Implementation of K-Means and DBSCAN algorithms: A Bibliometric Review
Fahmi Reza Ferdiansyah, Rikky Wisnu Nugraha, Rudy Sofian, Heri Purwanto, Didin Saepudin, Edi Andriansyah · Advances in engineering research/Advances in Engineering Research · 2024
K-Means and DBSCAN algorithms belong to Supervised Learning, they are one of the popular clustering algorithms used in Machine Learning/Data mining that do not need to be labeled.Both algorithms are always compared with other algorithms to find superior clusters.Bibliometric was used as a research methodology with stages using the Prisma framework, namely identification, screening, eligibility, included.The focus of this research is to find scientific articles related to the K-Means and DBSCAN algorithms.Units of analysis collected through Scopus.All articles were downloaded from 2014 to 2024, resulting in 170 scientific articles.The inspection was conducted in several stages, and the overall result was 104 articles.After careful consideration, the total number of articles considered eligible was 65.There are at least four major themes that discuss the use of K-Means and DBSCAN algorithms, namely the infrastructure, transportation, health, and education sectors.Of the four fields, health and transportation are most suitable for the implementation of the K-Means and DBSCAN algorithms.In addition, researchers use K-Means and/or DBSCAN algorithms to compare with other algorithms, the goal is to find the best clustering algorithm