Intelligent Forecasting Model of COVID-19 Novel Coronavirus Outbreak Empowered with Deep Extreme Learning Machine
- Authors
- Khan, Muhammad Adnan; Abbas, Sagheer; Khan, Khalid Masood; Al Ghamdi, Muhammad A.; Rehman, Abdur
- Issue Date
- Sep-2020
- Publisher
- TECH SCIENCE PRESS
- Keywords
- Coronavirus; nCoV; DELM; Mis rate; SERS-CoV; WHO; COVID-19
- Citation
- CMC-COMPUTERS MATERIALS & CONTINUA, v.64, no.3, pp.1329 - 1342
- Journal Title
- CMC-COMPUTERS MATERIALS & CONTINUA
- Volume
- 64
- Number
- 3
- Start Page
- 1329
- End Page
- 1342
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81141
- DOI
- 10.32604/cmc.2020.011155
- ISSN
- 1546-2218
- Abstract
- An epidemic is a quick and widespread disease that threatens many lives and damages the economy. The epidemic lifetime should be accurate so that timely and remedial steps are determined. These include the closing of borders schools, suspension of community and commuting services. The forecast of an outbreak effectively is a very necessary but difficult task. A predictive model that provides the best possible forecast is a great challenge for machine learning with only a few samples of training available. This work proposes and examines a prediction model based on a deep extreme learning machine (DELM). This methodology is used to carry out an experiment based on the recent Wuhan coronavirus outbreak. An optimized prediction model that has been developed, namely DELM, is demonstrated to be able to make a prediction that is fairly best. The results show that the new methodology is useful in developing an appropriate forecast when the samples are far from abundant during the critical period of the disease. During the investigation, it is shown that the proposed approach has the highest accuracy rate of 97.59% with 70% of training, 30% of test and validation. Simulation results validate the prediction effectiveness of the proposed scheme.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/81141)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.