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
Hu, H.; Wan, Y.; Tang, K. Y.; Li, Q.; Wang, X.
Affective-Computing-Driven Personalized Display of Cultural Information for Commercial Heritage Architecture Journal Article
In: Applied Sciences (Switzerland), vol. 15, no. 7, 2025, ISSN: 20763417 (ISSN).
Abstract | Links | BibTeX | Tags: Affective Computing, Cultural informations, Cultural value, Data fusion, Information display, Information fusion, Information presentation, Language Model, Large language model, Multimodal information fusion, User-generated, User-generated content, Virtual environments
@article{hu_affective-computing-driven_2025,
title = {Affective-Computing-Driven Personalized Display of Cultural Information for Commercial Heritage Architecture},
author = {H. Hu and Y. Wan and K. Y. Tang and Q. Li and X. Wang},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105002467183&doi=10.3390%2fapp15073459&partnerID=40&md5=1dc611258248d58a2bf5f44b6a0e890b},
doi = {10.3390/app15073459},
issn = {20763417 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Applied Sciences (Switzerland)},
volume = {15},
number = {7},
abstract = {The display methods for traditional cultural heritage lack personalization and emotional interaction, making it difficult to stimulate the public’s deep cultural awareness. This is especially true in commercialized historical districts, where cultural value is easily overlooked. Balancing cultural value and commercial value in information display has become one of the challenges that needs to be addressed. To solve the above problems, this article focuses on the identification of deep cultural values and the optimization of the information display in Beijing’s Qianmen Street, proposing a framework for cultural information mining and display based on affective computing and large language models. The pre-trained models QwenLM and RoBERTa were employed to analyze text and image data from user-generated content on social media, identifying users’ emotional tendencies toward various cultural value dimensions and quantifying their multilayered understanding of architectural heritage. This study further constructed a multimodal information presentation model driven by emotional feedback, mapping it into virtual reality environments to enable personalized, multilayered cultural information visualization. The framework’s effectiveness was validated through an eye-tracking experiment that assessed how different presentation styles impacted users’ emotional engagement and cognitive outcomes. The results show that the affective computing and multimodal data fusion approach to cultural heritage presentation accurately captures users’ emotions, enhancing their interest and emotional involvement. Personalized presentations of information significantly improve users’ engagement, historical understanding, and cultural experience, thereby fostering a deeper comprehension of historical contexts and architectural details. © 2025 by the authors.},
keywords = {Affective Computing, Cultural informations, Cultural value, Data fusion, Information display, Information fusion, Information presentation, Language Model, Large language model, Multimodal information fusion, User-generated, User-generated content, Virtual environments},
pubstate = {published},
tppubtype = {article}
}
The display methods for traditional cultural heritage lack personalization and emotional interaction, making it difficult to stimulate the public’s deep cultural awareness. This is especially true in commercialized historical districts, where cultural value is easily overlooked. Balancing cultural value and commercial value in information display has become one of the challenges that needs to be addressed. To solve the above problems, this article focuses on the identification of deep cultural values and the optimization of the information display in Beijing’s Qianmen Street, proposing a framework for cultural information mining and display based on affective computing and large language models. The pre-trained models QwenLM and RoBERTa were employed to analyze text and image data from user-generated content on social media, identifying users’ emotional tendencies toward various cultural value dimensions and quantifying their multilayered understanding of architectural heritage. This study further constructed a multimodal information presentation model driven by emotional feedback, mapping it into virtual reality environments to enable personalized, multilayered cultural information visualization. The framework’s effectiveness was validated through an eye-tracking experiment that assessed how different presentation styles impacted users’ emotional engagement and cognitive outcomes. The results show that the affective computing and multimodal data fusion approach to cultural heritage presentation accurately captures users’ emotions, enhancing their interest and emotional involvement. Personalized presentations of information significantly improve users’ engagement, historical understanding, and cultural experience, thereby fostering a deeper comprehension of historical contexts and architectural details. © 2025 by the authors.
