Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks
Though many countries have already launched COVID-19 mass vaccination programs to control the disease outbreak quickly, numerous countries around worldwide are grappling with unprecedented surges of new COVID-19 cases due to a more contagious and deadly variant of coronavirus. As the number of new c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-05-01
|
| Series: | Results in Physics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2211379721002904 |
| _version_ | 1818601465054232576 |
|---|---|
| author | Khondoker Nazmoon Nabi Md Toki Tahmid Abdur Rafi Muhammad Ehsanul Kader Md. Asif Haider |
| author_facet | Khondoker Nazmoon Nabi Md Toki Tahmid Abdur Rafi Muhammad Ehsanul Kader Md. Asif Haider |
| author_sort | Khondoker Nazmoon Nabi |
| collection | DOAJ |
| description | Though many countries have already launched COVID-19 mass vaccination programs to control the disease outbreak quickly, numerous countries around worldwide are grappling with unprecedented surges of new COVID-19 cases due to a more contagious and deadly variant of coronavirus. As the number of new cases is skyrocketing, pandemic fatigue and public apathy towards different intervention strategies pose new challenges to government officials to combat the pandemic. Henceforth, it is indispensable for the government officials to understand the future dynamics of COVID-19 flawlessly to develop strategic preparedness and resilient response planning. In light of the above circumstances, probable future outbreak scenarios in Brazil, Russia, and the United kingdom have been sketched in this study with the help of four deep learning models: long short term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN) and multivariate convolutional neural network (MCNN). In our analysis, the CNN algorithm has outperformed other deep learning models in terms of validation accuracy and forecasting consistency. It is unearthed in our study that CNN can provide robust long-term forecasting results in time-series analysis due to its capability of essential features learning, distortion invariance, and temporal dependence learning. However, the prediction accuracy of the LSTM algorithm has been found to be poor as it tries to discover seasonality and periodic intervals from any time-series dataset, which were absent in our studied countries. Our study has highlighted the promising validation of using convolutional neural networks instead of recurrent neural networks when forecasting with very few features and less amount of historical data. |
| first_indexed | 2024-12-16T12:51:48Z |
| format | Article |
| id | doaj.art-07201c2682c94c6ebc29c0776d17046f |
| institution | Directory Open Access Journal |
| issn | 2211-3797 |
| language | English |
| last_indexed | 2024-12-16T12:51:48Z |
| publishDate | 2021-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Physics |
| spelling | doaj.art-07201c2682c94c6ebc29c0776d17046f2022-12-21T22:31:08ZengElsevierResults in Physics2211-37972021-05-0124104137Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networksKhondoker Nazmoon Nabi0Md Toki Tahmid1Abdur Rafi2Muhammad Ehsanul Kader3Md. Asif Haider4Department of Mathematics, Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh; Corresponding author.Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshDepartment of Computer Science and Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshDepartment of Computer Science and Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshDepartment of Computer Science and Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, BangladeshThough many countries have already launched COVID-19 mass vaccination programs to control the disease outbreak quickly, numerous countries around worldwide are grappling with unprecedented surges of new COVID-19 cases due to a more contagious and deadly variant of coronavirus. As the number of new cases is skyrocketing, pandemic fatigue and public apathy towards different intervention strategies pose new challenges to government officials to combat the pandemic. Henceforth, it is indispensable for the government officials to understand the future dynamics of COVID-19 flawlessly to develop strategic preparedness and resilient response planning. In light of the above circumstances, probable future outbreak scenarios in Brazil, Russia, and the United kingdom have been sketched in this study with the help of four deep learning models: long short term memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN) and multivariate convolutional neural network (MCNN). In our analysis, the CNN algorithm has outperformed other deep learning models in terms of validation accuracy and forecasting consistency. It is unearthed in our study that CNN can provide robust long-term forecasting results in time-series analysis due to its capability of essential features learning, distortion invariance, and temporal dependence learning. However, the prediction accuracy of the LSTM algorithm has been found to be poor as it tries to discover seasonality and periodic intervals from any time-series dataset, which were absent in our studied countries. Our study has highlighted the promising validation of using convolutional neural networks instead of recurrent neural networks when forecasting with very few features and less amount of historical data.http://www.sciencedirect.com/science/article/pii/S2211379721002904Time series analysisDeep learningConvolutional neural network (CNN)Long short term memory (LSTM) |
| spellingShingle | Khondoker Nazmoon Nabi Md Toki Tahmid Abdur Rafi Muhammad Ehsanul Kader Md. Asif Haider Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks Results in Physics Time series analysis Deep learning Convolutional neural network (CNN) Long short term memory (LSTM) |
| title | Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks |
| title_full | Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks |
| title_fullStr | Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks |
| title_full_unstemmed | Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks |
| title_short | Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks |
| title_sort | forecasting covid 19 cases a comparative analysis between recurrent and convolutional neural networks |
| topic | Time series analysis Deep learning Convolutional neural network (CNN) Long short term memory (LSTM) |
| url | http://www.sciencedirect.com/science/article/pii/S2211379721002904 |
| work_keys_str_mv | AT khondokernazmoonnabi forecastingcovid19casesacomparativeanalysisbetweenrecurrentandconvolutionalneuralnetworks AT mdtokitahmid forecastingcovid19casesacomparativeanalysisbetweenrecurrentandconvolutionalneuralnetworks AT abdurrafi forecastingcovid19casesacomparativeanalysisbetweenrecurrentandconvolutionalneuralnetworks AT muhammadehsanulkader forecastingcovid19casesacomparativeanalysisbetweenrecurrentandconvolutionalneuralnetworks AT mdasifhaider forecastingcovid19casesacomparativeanalysisbetweenrecurrentandconvolutionalneuralnetworks |