Publications

@inproceedings{shrestha_generative_2024,

title = {Generative AI based industrial metaverse creation methodology},

author = {A. Shrestha and K. Imamoto},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85215066217&doi=10.1109%2fAIxB62249.2024.00017&partnerID=40&md5=d6d11729f16ccaa9f69fd5452befe492},

doi = {10.1109/AIxB62249.2024.00017},

isbn = {979-835039103-9 (ISBN)},

year  = {2024},

date = {2024-01-01},

booktitle = {Proc. - Artif. Intell. Bus., AIxB},

pages = {53–57},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {The metaverse has been proposed as a suitable apparatus for the dissemination of information in a railway maintenance and operation context. However, the generation of such a metaverse environment requires significant investment with the creation of simple prototypes taking an extended duration. Although there are generative artificial intelligencebased methods to create small scenes, there is an absence of a method to do so for industrial applications. We devised a platform to create railway environments with the assistance of the language models for code creation and semantic inference without the need for reprogramming or editing of the project source meaning environments could be generated by the end users. With a natural language input and a coding paradigm output the code generation module is shown together with the example environments from real-life railway lines in Tokyo, Japan as preliminary results. By creating such environments leveraging the rapid generation with the help of generative artificial intelligence, we show generative artificial intelligence can be used to automate the task of the programmer to create new environments on demand from the user in natural language. © 2024 IEEE.},

keywords = {Generative adversarial networks, Generative AI, Industrial metaverse, Industrial railroads, Investments, Maintenance and operation, Metaverses, Natural languages, Railroad transportation, Railway, Railway maintenance, Railway operations, Simple++, simulation},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{horvath_structured_2023,

title = {Structured Template Language and Generative AI Driven Content Management for Personalized Workspace Reconfiguration},

author = {I. Horvath and A. B. Csapo},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85184849596&doi=10.1109%2fCVR58941.2023.10395520&partnerID=40&md5=c3890e80798c9ec542fe453875dde253},

doi = {10.1109/CVR58941.2023.10395520},

isbn = {979-835033863-8 (ISBN)},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE Int. Conf. Cogn. Asp. Virtual Real., CVR},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {This work presents a systematic approach towards personalized workspace management and reconfiguration in 3D Virtual Reality (VR) spaces, focusing on a structured template language for defining and manipulating content layout schemas, as well as a generative AI supported content management solution. Recognizing the varying requirements of different tasks and workflows, on the one hand we propose a hierarchical template language that enables, through simple steps, the adaptation of number and variety of documents within geometric layout schemas in digital 3D spaces. In the second half of the paper, we present a generative AI driven framework for integrating associative-semantic content management into such workspaces, thereby enhancing the relevance and contextuality of workspace configurations. The proposed approach aids in identifying content that is semantically linked to a given spatial, temporal and topical environment, enabling workspace designers and users to create more efficient and personalized workspace layouts. © 2023 IEEE.},

keywords = {3D spaces, 3D virtual reality, Cognitive infocommunications, Content management, Content management solutions, Geometric layout, Knowledge engineering, Semantic content, Semantic content management, Semantics, Simple++, Virtual Reality, Work-flows},

pubstate = {published},

tppubtype = {inproceedings}

}