2024
Ma, H.; Yao, X.; Wang, X.
Metaverses for Parallel Transportation: From General 3D Traffic Environment Construction to Virtual-Real I2TS Management and Control Proceedings Article
In: Proc. - IEEE Int. Conf. Digit. Twins Parallel Intell., DTPI, pp. 598–603, Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 979-835034925-2 (ISBN).
Abstract | Links | BibTeX | Tags: Advanced traffic management systems, Data fusion, generative artificial intelligence, Highway administration, Information Management, Intelligent transportation systems, Interactive Intelligent Transportation System, Metaverses, Mixed Traffic, Parallel Traffic System, Social Diversity and Uncertainty, Traffic control, Traffic Metaverse, Traffic systems, Uncertainty, Virtual addresses, Virtual environments
@inproceedings{ma_metaverses_2024,
title = {Metaverses for Parallel Transportation: From General 3D Traffic Environment Construction to Virtual-Real I2TS Management and Control},
author = {H. Ma and X. Yao and X. Wang},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85214916181&doi=10.1109%2fDTPI61353.2024.10778876&partnerID=40&md5=94a6bf4b06a2a45f7c483936beee840f},
doi = {10.1109/DTPI61353.2024.10778876},
isbn = {979-835034925-2 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Proc. - IEEE Int. Conf. Digit. Twins Parallel Intell., DTPI},
pages = {598–603},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Metaverse technologies have enabled the creation of highly realistic artificial traffic system via real-time multi-source data fusion, while generative artificial intelligence (GAI) has facilitated the construction of large-scale traffic scenarios and the evaluation of strategies. This integration allows for the modeling of traffic environments that blend virtual and real-world interactions, providing digital proving grounds for the management and control (M&C) of intelligent transportation systems (ITS). This paper comprehensively reviews the evolution of traffic modeling tools, from traditional 2D and 3D traffic simulations to the construction of generative 3D traffic environments based on digital twin (DT) technologies and the metaverse. Furthermore, to address the challenges posed by social diversity and uncertainty in mixed traffic, as well as the limitations of traditional methods, we propose a virtual-real interaction M&C strategy based on GAI. This strategy integrates the metaverse into parallel traffic systems (PTS), enabling bidirectional interaction and collaboration between virtual and physical environments. Through specific case studies, this research demonstrates the potential of combining the metaverse with PTS to enhance the efficiency of mixed traffic systems. © 2024 IEEE.},
keywords = {Advanced traffic management systems, Data fusion, generative artificial intelligence, Highway administration, Information Management, Intelligent transportation systems, Interactive Intelligent Transportation System, Metaverses, Mixed Traffic, Parallel Traffic System, Social Diversity and Uncertainty, Traffic control, Traffic Metaverse, Traffic systems, Uncertainty, Virtual addresses, Virtual environments},
pubstate = {published},
tppubtype = {inproceedings}
}
Metaverse technologies have enabled the creation of highly realistic artificial traffic system via real-time multi-source data fusion, while generative artificial intelligence (GAI) has facilitated the construction of large-scale traffic scenarios and the evaluation of strategies. This integration allows for the modeling of traffic environments that blend virtual and real-world interactions, providing digital proving grounds for the management and control (M&C) of intelligent transportation systems (ITS). This paper comprehensively reviews the evolution of traffic modeling tools, from traditional 2D and 3D traffic simulations to the construction of generative 3D traffic environments based on digital twin (DT) technologies and the metaverse. Furthermore, to address the challenges posed by social diversity and uncertainty in mixed traffic, as well as the limitations of traditional methods, we propose a virtual-real interaction M&C strategy based on GAI. This strategy integrates the metaverse into parallel traffic systems (PTS), enabling bidirectional interaction and collaboration between virtual and physical environments. Through specific case studies, this research demonstrates the potential of combining the metaverse with PTS to enhance the efficiency of mixed traffic systems. © 2024 IEEE.