Classification of Covid-19 variants using boosting algorithm

Muhammad, Izzudin, Mukhlash, Imam, Jamhuri, Mohammad, Iqbal, Mohammad and Irawan, Mohammad Isa (2022) Classification of Covid-19 variants using boosting algorithm. Presented at 2022 9th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Jakarta, Indonesia, 6-7 Oct 2022.

Text 15016.pdf - Published Version Restricted to Repository staff only Download (639kB)

Abstract

COVID-19 is a disease caused by a virus from the coronavirus group, namely severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The Sars-CoV-2 virus has 5 variants that are included in the variant of concern (VOC) namely Alpha, Beta, Delta, Gamma, and Omicron. The COVID-19 virus has infected more than 400 million people worldwide. This information causes a significant increase in data with the result that computations are needed to obtain knowledge (pattern) from the data. Machine learning is a tool that can facilitate the analysis of big data, one of which is classification. In this paper, we implement two boosting algorithms: eXtreme Gradient Boosting (XGB) and Light Gradient Boosting Machine (LGBM), to classify the Deoxyribonucleic acid (DNA) sequence data from the COVID-19 virus variants. Additionally, we utilized one-hot encoded method to encode data. The experiment results showed that XGB has better accuracy than LGBM, but LGBM has faster computation time than XGB. The highest accuracy is 0.992.

Item Type:	Conference (Paper)
Keywords:	Classification of Covid-19 variants using boosting algorithm
Subjects:	01 MATHEMATICAL SCIENCES > 0102 Applied Mathematics > 010202 Biological Mathematics
Depositing User:	Mr Jamhuri Mohammad
Date Deposited:	15 Jun 2023 08:48

Downloads

Origin of downloads

Actions (login required)

View Item