Abstract

The ongoing coronavirus pandemic has caused the spread of information related to this virus to continue growing. COVID-19 mutates and gives rise to new variants. A taxonomy graph of these viruses can help us see the connections between viruses. Thus, we implemented a taxonomic graph of COVID-19 to determine the cause of the virus and its parent of origin. The virus dataset was retrieved from Wikidata. We exploited several graph algorithms to create the taxonomy graph: link prediction, triangle/grouping coefficients, and community detection algorithms. The results of the graph algorithms become the features of the Random Forest classifier. Random Forest predicts the relationship between two viruses. The research results showed average scores of accuracy, precision, and recall of 90%, 90%, and 91 %, respectively.

Original languageEnglish
Title of host publicationICEEIE 2023 - International Conference on Electrical, Electronics and Information Engineering
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350340501
DOIs
Publication statusPublished - 2023
Event8th International Conference on Electrical, Electronics and Information Engineering, ICEEIE 2023 - Malang City, Indonesia
Duration: 28 Sept 202329 Sept 2023

Publication series

NameICEEIE 2023 - International Conference on Electrical, Electronics and Information Engineering

Conference

Conference8th International Conference on Electrical, Electronics and Information Engineering, ICEEIE 2023
Country/TerritoryIndonesia
CityMalang City
Period28/09/2329/09/23

Keywords

  • Covid-19
  • Graph Algorithm
  • Random Forest
  • Taxonomy Graph

Fingerprint

Dive into the research topics of 'COVID-19 Viruses Link Prediction Using Graph Algorithms And Random Forest'. Together they form a unique fingerprint.

Cite this