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.
2024
Lee, S.; Park, W.; Lee, K.
Building Knowledge Base of 3D Object Assets Using Multimodal LLM AI Model Proceedings Article
In: Int. Conf. ICT Convergence, pp. 416–418, IEEE Computer Society, 2024, ISBN: 21621233 (ISSN); 979-835036463-7 (ISBN).
Abstract | Links | BibTeX | Tags: 3D object, Asset management, Content services, Exponentials, Information Management, Knowledge Base, Language Model, Large language model, LLM, Multi-modal, Multi-Modal AI, Reusability, Visual effects, XR
@inproceedings{lee_building_2024,
title = {Building Knowledge Base of 3D Object Assets Using Multimodal LLM AI Model},
author = {S. Lee and W. Park and K. Lee},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85217636269&doi=10.1109%2fICTC62082.2024.10827434&partnerID=40&md5=581ee8ca50eb3dae15dc9675971cf428},
doi = {10.1109/ICTC62082.2024.10827434},
isbn = {21621233 (ISSN); 979-835036463-7 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Int. Conf. ICT Convergence},
pages = {416–418},
publisher = {IEEE Computer Society},
abstract = {The proliferation of various XR (eXtended Reality) services and the increasing incorporation of visual effects into existing content services have led to an exponential rise in the demand for 3D object assets. This paper describes an LLM (Large Language Model)-based multimodal AI model pipeline that can be applied to a generative AI model for creating new 3D objects or restructuring the asset management system to enhance the reusability of existing 3D objects. By leveraging a multimodal AI model, we derived descriptive text for assets such as 3D object, 2D image at a human-perceptible level, rather than mere data, and subsequently used an LLM to generate knowledge triplets for constructing an asset knowledge base. The applicability of this pipeline was verified using actual 3D objects from a content production company. Future work will focus on improving the quality of the generated knowledge triplets themselves by training the multimodal AI model with real-world content usage assets. © 2024 IEEE.},
keywords = {3D object, Asset management, Content services, Exponentials, Information Management, Knowledge Base, Language Model, Large language model, LLM, Multi-modal, Multi-Modal AI, Reusability, Visual effects, XR},
pubstate = {published},
tppubtype = {inproceedings}
}
The proliferation of various XR (eXtended Reality) services and the increasing incorporation of visual effects into existing content services have led to an exponential rise in the demand for 3D object assets. This paper describes an LLM (Large Language Model)-based multimodal AI model pipeline that can be applied to a generative AI model for creating new 3D objects or restructuring the asset management system to enhance the reusability of existing 3D objects. By leveraging a multimodal AI model, we derived descriptive text for assets such as 3D object, 2D image at a human-perceptible level, rather than mere data, and subsequently used an LLM to generate knowledge triplets for constructing an asset knowledge base. The applicability of this pipeline was verified using actual 3D objects from a content production company. Future work will focus on improving the quality of the generated knowledge triplets themselves by training the multimodal AI model with real-world content usage assets. © 2024 IEEE.
Lombardo, A.; Morabito, G.; Quattropani, S.; Ricci, C.; Siino, M.; Tinnirello, I.
AI-GeneSI: Exploiting generative AI for autonomous generation of the southbound interface in the IoT Proceedings Article
In: IEEE World Forum Internet Things, WF-IoT, Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 979-835037301-1 (ISBN).
Abstract | Links | BibTeX | Tags: 'current, Autonomous generation, Codes (symbols), Communications protocols, Complex task, Data representations, Digital world, Interface functions, Language Model, Reusability, Sensor nodes, Sensors data, Virtual objects, Virtual Reality
@inproceedings{lombardo_ai-genesi_2024,
title = {AI-GeneSI: Exploiting generative AI for autonomous generation of the southbound interface in the IoT},
author = {A. Lombardo and G. Morabito and S. Quattropani and C. Ricci and M. Siino and I. Tinnirello},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85216509327&doi=10.1109%2fWF-IoT62078.2024.10811300&partnerID=40&md5=cb20d5004d1f99b73b536dd0738cabd5},
doi = {10.1109/WF-IoT62078.2024.10811300},
isbn = {979-835037301-1 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {IEEE World Forum Internet Things, WF-IoT},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Virtual objects, which are representations in the digital world of physical entities, uses the data collected by one or several sensor nodes to operate. To overcome the diversity and heterogeneity of protocols implemented by different sensor nodes and the way in which sensor data is represented, it is convenient to exploit appropriate components referred to as 'southbound interfaces' in this paper. The objective of the southbound interface is to convert the communication protocols implemented by sensor nodes and virtual objects and to harmonize data representations. The implementation of the southbound interfaces is not a complex task, however it is extremely specific of the current setting, which turns in low reusability of the code, and is time-consuming. In this paper, a methodology named AI-GeneSI is proposed to exploit Large Language Models (LLM)s to generate the code to communicate with the southbound interface. Such code is utilized to create and deploy a microservice which implements the southbound interface functions. A prototype of the proposed methodology has been implemented to demonstrate the feasibility of the proposed approach. © 2024 IEEE.},
keywords = {'current, Autonomous generation, Codes (symbols), Communications protocols, Complex task, Data representations, Digital world, Interface functions, Language Model, Reusability, Sensor nodes, Sensors data, Virtual objects, Virtual Reality},
pubstate = {published},
tppubtype = {inproceedings}
}
Virtual objects, which are representations in the digital world of physical entities, uses the data collected by one or several sensor nodes to operate. To overcome the diversity and heterogeneity of protocols implemented by different sensor nodes and the way in which sensor data is represented, it is convenient to exploit appropriate components referred to as 'southbound interfaces' in this paper. The objective of the southbound interface is to convert the communication protocols implemented by sensor nodes and virtual objects and to harmonize data representations. The implementation of the southbound interfaces is not a complex task, however it is extremely specific of the current setting, which turns in low reusability of the code, and is time-consuming. In this paper, a methodology named AI-GeneSI is proposed to exploit Large Language Models (LLM)s to generate the code to communicate with the southbound interface. Such code is utilized to create and deploy a microservice which implements the southbound interface functions. A prototype of the proposed methodology has been implemented to demonstrate the feasibility of the proposed approach. © 2024 IEEE.
