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
Wang, R. -G.; Tsai, C. H.; Tseng, M. C.; Hong, R. -C.; Syu, H.; Chou, C. -C.
Immersive Smart Meter Data Analytics: Leveraging eXtended Reality with LSTM and LLMs Proceedings Article
In: pp. 32–36, International Workshop on Computer Science and Engineering (WCSE), 2025.
Abstract | Links | BibTeX | Tags: Data Analytics, Data visualization, Decision making, Energy management, Energy-consumption, Exponential growth, Extended reality (XR), Forecasting, Human computer interaction, Immersive, Language Model, Large language model, large language models (LLMs), Long short-term memory, Long Short-Term Memory (LSTM), Short term memory, Smart Grid technologies, Smart Meters, Smart power grids, Visual analytics
@inproceedings{wang_immersive_2025,
title = {Immersive Smart Meter Data Analytics: Leveraging eXtended Reality with LSTM and LLMs},
author = {R. -G. Wang and C. H. Tsai and M. C. Tseng and R. -C. Hong and H. Syu and C. -C. Chou},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105017965008&doi=10.18178%2Fwcse.2025.06.006&partnerID=40&md5=866ab1ca8cdf0372c020f0131f1d68c1},
doi = {10.18178/wcse.2025.06.006},
year = {2025},
date = {2025-01-01},
pages = {32–36},
publisher = {International Workshop on Computer Science and Engineering (WCSE)},
abstract = {The rapid advancement of smart grid technologies has led to an exponential growth in smart meter data, creating new opportunities for more accurate energy consumption forecasting and immersive data visualization. This study proposes an integrated framework that combines eXtended Reality (XR), Long Short-Term Memory (LSTM) networks, and Large Language Models (LLMs) to enhance smart meter data analytics. The process begins with the application of LSTM to capture temporal dependencies in historical electricity usage data. Subsequently, the Large Language Models (LLMs) are employed to refine these textual forecasts, offering better predictions and explanations that are easily understandable by end-users. Finally, the enriched insights are presented through an XR environment, enabling users to interact with smart meter analytics in an immersive and intuitive way. By visualizing data trends, predictions, and explanatory narratives in a spatial computing interface, users can explore complex information more effectively. This multi-modal approach facilitates better decision-making for energy management, promotes user engagement, and supports smart city initiatives aiming for sustainable energy consumption. The integration of XR, LSTM, and LLMs technologies demonstrates a promising direction for future research and practical applications in smart energy systems. © 2025 Elsevier B.V., All rights reserved.},
keywords = {Data Analytics, Data visualization, Decision making, Energy management, Energy-consumption, Exponential growth, Extended reality (XR), Forecasting, Human computer interaction, Immersive, Language Model, Large language model, large language models (LLMs), Long short-term memory, Long Short-Term Memory (LSTM), Short term memory, Smart Grid technologies, Smart Meters, Smart power grids, Visual analytics},
pubstate = {published},
tppubtype = {inproceedings}
}
The rapid advancement of smart grid technologies has led to an exponential growth in smart meter data, creating new opportunities for more accurate energy consumption forecasting and immersive data visualization. This study proposes an integrated framework that combines eXtended Reality (XR), Long Short-Term Memory (LSTM) networks, and Large Language Models (LLMs) to enhance smart meter data analytics. The process begins with the application of LSTM to capture temporal dependencies in historical electricity usage data. Subsequently, the Large Language Models (LLMs) are employed to refine these textual forecasts, offering better predictions and explanations that are easily understandable by end-users. Finally, the enriched insights are presented through an XR environment, enabling users to interact with smart meter analytics in an immersive and intuitive way. By visualizing data trends, predictions, and explanatory narratives in a spatial computing interface, users can explore complex information more effectively. This multi-modal approach facilitates better decision-making for energy management, promotes user engagement, and supports smart city initiatives aiming for sustainable energy consumption. The integration of XR, LSTM, and LLMs technologies demonstrates a promising direction for future research and practical applications in smart energy systems. © 2025 Elsevier B.V., All rights reserved.
2024
Weerasinghe, K.; Janapati, S.; Ge, X.; Kim, S.; Iyer, S.; Stankovic, J. A.; Alemzadeh, H.
Real-Time Multimodal Cognitive Assistant for Emergency Medical Services Proceedings Article
In: Proc. - ACM/IEEE Conf. Internet-of-Things Des. Implement., IoTDI, pp. 85–96, Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 9798350370256 (ISBN).
