A bibliometric analysis of machine learning techniques in photovoltaic cells and solar energy (2014–2022)

Zaidi, Abdelhamid

doi:10.1016/j.egyr.2024.02.036

Cited by 5 publications

(1 citation statement)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study [8] critically analyzes the use of machine learning in photovoltaic and solar energy research using the PRIZMA 1 approach to the Scopus database, including publication trends and bibliometric analysis. PRIZMA approach plays an essential role in writing systematic reviews, but really this article only uses the capabilities of VOSviewer software and Scopus analytics.…”

mentioning

confidence: 99%

IEEE Terms Analysis of 2019–2024 IEEE Xplore Data on the Topic of Energy Systems

Chigarev

2024

Preprint

View full text Add to dashboard Cite

Relevance of the subject. Keyword selection is critical to finding relevant literature and requires justification for querying abstract databases and other sources to ensure accuracy and completeness. The topic of Energy Systems is of great importance due to the introduction of renewable energy sources, modern control methods, and complex energy systems during the energy transition. The aim of this study. The goal of this paper was to identify keywords that would be useful to subject matter experts when collecting literature on a particular topic, based on entries in the IEEE Terms field. Data. Bibliometric data were exported from the IEEE Xplore platform in the following order: for 2019-2023, 2000 records sorted by relevance, for 2024, 1680 records current as of April 11, 2024. Analytical methods applied and software used. VOSviewer, Scimago Graphica implementing the Clauset-Newman-Moore algorithm and agglomerative hierarchical clustering method implemented in Multidendrograms. Results. The main issues of the Energy Systems topic are presented in tabular and graphical formats. The fpgrowth utility offers flexible data preparation options, which makes it worthwhile to conduct a separate study to analyze the score of co-occurrence terms given by its algorithm.

show abstract

mentioning

confidence: 99%