Home // HEALTHINFO 2021, The Sixth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article

Early-Stage Epidemic Forecasting

Authors:
Olayemi Olabisi
Andrea Corradini

Keywords: Forecasting; Grey Forecasting model; Early Stage Epidemic; Coronavirus;

Abstract:
Statistical methods and machine learning methods are currently the most popular ways for forecasting. Some of these include autoregressive models, cumulative sum charts, growth models, SVM for regression, polynomial neural networks (PNNs) as well as several others. The inherent limitation associated with these models is that they require large sample size for accurate forecasts. In this paper, we investigate the ability to forecast a disease outbreak when data is limited by employing variations of the Grey Model (GM) forecasting. Lack or limitation of data is rather common in the early stages of a disease outbreak. We present the results of a simulation that shows the model’s ability to leverage the exponential growth associated with the rate of spread of diseases in the early stages. A comparative analysis of our quantitative results using the coronavirus dataset of a few countries indicate that both the Gompertz model and the PNN model perform better than the traditional Grey Model GM(1,1) in fitting and forecasting. At the same time, qualitative evidence indicate that the Grey Model is suitable for early-stage epidemics provided methods of enhancement are employed i.e. improved background value calculations and better methods for accumulative generating operation as seen in the Fractional Grey Model FGM(1,1) algorithm.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2021

Publication date: October 3, 2021

Published in: conference

ISSN: 2519-8491

ISBN: 978-1-61208-916-4

Location: Barcelona, Spain

Dates: from October 3, 2021 to October 7, 2021