A Computational Intelligence Approach to Detect Future Trends of COVID-19 in France by Analyzing Chinese Data | ||
| Health Education and Health Promotion | ||
| Article 1, Volume 8, Issue 3, 2020, Pages 107-113 PDF (946.61 K) | ||
| Document Type: Original Research | ||
| Authors | ||
| Z. Sazvar* ; M. Tanhaeean; S.S. Aria; A. Akbari; S.F. Ghaderi; S.H. Iranmanesh | ||
| Department of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran | ||
| Abstract | ||
| Aims: Due to the terrible effects of 2019 novel coronavirus (COVID-19) on health systems and the global economy, the necessity to study future trends of the virus outbreaks around the world is seriously felt. Since geographical mobility is a risk factor of the disease, it has spread to most of the countries recently. It, therefore, necessitates to design a decision support model to 1) identify the spread pattern of coronavirus and, 2) provide reliable information for the detection of future trends of the virus outbreaks. Materials & Methods: The present study adopts a computational intelligence approach to detect the possible trends in the spread of 2019-nCoV in China for a one-month period. Then, a validated model for detecting future trends in the spread of the virus in France is proposed. It uses ANN (Artificial Neural Network) and a combination of ANN and GA (Genetic Algorithm), PSO (Particle Swarm Optimization), and ICA (Imperialist Competitive Algorithm) as predictive models. Findings: The models work on the basis of data released from the past and the present days from WHO (World Health Organization). By comparing four proposed models, ANN and GA-ANN achieve a high degree of accuracy in terms of performance indicators. Conclusion: The models proposed in the present study can be used as decision support tools for managing and controlling of 2019-nCoV outbreaks. | ||
| Keywords | ||
| Coronavirus; Pandemic; artificial neural network; genetic algorithm | ||
| References | ||
|
| ||
|
Statistics Article View: 28 PDF Download: 27 |
||
| Number of Journals | 45 |
| Number of Issues | 2,171 |
| Number of Articles | 24,674 |
| Article View | 24,479,401 |
| PDF Download | 17,565,682 |