Comparative study of a mathematical epidemic model, statistical modeling, and deep learning for COVID-19 forecasting and management rights and content


Machine learning prediction helps public health resource management.

Mathematical modeling helps understand dynamic dependency of parameters on outbreak.

Analysis of mathematical epidemic model identify effective control strategies.


The COVID-19 pandemic has caused a global crisis with 47,209,305 confirmed cases and 1,209,505 confirmed deaths worldwide as of November 2, 2020. Forecasting confirmed cases and understanding the virus dynamics is necessary to provide valuable insights into the growth of the outbreak and facilitate policy-making regarding virus containment and utilization of medical resources. In this study, we applied a mathematical epidemic model (MEM), statistical model, and recurrent neural network (RNN) variants to forecast the cumulative confirmed cases. We proposed a reproducible framework for RNN variants that addressed the stochastic nature of RNN variants leveraging z-score outlier detection. We incorporated heterogeneity in susceptibility into the MEM considering lockdowns and the dynamic dependency of the transmission and identification rates which were estimated using Poisson likelihood fitting. While the experimental results demonstrated the superiority of RNN variants in forecasting accuracy, the MEM presented comprehensive insights into the virus spread and potential control strategies.


COVID-19 forecasting
Mathematical epidemic model
Statistical modeling
Deep learning

Mohammad Masum is currently a fourth-year Ph.D. candidate in the School of Data Science and Analytics, Kennesaw State University, under Professor Hossain Shahriar's supervision. He holds an MS in Mathematical Sciences from East Tennessee State University, USA, and an MS in Applied Mathematics from the University of Dhaka, Bangladesh. His research interest includes developing Machine Learning and Deep Learning techniques for Health Informatics and the cybersecurity domains. He has published several peer-reviewed conference papers, available here. He is also a regular contributor at the online platform Medium.

M. A. Masud is now contributing as a post-doctoral researcher in Busan National University, South Korea. He is on leave from North South University holding the position of Assistant Professor. He completed Ph.D. from Kyungpook National University, South Korea. He has several articles published in peer-reviewed reputed journals. His research aim is to develop and use mathematical and computational tools to explore mechanisms in biology and medicine which are as diverse as epidemiology, immunology, conservation biology, to name just a few. These require skills in mathematical modeling, probabilistic modeling, stability and bifurcation analysis, optimal control theory, game theory.

Muhaiminul Islam Adnan, presently working as a lecturer in Mathematics at United International University, Bangladesh. He obtained his B.S in Mathematics and M.S in Applied Mathematics degree from the University of Dhaka, Bangladesh. He published several journal articles in the field of numerical analysis, Statistics and epidemiology. His research interest includes epidemic modeling, numerical analysis, Machine learning, data analysis, and health science.

Dr. Hossain Shahriar is currently an Associate Professor of Information Technology and BSIT/BASIT program co-ordinator. He received his Ph.D. in Computing from Queen's University. His current research interests include application security, health information security, connected health, blockchain application, and computing education. His research has appeared in various journals and conferences including Computers and Security, Information Security Journal: Global Perspective, Future Generation Computer Systems, Journal of Systems and Software, ACM Computing Surveys, Blockchain in Healthcare Today, and many conferences such as IEEE BigData, IEEE COMPSAC, SIGCSE, IEEE FIE, and ACM SAC.

Sangil Kim is an Associate Professor in Mathematics at Pusan National University and Deputy Director of Finance/Fishery/Manufacture Industrial Mathematics Center on Big Data. He is an author of many publications concerning Biomathematics, Numerical Modeling with Artificial Intelligence, Optimal Control Theory, Decomposition in main effects and interaction term in multiple contingency tables and Correspondence Analysis in presence the ordinal variables by means orthogonal polynomials and/or cumulative analysis.


These two authors contributed equally.

View Abstract