A Study on Metaverse Realistic Content Education Platform Using Deep Learning
- Authors
- Lee, Hyunsook; Youm, Sekyoung
- Issue Date
- Jun-2023
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Keywords
- Engineering Education; Artificial Intelligence Technologies; Educational Environment; Front End; Immersive; Machine Learning Agents; Metaverses; Quality Of Education; Resource Efficiencies; Specific Languages; Web Environment; Deep Learning
- Citation
- Lecture Notes in Electrical Engineering, v.1028 LNEE, pp 313 - 317
- Pages
- 5
- Indexed
- SCOPUS
- Journal Title
- Lecture Notes in Electrical Engineering
- Volume
- 1028 LNEE
- Start Page
- 313
- End Page
- 317
- URI
- https://scholarworks.dongguk.edu/handle/sw.dongguk/19385
- DOI
- 10.1007/978-981-99-1252-0_41
- ISSN
- 1876-1100
1876-1119
- Abstract
- Artificial intelligence technology combined with Metaverse Realistic Content (VR/AR Content) is a powerful combination that provides a diverse educational environment. Recent developments in artificial intelligence technology can enhance the quality of education without the help of assistants in immersive education and it can be seen as a field that can be developed in terms of resource efficiency and time saving by learning repetitive outcomes (success/failure). However, this combination has challenges. Currently, Unity’s Machine Learning Agent toolkit exists, but it has limitations for specific languages and specific environments and has additional learning challenges. In addition, it is difficult to realize that it is necessary to support various front-end frameworks and various hardware, and to support the entire combination. In addition, it is necessary to study connections between frameworks to support mobile devices and web environment. This problem has long been recognized in computer science and has been solved by compiler technology. In this paper, we propose a Framework Bridge Model based on LLVM IR (Low-level virtual machine intermediate representation) in VR/AR development environment, so that deep learning developers can choose the optimal combination of frameworks. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Department of Industrial and Systems Engineering > 1. Journal Articles

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.