2008
Sabatucci, Luca; Garcia, Alessandro F.; Cacho, Nélio; Cossentino, Massimo; Gaglio, Salvatore
Conquering Fine-Grained Blends of Design Patterns Proceedings Article
In: ICSR, pp. 294–305, 2008.
Abstract | Links | BibTeX | Tags: Design Patterns, Pattern Blending, Reusability
@inproceedings{sabatucciConqueringFineGrainedBlends2008,
title = {Conquering Fine-Grained Blends of Design Patterns},
author = { Luca Sabatucci and Alessandro F. Garcia and Nélio Cacho and Massimo Cossentino and Salvatore Gaglio},
doi = {10.1007/978-3-540-68073-4_32},
year = {2008},
date = {2008-01-01},
booktitle = {ICSR},
pages = {294--305},
abstract = {The reuse of design patterns in realistic software systems is often a result of blending multiple pattern elements together rather than instantiating them in an isolated manner. The explicit description of pattern compositions is the key for (i) documenting the structure and the behavior of blended patterns and, (ii) more importantly, supporting the reuse of composite patterns across different software projects. In this context, this paper proposes a fine-grained composition language for describing varying blends of design patterns based on their structural and behavioural semantics. The reusability and expressiveness of the proposed language are assessed through its application to 32 compositions of GoF patterns recurrently appearing in three different case studies: the OpenOrb middleware, the JHotDraw and JUnit frameworks.},
keywords = {Design Patterns, Pattern Blending, Reusability},
pubstate = {published},
tppubtype = {inproceedings}
}
The reuse of design patterns in realistic software systems is often a result of blending multiple pattern elements together rather than instantiating them in an isolated manner. The explicit description of pattern compositions is the key for (i) documenting the structure and the behavior of blended patterns and, (ii) more importantly, supporting the reuse of composite patterns across different software projects. In this context, this paper proposes a fine-grained composition language for describing varying blends of design patterns based on their structural and behavioural semantics. The reusability and expressiveness of the proposed language are assessed through its application to 32 compositions of GoF patterns recurrently appearing in three different case studies: the OpenOrb middleware, the JHotDraw and JUnit frameworks.
Sabatucci, Luca; Garcia, Alessandro F.; Cacho, Nélio; Cossentino, Massimo; Gaglio, Salvatore
Conquering Fine-Grained Blends of Design Patterns Proceedings Article
In: ICSR, pp. 294–305, 2008.
Abstract | Links | BibTeX | Tags: Design Patterns, Pattern Blending, Reusability
@inproceedings{sabatucci_conquering_2008,
title = {Conquering Fine-Grained Blends of Design Patterns},
author = {Luca Sabatucci and Alessandro F. Garcia and Nélio Cacho and Massimo Cossentino and Salvatore Gaglio},
doi = {10.1007/978-3-540-68073-4_32},
year = {2008},
date = {2008-01-01},
booktitle = {ICSR},
pages = {294–305},
abstract = {The reuse of design patterns in realistic software systems is often a result of blending multiple pattern elements together rather than instantiating them in an isolated manner. The explicit description of pattern compositions is the key for (i) documenting the structure and the behavior of blended patterns and, (ii) more importantly, supporting the reuse of composite patterns across different software projects. In this context, this paper proposes a fine-grained composition language for describing varying blends of design patterns based on their structural and behavioural semantics. The reusability and expressiveness of the proposed language are assessed through its application to 32 compositions of GoF patterns recurrently appearing in three different case studies: the OpenOrb middleware, the JHotDraw and JUnit frameworks.},
keywords = {Design Patterns, Pattern Blending, Reusability},
pubstate = {published},
tppubtype = {inproceedings}
}
The reuse of design patterns in realistic software systems is often a result of blending multiple pattern elements together rather than instantiating them in an isolated manner. The explicit description of pattern compositions is the key for (i) documenting the structure and the behavior of blended patterns and, (ii) more importantly, supporting the reuse of composite patterns across different software projects. In this context, this paper proposes a fine-grained composition language for describing varying blends of design patterns based on their structural and behavioural semantics. The reusability and expressiveness of the proposed language are assessed through its application to 32 compositions of GoF patterns recurrently appearing in three different case studies: the OpenOrb middleware, the JHotDraw and JUnit frameworks.
