Neuromorphic Solutions

Authors

Swapna Halder, Department of Computer Science and Engineering, St. Thomas College of Engineering & Technology, India; Centre for IOT and AI Integration with Education -Industry- Agriculture, Kazi Nazrul University, India
Saswati Naskar, Department of Computer Science and Engineering, Heritage Institute of Technology, India
Saibal Majumder, Department of Computer Science and Engineering (Data Science), Dr. B. C. Roy Engineering College, Durgapur, India
Arindam Biswas, Department of Computer Science and Engineering (Data Science), Dr. B. C. Roy Engineering College, Durgapur, India; School of Mines and Metallurgy, Kazi Nazrul University, India

Abstract

The COVID-19 epidemic left the entire world in terrible shape and put people's everyday lives in grave danger. Predicting the death rate from this worldwide pandemic is an essential component of the healthcare system. As a result, monitoring and forecasting the death rate in order to implement preventive measures inside the healthcare system becomes extremely ineffective. Predicting the death rate of COVID-19 cases is extremely difficult due to the non-linearity of the time series data. Numerous forecasting models are employed to estimate the death rate. In this study, we examined the outcomes of two standard statistical models for death forecasting: the Autoregressive Integrated Moving Average (ARIMA) model and its extended form, the Seasonal Autoregressive Integrated Moving Average (SARIMA) model. In order to forecast the death rate for the next three weeks, we have examined COVID-19 data from four Asian nations: Israel, Bangladesh, Japan, and India.

Recommended Citation

Halder, Swapna; Naskar, Saswati; Majumder, Saibal; and Biswas, Arindam (2024) "Neuromorphic Solutions," Uddalak: Vol. 1: Iss. 1, Article 2.
Available at: https://uddalak.researchcommons.org/journal/vol1/iss1/2