AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2025
Tomkou, D.; Fatouros, G.; Andreou, A.; Makridis, G.; Liarokapis, F.; Dardanis, D.; Kiourtis, A.; Soldatos, J.; Kyriazis, D.
Bridging Industrial Expertise and XR with LLM-Powered Conversational Agents Proceedings Article
In: pp. 1050–1056, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 9798331543723 (ISBN).
Abstract | Links | BibTeX | Tags: Air navigation, Conversational Agents, Conversational AI, Embeddings, Engineering education, Extended reality, Knowledge Management, Knowledge transfer, Language Model, Large language model, large language models, Personnel training, Remote Assistance, Retrieval-Augmented Generation, Robotics, Semantics, Smart manufacturing
@inproceedings{tomkou_bridging_2025,
title = {Bridging Industrial Expertise and XR with LLM-Powered Conversational Agents},
author = {D. Tomkou and G. Fatouros and A. Andreou and G. Makridis and F. Liarokapis and D. Dardanis and A. Kiourtis and J. Soldatos and D. Kyriazis},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105013837767&doi=10.1109%2FDCOSS-IoT65416.2025.00158&partnerID=40&md5=45e35086d8be9d3e16afeade6598d238},
doi = {10.1109/DCOSS-IoT65416.2025.00158},
isbn = {9798331543723 (ISBN)},
year = {2025},
date = {2025-01-01},
pages = {1050–1056},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {This paper introduces a novel integration of Retrieval-Augmented Generation (RAG) enhanced Large Language Models (LLMs) with Extended Reality (XR) technologies to address knowledge transfer challenges in industrial environments. The proposed system embeds domain-specific industrial knowledge into XR environments through a natural language interface, enabling hands-free, context-aware expert guidance for workers. We present the architecture of the proposed system consisting of an LLM Chat Engine with dynamic tool orchestration and an XR application featuring voice-driven interaction. Performance evaluation of various chunking strategies, embedding models, and vector databases reveals that semantic chunking, balanced embedding models, and efficient vector stores deliver optimal performance for industrial knowledge retrieval. The system's potential is demonstrated through early implementation in multiple industrial use cases, including robotic assembly, smart infrastructure maintenance, and aerospace component servicing. Results indicate potential for enhancing training efficiency, remote assistance capabilities, and operational guidance in alignment with Industry 5.0's human-centric and resilient approach to industrial development. © 2025 Elsevier B.V., All rights reserved.},
keywords = {Air navigation, Conversational Agents, Conversational AI, Embeddings, Engineering education, Extended reality, Knowledge Management, Knowledge transfer, Language Model, Large language model, large language models, Personnel training, Remote Assistance, Retrieval-Augmented Generation, Robotics, Semantics, Smart manufacturing},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper introduces a novel integration of Retrieval-Augmented Generation (RAG) enhanced Large Language Models (LLMs) with Extended Reality (XR) technologies to address knowledge transfer challenges in industrial environments. The proposed system embeds domain-specific industrial knowledge into XR environments through a natural language interface, enabling hands-free, context-aware expert guidance for workers. We present the architecture of the proposed system consisting of an LLM Chat Engine with dynamic tool orchestration and an XR application featuring voice-driven interaction. Performance evaluation of various chunking strategies, embedding models, and vector databases reveals that semantic chunking, balanced embedding models, and efficient vector stores deliver optimal performance for industrial knowledge retrieval. The system's potential is demonstrated through early implementation in multiple industrial use cases, including robotic assembly, smart infrastructure maintenance, and aerospace component servicing. Results indicate potential for enhancing training efficiency, remote assistance capabilities, and operational guidance in alignment with Industry 5.0's human-centric and resilient approach to industrial development. © 2025 Elsevier B.V., All rights reserved.
Zhao, P.; Wei, X.
