Comparison of ARIMA, ES, GRNN and ARIMA–GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States

Wang, Gang; Wu, Tiantian; Wei, Wudi; Jiang, Junjun; An, Sanqi; Liang, Bingyu; Li, Ye; Liang, Hao

doi:10.1017/s0950268821002375

Cited by 15 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wang Gang compared the differences between CARIMA, es, GRNN and ARIMA–GRNN in predicting the number of daily cases. This result demonstrated that the ARIMA–GRNN mixed model 8 is better. Mohan et al 11 used Supervised machine learning model (EAMA) for predicting long-term COVID-19 related parameters within India and globally.…”

Section: Introductionmentioning

confidence: 73%

An innovative ensemble model based on deep learning for predicting COVID-19 infection

Sun

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Nowadays, global public health crises are occurring more frequently, and accurate prediction of these diseases can reduce the burden on the healthcare system. Taking COVID-19 as an example, accurate prediction of infection can assist experts in effectively allocating medical resources and diagnosing diseases. Currently, scholars worldwide use single model approaches or epidemiology models more often to predict the outbreak trend of COVID-19, resulting in poor prediction accuracy. Although a few studies have employed ensemble models, there is still room for improvement in their performance. In addition, there are only a few models that use the laboratory results of patients to predict COVID-19 infection. To address these issues, research efforts should focus on improving disease prediction performance and expanding the use of medical disease prediction models. In this paper, we propose an innovative deep learning model Whale Optimization Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM) and Artificial Neural Network (ANN) called WOCLSA which incorporates three models ANN, CNN and LSTM. The WOCLSA model utilizes the Whale Optimization Algorithm to optimize the neuron number, dropout and batch size parameters in the integrated model of ANN, CNN and LSTM, thereby finding the global optimal solution parameters. WOCLSA employs 18 patient indicators as predictors, and compares its results with three other ensemble deep learning models. All models were validated with train-test split approaches. We evaluate and compare our proposed model and other models using accuracy, F1 score, recall, AUC and precision metrics. Through many studies and tests, our results show that our prediction models can identify patients with COVID-19 infection at the AUC of 91%, 91%, and 93% respectively. Other prediction results achieve a respectable accuracy of 92.82%, 92.79%, and 91.66% respectively, f1-score of 93.41%, 92.79%, and 92.33% respectively, precision of 93.41%, 92.79%, and 92.33% respectively, recall of 93.41%, 92.79%, and 92.33% respectively. All of these exceed 91%, surpassing those of comparable models. The execution time of WOCLSA is also an advantage. Therefore, the WOCLSA ensemble model can be used to assist in verifying laboratory research results and predict and to judge various diseases in public health events.

show abstract

Section: Introductionmentioning

confidence: 73%

An innovative ensemble model based on deep learning for predicting COVID-19 infection

Sun

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The exponential smoothing model is a time series forecasting model that assigns different weights based on different observations [32]. JMP 14 Pro software was used to explore the optimal exponential smoothing model, as previously described [33,34]. First, the preliminary values are determined.…”

Section: Construction Of the Exponential Smoothing Modelmentioning

confidence: 99%

Time series prediction for the epidemic trends of monkeypox using the ARIMA, exponential smoothing, GM (1, 1) and LSTM deep learning methods

Wei

Wang

Tao

et al. 2023

Journal of General Virology

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Some recent studies have implemented autoregressive integrated moving average (ARIMA) and exponential smoothing (ES) for forecasting the number of COVID-19 cases in India ( Wang et al, 2021 , Katoch & Sidhu, 2021 , Mangla et al, 2021 , Arora et al, 2021 ) and in USA ( Wang et al, 2021 ). Though most of these studies have considered ARIMA and ES models with the number of COVID-19 cases as functions of previously reported numbers, importance of auxiliary indicators such as government adopted stringency measures and meteorological features have also been found as dominant predictors of the growth of COVID-19 epidemic ( Bertozzi et al, 2020 , Khan, Abedin, Khan, et al, 2022 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Deep neural network for monitoring the growth of COVID-19 epidemic using meteorological covariates

Khan

Chowdhury

Imon

2023

Intelligent Systems with Applications

View full text Add to dashboard Cite

Comparison of ARIMA, ES, GRNN and ARIMA–GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States

Cited by 15 publications

References 37 publications

An innovative ensemble model based on deep learning for predicting COVID-19 infection

An innovative ensemble model based on deep learning for predicting COVID-19 infection

Time series prediction for the epidemic trends of monkeypox using the ARIMA, exponential smoothing, GM (1, 1) and LSTM deep learning methods

Deep neural network for monitoring the growth of COVID-19 epidemic using meteorological covariates

Contact Info

Product

Resources

About