Related Experiment Video
Updated: Nov 12, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
1.1K
Forecasting of COVID-19 using deep layer Recurrent Neural Networks (RNNs) with Gated Recurrent Units (GRUs) and Long
K E ArunKumar1, Dinesh V Kalaga2, Ch Mohan Sai Kumar3
1Department of Chemical and Biological Engineering, South Dakota School of Mines and Technology, Rapid City, SD 57701, United States.
Chaos, Solitons, and Fractals
|March 22, 2021
Summary
This study uses deep learning models like Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) cells to forecast COVID-19 cases, recoveries, and fatalities globally. The predictions aid countries in pandemic preparedness and control strategies.
Area of Science:
- * Computational epidemiology
- * Public health informatics
- * Deep learning applications in disease modeling
Background:
- * The COVID-19 pandemic, declared in March 2020, rapidly spread globally, causing millions of confirmed cases and fatalities.
- * Accurate forecasting of COVID-19 trends is crucial for effective public health interventions and resource allocation.
- * Factors such as age, preventive measures, healthcare capacity, and population density significantly influence pandemic spread.
Purpose of the Study:
- * To develop and apply advanced deep learning models for predicting country-wise COVID-19 cumulative confirmed cases, recovered cases, and fatalities.
- * To provide reliable future trend predictions to assist global pandemic management.
- * To highlight the impact of demographic and societal factors on disease transmission.
Main Methods:
- * Utilization of state-of-the-art Recurrent Neural Networks (RNNs), including Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) cells.
- * Application of deep learning architectures for time-series forecasting of epidemiological data.
- * Data sourced from the publicly available John Hopkins University COVID-19 database.
Main Results:
- * Successful development of RNN-based models (GRU and LSTM) capable of forecasting COVID-19 epidemiological data.
- * Generation of country-wise predictions for cumulative confirmed cases, recovered cases, and fatalities.
- * Identification of key factors influencing the pandemic's rapid spread.
Conclusions:
- * Deep learning models, particularly RNNs, GRUs, and LSTMs, offer a powerful tool for forecasting COVID-19 trajectories.
- * The forecasted results are valuable for enabling countries to enhance their preparedness and control measures against the pandemic.
- * Understanding the influence of various factors is essential for mitigating future public health crises.
