESDF.2023.131960

International Journal of Electronic Security and Digital Forensics, 2023 Vol.15 No.4, pp.359 - 386

Received: 20 Aug 2022
Accepted: 05 Oct 2022
Published online: 05 Jul 2023 *

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