Abstract | Links | BibTeX | Tags: Artificial intelligence, Augmented Reality, Cognitive Assistance, Computational Linguistics, Decision making, Domain knowledge, Edge computing, Emergency medical services, Forecasting, Graphic methods, Language Model, machine learning, Machine-learning, Multi-modal, Real- time, Service protocols, Smart Health, Speech recognition, State of the art
@inproceedings{weerasinghe_real-time_2024,
title = {Real-Time Multimodal Cognitive Assistant for Emergency Medical Services},
author = {K. Weerasinghe and S. Janapati and X. Ge and S. Kim and S. Iyer and J. A. Stankovic and H. Alemzadeh},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85197769304&doi=10.1109%2FIoTDI61053.2024.00012&partnerID=40&md5=79a4d9cd1054891f10fef7a88fefd3a3},
doi = {10.1109/IoTDI61053.2024.00012},
isbn = {9798350370256 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Proc. - ACM/IEEE Conf. Internet-of-Things Des. Implement., IoTDI},
pages = {85–96},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Emergency Medical Services (EMS) responders often operate under time-sensitive conditions, facing cognitive overload and inherent risks, requiring essential skills in critical thinking and rapid decision-making. This paper presents CognitiveEMS, an end-to-end wearable cognitive assistant system that can act as a collaborative virtual partner engaging in the real-time acquisition and analysis of multimodal data from an emergency scene and interacting with EMS responders through Augmented Reality (AR) smart glasses. CognitiveEMS processes the continuous streams of data in real-time and leverages edge computing to provide assistance in EMS protocol selection and intervention recognition. We address key technical challenges in real-time cognitive assistance by introducing three novel components: (i) a Speech Recognition model that is fine-tuned for real-world medical emergency conversations using simulated EMS audio recordings, augmented with synthetic data generated by large language models (LLMs); (ii) an EMS Protocol Prediction model that combines state-of-the-art (SOTA) tiny language models with EMS domain knowledge using graph-based attention mechanisms; (iii) an EMS Action Recognition module which leverages multimodal audio and video data and protocol predictions to infer the intervention/treatment actions taken by the responders at the incident scene. Our results show that for speech recognition we achieve superior performance compared to SOTA (WER of 0.290 vs. 0.618) on conversational data. Our protocol prediction component also significantly outperforms SOTA (top-3 accuracy of 0.800 vs. 0.200) and the action recognition achieves an accuracy of 0.727, while maintaining an end-to-end latency of 3.78s for protocol prediction on the edge and 0.31s on the server. © 2024 Elsevier B.V., All rights reserved.},
keywords = {Artificial intelligence, Augmented Reality, Cognitive Assistance, Computational Linguistics, Decision making, Domain knowledge, Edge computing, Emergency medical services, Forecasting, Graphic methods, Language Model, machine learning, Machine-learning, Multi-modal, Real- time, Service protocols, Smart Health, Speech recognition, State of the art},
pubstate = {published},
tppubtype = {inproceedings}
}
Emergency Medical Services (EMS) responders often operate under time-sensitive conditions, facing cognitive overload and inherent risks, requiring essential skills in critical thinking and rapid decision-making. This paper presents CognitiveEMS, an end-to-end wearable cognitive assistant system that can act as a collaborative virtual partner engaging in the real-time acquisition and analysis of multimodal data from an emergency scene and interacting with EMS responders through Augmented Reality (AR) smart glasses. CognitiveEMS processes the continuous streams of data in real-time and leverages edge computing to provide assistance in EMS protocol selection and intervention recognition. We address key technical challenges in real-time cognitive assistance by introducing three novel components: (i) a Speech Recognition model that is fine-tuned for real-world medical emergency conversations using simulated EMS audio recordings, augmented with synthetic data generated by large language models (LLMs); (ii) an EMS Protocol Prediction model that combines state-of-the-art (SOTA) tiny language models with EMS domain knowledge using graph-based attention mechanisms; (iii) an EMS Action Recognition module which leverages multimodal audio and video data and protocol predictions to infer the intervention/treatment actions taken by the responders at the incident scene. Our results show that for speech recognition we achieve superior performance compared to SOTA (WER of 0.290 vs. 0.618) on conversational data. Our protocol prediction component also significantly outperforms SOTA (top-3 accuracy of 0.800 vs. 0.200) and the action recognition achieves an accuracy of 0.727, while maintaining an end-to-end latency of 3.78s for protocol prediction on the edge and 0.31s on the server. © 2024 Elsevier B.V., All rights reserved.