Fourth wave Covid19 analyzing using mathematical seirs epidemic model & deep neural network

• Published in: Multimedia tools and applications 2024-03, Vol.83 (9), p.27507-27526
• Main Authors: Shukla, Shiv Shankar Prasad, Jain, Vikas Kumar, Yadav, Anil Kumar, Pandey, Samir Kumar
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Computer Communication Networks; Computer Science; Coronaviruses; COVID-19; Data Structures and Information Theory; Datasets; Economic development; Epidemics; Mathematical analysis; Mathematical models; Multimedia Information Systems; Neural networks; Resource allocation; Severe acute respiratory syndrome; Special Purpose and Application-Based Systems; Track 2: Medical Applications of Multimedia; Viral diseases
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-16609-x

The novel coronavirus (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 and becomes a global pandemic in a few months. Due to this, many of the country has taken harsh measures such as a complete lockdown, which has severely affected the country's economic growth. Thus, predicting the 4 th wave of Covid 19 cases in India and knowing the forecast on the Covid19 cases like confirmed cases, death cases and recovered Cases helps the country to pre-planned the measures to be taken. Mathematical modelling and trending AI algorithms can analyze data to trace the spread of diseases or predict future trends, enabling proactive measures and resource allocation. For analyzing the fourth wave Covid19 the SEIRS epidemic model analyze the ideation of epidemics flow and deep neural network model, i.e., optimized LSTM model supports the ideation with trained on the pre-processed featured datasets and predicting or forecasting the confirmed cases, recovered cases and death cases due to Covid19. The model has been trained and tested on real datasets from genuine government sites. The model produces the RSME as 967.94 and R-squared as 0.6. The model also has forecasted confirmed cases from Jan to April 2022 in India, which is very close to the real datasets. Cross-validation has been applied to ensure the performance of the optimized model.