Time series prediction for the epidemic trends of monkeypox using the ARIMA, exponential smoothing, GM (1, 1) and LSTM deep learning methods. (6th April 2023)
- Record Type:
- Journal Article
- Title:
- Time series prediction for the epidemic trends of monkeypox using the ARIMA, exponential smoothing, GM (1, 1) and LSTM deep learning methods. (6th April 2023)
- Main Title:
- Time series prediction for the epidemic trends of monkeypox using the ARIMA, exponential smoothing, GM (1, 1) and LSTM deep learning methods
- Authors:
- Wei, Wudi
Wang, Gang
Tao, Xing
Luo, Qiang
Chen, Lixiang
Bao, Xiuli
Liu, Yuxuan
Jiang, Junjun
Liang, Hao
Ye, Li - Abstract:
- Abstract : Monkeypox is a critical public health emergency with international implications. Few confirmed monkeypox cases had previously been reported outside endemic countries. However, since May 2022, the number of monkeypox infections has increased exponentially in non-endemic countries, especially in North America and Europe. The objective of this study was to develop optimal models for predicting daily cumulative confirmed monkeypox cases to help improve public health strategies. Autoregressive integrated moving average (ARIMA), exponential smoothing, long short-term memory (LSTM) and GM (1, 1) models were employed to fit the cumulative cases in the world, the USA, Spain, Germany, the UK and France. Performance was evaluated by minimum mean absolute percentage error (MAPE), among other metrics. The ARIMA (2, 2, 1) model performed best on the global monkeypox dataset, with a MAPE value of 0.040, while ARIMA (2, 2, 3) performed the best on the USA and French datasets, with MAPE values of 0.164 and 0.043, respectively. The exponential smoothing model showed superior performance on the Spanish, German and UK datasets, with MAPE values of 0.043, 0.015 and 0.021, respectively. In conclusion, an appropriate model should be selected according to the local epidemic characteristics, which is crucial for monitoring the monkeypox epidemic. Monkeypox epidemics remain severe, especially in North America and Europe, e.g. in the USA and Spain. The development of a comprehensive,Abstract : Monkeypox is a critical public health emergency with international implications. Few confirmed monkeypox cases had previously been reported outside endemic countries. However, since May 2022, the number of monkeypox infections has increased exponentially in non-endemic countries, especially in North America and Europe. The objective of this study was to develop optimal models for predicting daily cumulative confirmed monkeypox cases to help improve public health strategies. Autoregressive integrated moving average (ARIMA), exponential smoothing, long short-term memory (LSTM) and GM (1, 1) models were employed to fit the cumulative cases in the world, the USA, Spain, Germany, the UK and France. Performance was evaluated by minimum mean absolute percentage error (MAPE), among other metrics. The ARIMA (2, 2, 1) model performed best on the global monkeypox dataset, with a MAPE value of 0.040, while ARIMA (2, 2, 3) performed the best on the USA and French datasets, with MAPE values of 0.164 and 0.043, respectively. The exponential smoothing model showed superior performance on the Spanish, German and UK datasets, with MAPE values of 0.043, 0.015 and 0.021, respectively. In conclusion, an appropriate model should be selected according to the local epidemic characteristics, which is crucial for monitoring the monkeypox epidemic. Monkeypox epidemics remain severe, especially in North America and Europe, e.g. in the USA and Spain. The development of a comprehensive, evidence-based scientific programme at all levels is critical to controlling the spread of monkeypox infection. … (more)
- Is Part Of:
- Journal of general virology. Volume 104:Number 4(2023)
- Journal:
- Journal of general virology
- Issue:
- Volume 104:Number 4(2023)
- Issue Display:
- Volume 104, Issue 4 (2023)
- Year:
- 2023
- Volume:
- 104
- Issue:
- 4
- Issue Sort Value:
- 2023-0104-0004-0000
- Page Start:
- Page End:
- Publication Date:
- 2023-04-06
- Subjects:
- monkeypox -- ARIMA -- LSTM -- exponential smoothing -- GM (1, 1)
Virology -- Periodicals
Viruses
Microbiology
Virology
Virologie -- Périodiques
Microbiologie -- Périodiques
Virology
Virologie
Virologie
Electronic journals
Periodical
Periodicals
579.2 - Journal URLs:
- https://www.microbiologyresearch.org/content/journal/jgv ↗
- DOI:
- 10.1099/jgv.0.001839 ↗
- Languages:
- English
- ISSNs:
- 0022-1317
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library HMNTS - ELD Digital store
- Ingest File:
- 26776.xml