2003
Cossentino, Massimo; Sabatucci, Luca; Chella, Antonio
A Possible Approach to the Development of Robotic Multi-Agent Systems Proceedings Article
In: IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003., pp. 539–544, IEEE, 2003.
Abstract | Links | BibTeX | Tags: Agents, Design Process, Multi agent systems, Reusability, Robotic Applications
@inproceedings{cossentinoPossibleApproachDevelopment2003,
title = {A Possible Approach to the Development of Robotic Multi-Agent Systems},
author = { Massimo Cossentino and Luca Sabatucci and Antonio Chella},
doi = {10.1109/IAT.2003.1241140},
year = {2003},
date = {2003-01-01},
booktitle = {IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.},
pages = {539--544},
publisher = {IEEE},
abstract = {The design of a an agent system for robotics is a problem that involves aspects coming from many different disciplines (robotics, artificial intelligence, computer vision, software engineering). The most difficult part of it, often consists in producing and tuning the algorithms that incorporates the robot behavior (planning, obstacle avoidance,. . . ) and abilities (vision, manipulation, navigation,. . . ). Frequently, the reuse of these parts is left to a copy and paste procedure from previous applications to the new one. In so doing many problems could arise. We propose a comprehensive approach for multi-agent systems oriented to robotics applications that uses a complete design methodology supported by a specific design tools and a pattern repository that interacting each other and with the designer allow the production of a coherent design that easily incorporates patterns coming from previously experienced features and automatically produces a large part of the final code},
keywords = {Agents, Design Process, Multi agent systems, Reusability, Robotic Applications},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of a an agent system for robotics is a problem that involves aspects coming from many different disciplines (robotics, artificial intelligence, computer vision, software engineering). The most difficult part of it, often consists in producing and tuning the algorithms that incorporates the robot behavior (planning, obstacle avoidance,. . . ) and abilities (vision, manipulation, navigation,. . . ). Frequently, the reuse of these parts is left to a copy and paste procedure from previous applications to the new one. In so doing many problems could arise. We propose a comprehensive approach for multi-agent systems oriented to robotics applications that uses a complete design methodology supported by a specific design tools and a pattern repository that interacting each other and with the designer allow the production of a coherent design that easily incorporates patterns coming from previously experienced features and automatically produces a large part of the final code
Cossentino, Massimo; Sabatucci, Luca; Chella, Antonio
A possible approach to the development of robotic multi-agent systems Proceedings Article
In: IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003., pp. 539–544, IEEE, 2003.
Abstract | Links | BibTeX | Tags: Agents, Design Process, Multi agent systems, Reusability, Robotic Applications
@inproceedings{cossentino_possible_2003,
title = {A possible approach to the development of robotic multi-agent systems},
author = {Massimo Cossentino and Luca Sabatucci and Antonio Chella},
doi = {10.1109/IAT.2003.1241140},
year = {2003},
date = {2003-01-01},
booktitle = {IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.},
pages = {539–544},
publisher = {IEEE},
abstract = {The design of a an agent system for robotics is a problem that involves aspects coming from many different disciplines (robotics, artificial intelligence, computer vision, software engineering). The most difficult part of it, often consists in producing and tuning the algorithms that incorporates the robot behavior (planning, obstacle avoidance,. . . ) and abilities (vision, manipulation, navigation,. . . ). Frequently, the reuse of these parts is left to a copy and paste procedure from previous applications to the new one. In so doing many problems could arise. We propose a comprehensive approach for multi-agent systems oriented to robotics applications that uses a complete design methodology supported by a specific design tools and a pattern repository that interacting each other and with the designer allow the production of a coherent design that easily incorporates patterns coming from previously experienced features and automatically produces a large part of the final code},
keywords = {Agents, Design Process, Multi agent systems, Reusability, Robotic Applications},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of a an agent system for robotics is a problem that involves aspects coming from many different disciplines (robotics, artificial intelligence, computer vision, software engineering). The most difficult part of it, often consists in producing and tuning the algorithms that incorporates the robot behavior (planning, obstacle avoidance,. . . ) and abilities (vision, manipulation, navigation,. . . ). Frequently, the reuse of these parts is left to a copy and paste procedure from previous applications to the new one. In so doing many problems could arise. We propose a comprehensive approach for multi-agent systems oriented to robotics applications that uses a complete design methodology supported by a specific design tools and a pattern repository that interacting each other and with the designer allow the production of a coherent design that easily incorporates patterns coming from previously experienced features and automatically produces a large part of the final code