THE BIBLIOMETRIC ANALYSIS OF MACHINE LEARNING USE IN THE DETECTION OF PHYCOCYANIN PIGMENT

Abstract

In freshwater systems, cyanobacteria harmful algal blooms (HABs) have been a major source of worry for environmental and public health agencies around the world. Machine learning can be used to detect Phycocyanin pigment which is an indicator to identify HABs in the water area. However, the use of machine learning is still low compared to remote sensing method. This research was conducted bibliometric analysis by using VOS Viewer software to show the gap and evolution of this research topic through published works. This research used the data of the publications from Scopus database which using machine learning to detect Phycocyanin pigment instead of remote sensing. It has shown that the machine learning method in Phycocyanin detection became more common in scientific community. The total publications that mentioned machine learning in Phycocyanin pigment detection in HABs has been increased gradually started from 2012 and the momentum still going strong. For the conclusion, machine learning has been used more frequently compared to 20 years ago in detection of Phycocyanin pigment in HABs and more researchers became more interested to make research in this specific field.