Publications

@inproceedings{monaco_negotiator_2024,

title = {The Negotiator: Interactive Hostage-Taking Training Simulation},

author = {P. -B. Monaco and P. Backlund and S. Gobron},

editor = {De Rango F. and Werner F. and Wagner G.},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85206332014&doi=10.5220%2f0012720300003758&partnerID=40&md5=03ebb4c5577432071e3f180a5f50be2b},

doi = {10.5220/0012720300003758},

isbn = {21842841 (ISSN); 978-989758708-5 (ISBN)},

year  = {2024},

date = {2024-01-01},

booktitle = {Proc. Int. Conf. Simul. Model. Methodol. Technol. Appl.},

pages = {242–249},

publisher = {Science and Technology Publications, Lda},

abstract = {High-stakes professions like negotiators and pilots utilize simulations for risk-free training, enhancing skills and decision-making. Traditional simulations, while effective, are resource-intensive. Computer simulations offer a scalable alternative but lack realism and sensory engagement, impacting immersion. This study explores mobile phones’ role in simulation-based learning, using a 3D hostage-taking scenario to improve immersion through realistic interactions. The simulation integrates a detailed environment and interactive elements, and demonstrate the potential of mobile technology to enhance training in critical fields by making simulations more lifelike and engaging. This paper is presented alongside a twin paper, both part of the same project Master final project. The second paper introduces a different version of the simulation using a Large Language Model (like ChatGPT) for generating dialogue freely and interactively. It also discusses the results of a study comparing immersion levels between the two versions. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.},

keywords = {3D, Decision-Making, Hostage-Taking, Human-Machine Interface, Immersion, Mobile Phone, Multimodal Systems, Natural Language Processing, Negotiation, Virtual Reality},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{klein_ai_2024,

title = {AI in mixed reality - Copilot on HoloLens: Spatial computing with large language models},

author = {A. Klein and E. Arnowitz},

editor = {Spencer S.N.},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200657459&doi=10.1145%2f3641520.3665305&partnerID=40&md5=07d385771b8813c1fafa0efb7ae7e9f2},

doi = {10.1145/3641520.3665305},

isbn = {979-840070526-7 (ISBN)},

year  = {2024},

date = {2024-01-01},

booktitle = {Proc. - SIGGRAPH Real-Time Live!},

publisher = {Association for Computing Machinery, Inc},

abstract = {Mixed reality together with AI presents a human-first interface that promises to transform operations. Copilot can assist industrial workers in real-time with speech and holograms; generative AI is used to search technical documentation, service records, training content, and other sources. Copilot then summarizes to provide interactive guidance. © 2024 Owner/Author.},

keywords = {3D, AI, AR, Gesture, Gestures, HoloLens, Language Model, LLM, Mixed reality, Real- time, Real-time, Spatial computing, User experience design, User interfaces, Voice},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{joseph_iot_2023,

title = {IoT Empowered AI: Transforming Object Recognition and NLP Summarization with Generative AI},

author = {S. Joseph and B. S. Priya and R. Poorvaja and M. Santhosh Kumaran and S. Shivaraj and V. Jeyanth and R. P. Shivesh},

editor = {Arya K.V. and Wada T.},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189754688&doi=10.1109%2fCVMI59935.2023.10465077&partnerID=40&md5=9c1a9d7151c0b04bab83586f515d30aa},

doi = {10.1109/CVMI59935.2023.10465077},

isbn = {979-835030514-2 (ISBN)},

year  = {2023},

date = {2023-01-01},

booktitle = {Proc. IEEE Int. Conf. Comput. Vis. Mach. Intell., CVMI},

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

abstract = {In anticipation of the widespread adoption of augmented reality in the future, this paper introduces an advanced mobile application that seamlessly integrates AR and IoT technologies. The application aims to make these cutting-edge technologies more affordable and accessible to users while highlighting their immense benefits in assisting with household appliance control, as well as providing interactive and educational experiences. The app employs advanced algorithms such as object detection, Natural Language Processing (NLP), and Optical Character Recognition (OCR) to scan the smartphone's camera feed. Upon identification, AR controls for appliances, their power consumption, and electric bill tracking are displayed. Additionally, the application makes use of APIs to access the internet, retrieving relevant 3D generative models, 360-degree videos, 2D images, and textual information based on user interactions with detected objects. Users can effortlessly explore and interact with the 3D generative models using intuitive hand gestures, providing an immersive experience without the need for additional hardware or dedicated VR headsets. Beyond home automation, the app offers valuable educational benefits, serving as a unique learning tool for students to gain hands-on experience. Medical practitioners can quickly reference organ anatomy and utilize its feature-rich functionalities. Its cost-effectiveness, requiring only installation, ensures accessibility to a wide audience. The app's functionality is both intuitive and efficient, detecting objects in the camera feed and prompting user interactions. Users can select objects through simple hand gestures, choosing desired content like 3D generative models, 2D images, textual information, 360-degree videos, or shopping-related details. The app then retrieves and overlays the requested information onto the real-world view in AR. In conclusion, this groundbreaking AR and IoT -powered app revolutionizes home automation and learning experiences, leveraging only a smartphone's camera, without the need for additional hardware or expensive installations. Its potential applications extend to education, industries, and health care, making it a versatile and valuable tool for a broad range of users. © 2023 IEEE.},

keywords = {2D, 3D, Application program interface, Application Program Interface (API), Application program interfaces, Application programming interfaces (API), Application programs, Augmented Reality, Augmented Reality(AR), Automation, Cameras, Cost effectiveness, Domestic appliances, GenAl, Internet of Things, Internet of Things (IoT) technologies, Internet of things technologies, Language processing, Natural Language Processing, Natural language processing systems, Natural languages, Object Detection, Object recognition, Objects detection, Optical character recognition, Optical Character Recognition (OCR), Smartphones},

pubstate = {published},

tppubtype = {inproceedings}

}