Exploring the Research Trend of Smart Factory with Topic Modeling

Abstract

Growing competition among manufacturing businesses and the advent of the Fourth Industrial Revolution has meant that many countries are conducting various research projects to understand how to introduce and populate smart factories. Smart factories are expected to provide a way of solving the manufacturing industries’ complex problems, to take a role in breakthroughs in factories and to carry on a sustainable business. Smart factories are currently in the introduction stage, so we should follow up on the majorities and check their tendencies. However, smart-factory research is an interdisciplinary field that should be studied by researchers with diverse backgrounds in various domains. Thus, studying the past and present overall research trends of smart factory studies is required for their successful introduction and sustainable research. In this study, we explored the research trends of smart factories in both international and specifically Korean research, as an example of a nation case, to determine the major research directions. We determined trends using latent semantic analysis, which is a known topic-modeling technique, and analyzed the trends with regression-based methods. As a result, we could read the clear trends by analyzing existing studies related to smart factories. In addition, it is possible to compare research trends in Korea and international research trends for the commonly appeared topics, such as ‘ICT’ (Information and Communications Technology) and ‘R&D (Research and Development)/Technology Innovation’. We expect that the quantitative analysis results and suggestions presented in this study can be used to formulate strategies for the future diffusion of smart factories.

Exploring the Future Development of Research, Technology and Business of Machine Tool Domain in New-Generation Information Technology Environment Based on Machine Learning

“…To deeply analyze the contents of scientific literatures, machine learning method based on topic models has been widely used in technology trend analysis tasks in recent years [26][27][28][29]32]. Yang et al explored the research trending topics of smart factories using topic modeling method to determine the future research directions [11]. Abuhay et al modeled the underlying topical structures of the International Conference on Computational Science and provided insights regarding the past and future technology trends in computational science [31].…”

“…Based on expert domain experience, these works provided valuable insights to some extent for guiding the future development of technology. However, it is difficult to explore a large number of related papers by reading them because of the enormous time and energy required and the difficulties in comprehending topics in heterogeneous areas [11]. The above qualitative analysis method is incapable of keeping up with the rapid increase number of papers comprehensively in the whole machine tool discipline.…”

“…In light of the fact that literatures can enable us to obtain the solutions to specific problems and learn the creation of new ideas, a large amount of information reflecting the technological development trend exist in the content of scientific literatures. Implementing detailed mining of literatures content can help us obtain deeper insight into technology development [11]. To effectively process and analyze the content of scientific literatures, machine learning method based on topic models have been proposed and widely used in technical foresight tasks in recent years [26][27][28][29][30][31][32].…”

Exploring the Development of Research, Technology and Business of Machine Tool Domain in New-Generation Information Technology Environment Based on Machine Learning

“…Based on expert domain experience, these works provided valuable insights to some extent for guiding the future development of technology. However, it is difficult to explore a large number of related papers by reading them because of the enormous time and energy required and the difficulties in comprehending topics in heterogeneous areas [11]. The above qualitative analysis method is incapable of keeping up with the rapidly increasing number of papers comprehensively in the whole machine tool discipline.…”

“…Because literature can enable us to obtain the solutions to specific problem and learn the creation of a new idea, a large amount of information reflecting the technology development exist in the contents of scientific literature. Implementing detailed mining of literature contents can help us obtain deeper insight into technology development [11]. To effectively process and analyze the contents of scientific literature, machine learning method based on topic models has been proposed and widely used in technology mining tasks in recent years [27][28][29][30][31][32][33].…”