Article
Open Access
Expand
EEMD-LSTM modelling of daily confirmed COVID-19 cases in Malaysia
1 Department of Mathematical Sciences, Faculty of Science, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Malaysia
2 School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Malaysia
  • Volume
  • Citation
    Shabri A, Samsudin R, Yunos ZM, Ismail AF, Ali A. EEMD-LSTM modelling of daily confirmed COVID-19 cases in Malaysia. Proc. Comput. Sci. 2023(1):0005, https://doi.org/10.55092/pcs2023020005. 
  • DOI
    10.55092/pcs2023020005
  • Copyright
    Copyright2023 by the authors. Published by ELSP.
Abstract

The World Health Organization proclaimed COVID-19 to be in a pandemic state on March 11, 2020, when there were over 118000 confirmed cases worldwide across more than 110 countries. Accurate modeling and forecasting of the spread of confirmed and recovered COVID-19 cases are crucial for assisting decision-makers in fighting the epidemic. Such situations commonly exhibit non-linear patterns, motivating us to develop a system that can keep track of such alterations. The project’s ultimate objective is to provide a method for

anticipating new COVID 19 scenarios utilizing a hybrid EEMD-LSTM model. In this scenario, a prediction is produced regarding the total amount of daily COVID-19 cases that were officially confirmed in Malaysia between March 13, 2020, and January 4, 2021. The

Global Change Data Lab at Oxford University provided the dataset.

Keywords

forecasting COVID-19; Long-Short Term Memory (LSTM) network; Ensemble Empirical Mode Decomposition (EEMD)

Preview