A deep learning algorithm for modeling and forecasting of COVID-19 in five worst affected states of India

Farooq, Junaid; Bazaz, Mohammad Abid

doi:10.1016/j.aej.2020.09.037

Cited by 45 publications

(27 citation statements)

References 16 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning models have achieved outperformance in various classification, regression, and time-series analyses ( Khan et al, 2020 ). Farooq and Bazaz (2021) developed a deep neural network model for modeling the COVID-19 spread in India’s five worst-affected states. The model parameters were updated using an adaptive online incremental learning technique.…”

Section: Related Workmentioning

confidence: 99%

“…The observed cases are based on the testing results, so the number of actual infections is higher than that of reported infections. It is pertinent to mention that under-testing leads to errors in the forecasting model ( Farooq and Bazaz, 2021 ). As a result, predicting the number of infected persons is critical ( Saba and Elsheikh, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning model for forecasting COVID-19 outbreak in Egypt

Marzouk

Elshaboury

AbdelLatif

et al. 2021

Process Safety and Environmental Protection

View full text Add to dashboard Cite

The World Health Organization has declared COVID-19 as a global pandemic in early 2020. A comprehensive understanding of the epidemiological characteristics of this virus is crucial to limit its spreading. Therefore, this research applies artificial intelligence-based models to predict the prevalence of the COVID-19 outbreak in Egypt. These models are long short-term memory network (LSTM), convolutional neural network, and multilayer perceptron neural network. They are trained and validated using the dataset records from 14 February 2020 to 15 August 2020. The results of the models are evaluated using the determination coefficient and root mean square error. The LSTM model exhibits the best performance in forecasting the cumulative infections for one week and one month ahead. Finally, the LSTM model with the optimal parameter values is applied to forecast the spread of this epidemic for one month ahead using the data from 14 February 2020 to 30 June 2021. The total size of infections, recoveries, and deaths is estimated to be 285,939, 234,747, and 17,251 cases on 31 July 2021. This study could assist the decision-makers in developing and monitoring policies to confront this disease.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning model for forecasting COVID-19 outbreak in Egypt

Marzouk

Elshaboury

AbdelLatif

et al. 2021

Process Safety and Environmental Protection

View full text Add to dashboard Cite

show abstract

“…Farooq and Bazaz ( 22 ) used an artificial neural network (ANN) to forecast the COVID-19 based on an online incremental learning technique using an adaptive and non-intrusive analytical model. The COVID-19 data was updated every day, so online incremental learning was the best option for forecasting since there is no need to retrain or rebuild the model from scratch.…”

Section: Related Workmentioning

confidence: 99%

Performance Evaluation of Regression Models for the Prediction of the COVID-19 Reproduction Rate

Kaliappan

Srinivasan

Qaisar

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

This paper aims to evaluate the performance of multiple non-linear regression techniques, such as support-vector regression (SVR), k-nearest neighbor (KNN), Random Forest Regressor, Gradient Boosting, and XGBOOST for COVID-19 reproduction rate prediction and to study the impact of feature selection algorithms and hyperparameter tuning on prediction. Sixteen features (for example, Total_cases_per_million and Total_deaths_per_million) related to significant factors, such as testing, death, positivity rate, active cases, stringency index, and population density are considered for the COVID-19 reproduction rate prediction. These 16 features are ranked using Random Forest, Gradient Boosting, and XGBOOST feature selection algorithms. Seven features are selected from the 16 features according to the ranks assigned by most of the above mentioned feature-selection algorithms. Predictions by historical statistical models are based solely on the predicted feature and the assumption that future instances resemble past occurrences. However, techniques, such as Random Forest, XGBOOST, Gradient Boosting, KNN, and SVR considered the influence of other significant features for predicting the result. The performance of reproduction rate prediction is measured by mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R-Squared, relative absolute error (RAE), and root relative squared error (RRSE) metrics. The performances of algorithms with and without feature selection are similar, but a remarkable difference is seen with hyperparameter tuning. The results suggest that the reproduction rate is highly dependent on many features, and the prediction should not be based solely upon past values. In the case without hyperparameter tuning, the minimum value of RAE is 0.117315935 with feature selection and 0.0968989 without feature selection, respectively. The KNN attains a low MAE value of 0.0008 and performs well without feature selection and with hyperparameter tuning. The results show that predictions performed using all features and hyperparameter tuning is more accurate than predictions performed using selected features.

show abstract

“…[12] introduces a Composite Monte Carlo method to predict daily new confirmed COVID-19 cases, which is enhanced by deep learning and fuzzy rule induction. [13] exploits epidemic propagation model to predict daily cumulative confirmed cases of five worst affected states in India.…”

Section: Covid-19 Predictionmentioning

confidence: 99%

COVID-19 cases prediction in multiple areas via shapelet learning

Wang

Cai

2021

Appl Intell

View full text Add to dashboard Cite

Predicting the number of COVID-19 cases in a geographical area is important for the management of health resources and decision making. Several methods have been proposed for COVID-19 case predictions but they have important limitations in terms of model interpretability, related to COVID-19's incubation period and major trends of disease transmission. To be able to explain prediction results in terms of incubation period and transmission trends, this paper presents the Multivariate Shapelet Learning (MSL) model to learn shapelets from historical observations in multiple areas. An experimental evaluation was done to compare the prediction performance of eleven algorithms, using the data collected from 50 US provinces/states. Results show that the proposed method is effective and efficient. The learned shapelets explain increasing and decreasing trends of new confirmed cases, and reveal that the COVID-19 incubation period in the USA is around 28 days.

show abstract

A deep learning algorithm for modeling and forecasting of COVID-19 in five worst affected states of India

Cited by 45 publications

References 16 publications

Deep learning model for forecasting COVID-19 outbreak in Egypt

Deep learning model for forecasting COVID-19 outbreak in Egypt

Performance Evaluation of Regression Models for the Prediction of the COVID-19 Reproduction Rate

COVID-19 cases prediction in multiple areas via shapelet learning

Contact Info

Product

Resources

About