The Role of 3D Virtual Humans in Communication and Assisting Students' Learning in Transparent Display Environments: Perspectives of Pre-Service Teachers Proceedings Article
In: Chui, K. T.; Jaikaeo, C.; Niramitranon, J.; Kaewmanee, W.; Ng, K. -K.; Ongkunaruk, P. (Ed.): pp. 319–323, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 9798331595500 (ISBN).
Abstract | Links | BibTeX | Tags: 3D virtual human, Assistive technology, CDIO teaching model, Collaborative learning, Collaborative practices, Display environments, E-Learning, Educational Technology, Engineering education, feedback, Integration, Knowledge delivery, Knowledge transfer, Learning algorithms, Natural language processing systems, Preservice teachers, Psychology computing, Student learning, Students, Teaching, Teaching model, Transparent display environment, Transparent displays, Virtual Reality
@inproceedings{zhao_role_2025,
title = {The Role of 3D Virtual Humans in Communication and Assisting Students' Learning in Transparent Display Environments: Perspectives of Pre-Service Teachers},
author = {P. Zhao and X. Wei},
editor = {K. T. Chui and C. Jaikaeo and J. Niramitranon and W. Kaewmanee and K. -K. Ng and P. Ongkunaruk},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105015746241&doi=10.1109%2FISET65607.2025.00069&partnerID=40&md5=08c39b84fa6bd6ac13ddbed203d7b1d9},
doi = {10.1109/ISET65607.2025.00069},
isbn = {9798331595500 (ISBN)},
year = {2025},
date = {2025-01-01},
pages = {319–323},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The integration of transparent display and 3D virtual human technologies into education is expanding rapidly; however, their systematic incorporation into the CDIO teaching model remains underexplored, particularly in supporting complex knowledge delivery and collaborative practice. This study developed an intelligent virtual teacher assistance system based on generative AI and conducted a teaching experiment combining transparent display and 3D virtual human technologies. Feedback was collected through focus group interviews with 24 pre-service teachers. Results show that the virtual human, through natural language and multimodal interaction, significantly enhanced classroom engagement and contextual understanding, while its real-time feedback and personalized guidance effectively supported CDIO-based collaborative learning. Nonetheless, challenges remain in contextual adaptability and emotional feedback accuracy. Accordingly, the study proposes a path for technical optimization through the integration of multimodal emotion recognition, adaptive instructional algorithms, and nonintrusive data collection, offering empirical and theoretical insights into educational technology integration within the CDIO framework and future intelligent learning tools. © 2025 Elsevier B.V., All rights reserved.},
keywords = {3D virtual human, Assistive technology, CDIO teaching model, Collaborative learning, Collaborative practices, Display environments, E-Learning, Educational Technology, Engineering education, feedback, Integration, Knowledge delivery, Knowledge transfer, Learning algorithms, Natural language processing systems, Preservice teachers, Psychology computing, Student learning, Students, Teaching, Teaching model, Transparent display environment, Transparent displays, Virtual Reality},
pubstate = {published},
tppubtype = {inproceedings}
}
The integration of transparent display and 3D virtual human technologies into education is expanding rapidly; however, their systematic incorporation into the CDIO teaching model remains underexplored, particularly in supporting complex knowledge delivery and collaborative practice. This study developed an intelligent virtual teacher assistance system based on generative AI and conducted a teaching experiment combining transparent display and 3D virtual human technologies. Feedback was collected through focus group interviews with 24 pre-service teachers. Results show that the virtual human, through natural language and multimodal interaction, significantly enhanced classroom engagement and contextual understanding, while its real-time feedback and personalized guidance effectively supported CDIO-based collaborative learning. Nonetheless, challenges remain in contextual adaptability and emotional feedback accuracy. Accordingly, the study proposes a path for technical optimization through the integration of multimodal emotion recognition, adaptive instructional algorithms, and nonintrusive data collection, offering empirical and theoretical insights into educational technology integration within the CDIO framework and future intelligent learning tools. © 2025 Elsevier B.V., All rights reserved.