Global COVID-19 development trend forecast based on machine learning

Cheng, Yi; Bai, Yanping; Xu, Tao; Hu, Hongping

doi:10.1109/bdicn55575.2022.00032

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model performance comparison is made among models of APC, SES, DES, and Holt's linear method in [18]. It shows that the Holt's linear method performs better than others.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…The 30-day forecast from the best model, Holt's method, reveal that the pandemic trend would substantially increase. Cheng et al [18] compare and evaluate between two prediction models, ARIMA and SVM, to predict the COVID-19 trend. The prediction performance of ARIMA model is worse as compared to the SVM model in the experiments, which show that ARIMA model is more suitable for regular and stable sample data.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Predictive Information Workflow of Forecasting Number of COVID-19 Confirmed Cases

Gam

Cao

Seow

2022

2022 IEEE 21st International Conference on Ubiquitous Computing and Communications (IUCC/CIT/DSCI/SmartCNS)

View full text Add to dashboard Cite

There are questions about how to accurately prepare with the correct number of resources for distribution in order to properly manage the healthcare resources (e.g., healthcare workers, Masks, ART-19 TestKit) required to tighten the grip on the COVID-19 pandemic. Mathematical and computational forecasting models have well served the means to address these questions, as well as the resulting advisories to governments. A workflow is proposed in this research, aiming to develop a forecasting simulation that makes accurate predictions on COVID-19 confirmed cases in Singapore. According to the analysis of the prior works, six candidate forecasting models are evaluated and compared in the workflow: polynomial regression, linear regression, SVM, Prophet, Holt's linear, and LSTM models. The study's goal is to determine the most suitable forecasting model for COVID-19 cases in Singapore. Two algorithms are also proposed to better compute the performance of two models: the order algorithm to determine optimal degree order for the polynomial regression model , and the optimizing algorithm for the Holt's linear model to calculate the optimal smoothing parameters. Observed from the experiment results with the COVID-19 dataset, the Prophet method model achieves the best performance with the lowest Root Mean Square Error (RMSE) score of 1557.744836 and Mean Absolute Percentage Error (MAPE) score of 0.468827, compared to the other five models. The Prophet method model achieving average accuracy range of 90% when forecasting the number of confirmed COVID-19 cases in Singapore for the next 87 days ahead. is chosen and recommended to be used as a system model for forecast the COVID-19 confirm cases in Singapore. The developed workflow will greatly assist the authorities in taking timely actions and making decisions to contain the COVID-19 pandemic.

show abstract

“…The model performance comparison is made among models of APC, SES, DES, and Holt's linear method in [18]. It shows that the Holt's linear method performs better than others.…”

Section: Proposed Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%