Research Trends in Utilizing Artificial Intelligence in Satellite-Based Internet of Things: A Scientometric Analysis

Today, according to the development of satellite-based hybrid networks -that are able to provide diverse and new services to the most parts of the planet-, the designers of such networks are encouraged to use new communication technologies such as the Internet of Things (IoT) and artificial intelligence (AI) to improve the performance of such classes of networks. In this article, using scientometric tools, the status of scientific publications in the field of "utilizing AI in satellite-based IoT" has been investigated. For this purpose, more than 475 research documents published from 2013 to 2023 have been extracted from the SCOPUS database and accordingly evaluated and analyzed using software tools such as Bibexcel and VOSviewer. Based on the statistical results, China, India and North America are among the top performing countries in this field. In addition, based on our findings, the schemes namely machine learning, deep learning, reinforcement learning, neural networks and convolutional neural networks have been used the most, in this research domain.