What is it about?
Research papers contain valuable information on scientific and technical research, and knowledge maps generated from them help identify areas of research and knowledge flow. This study develops a model based on meta-knowledge, including citations, abstracts, and area codes, for predicting future growth potential of technologies using deep learning algorithms. The study investigates the applicability of various forms of meta-knowledge to the prediction of future growth potential and proposes a method of selecting promising technology clusters based on the model.
Featured Image
Photo by Markus Spiske on Unsplash
Why is it important?
By developing a deep learning-based model that utilizes meta-knowledge from research papers, the study proposes a practical way to predict the future growth potential of various technologies. This approach enables the identification of promising areas of scientific and technical research, which is crucial for making informed decisions. The paper's findings can have significant implications for academia, industry, and policymakers alike, as they offer a valuable tool for enhancing research and development activities in various fields.
Perspectives
I hope that the model we developed using meta-knowledge and deep learning to predict future growth potential can be utilized not only by researchers, but also by various fields such as industry and government.
Dohyun Kim
Read the Original
This page is a summary of: Deep learning-based prediction of future growth potential of technologies, PLoS ONE, June 2021, PLOS,
DOI: 10.1371/journal.pone.0252753.
You can read the full text:
Contributors
The following have contributed to this page
