Advanced Data MIning Research And (Business intelligence | Bioinformatics | Big Data) LEarning
SAVOR project
Self-Adaptive and context-aware intelligent training systems in sensorised immersive Virtual Reality environments for Occupational Risk Prevention
Project summary
Occupational Risk Prevention (ORP) aims to train workers in good health and safety habits and is essential to complete the technical training required to use new loading equipment such as forklifts and telehandlers. This is paramount in key sectors such as industry, construction, and agriculture, where a large number of accidents at work are concentrated in the country’s companies, causing a human tragedy, additional costs to the health system and a significant loss of productivity for companies. Previous studies have shown that adaptive learning (where the problem, stimulus or task varies according to the learner’s performance) significantly improves learning outcomes. Immersive Virtual Reality (IVR) enables to simulate complex situations, but so far it only offers ad-hoc solutions for specific scenarios that do not adapt to different learning styles (experience, reaction to risk situations, gender…).
The aim of this project is to design and implement a self-adaptive system for training the operation of these machines in virtual environments, which will represent a significant advance in the ORP of these key sectors.
The main challenge is to make the IVR simulator “intelligent” and to turn it into an adaptive simulator, capable of adapting in real time to the needs and rhythms of the user by regulating the virtual environment and through intelligent agents (avatars). To this end, based on multimodal datasets of users and environments, advanced artificial intelligence (AI) techniques will be studied and applied, allowing the system to be scalable to new learning tasks, including the development of new algorithms if necessary. Among others, the project proposes to exploit the use of semi-supervised learning (to reduce the need for labelled data by experts), unbalanced, real-time learning, feature selection, and transfer learning (key to improving the simulator performance of one domain or machine by using data from another).
Simplified diagram of an adaptive system, as envisioned in the SAVOR project
The final outcome of the project (a product with TRL 6 maturity) will be tested in the facilities of several collaborating companies and public training organisations (8 in total) that have expressed interest in the project and have committed to collaborate in the tasks of data collection with users and validation of results.
Buscamos personas voluntarias para Experimento de Realidad Virtual con sensores fisiológicos
Estamos llevando a cabo un experimento, y necesitamos vuestra colaboración.
🔬 Objetivo:
Conocer y analizar distintas respuestas fisiológicas en un entorno experimental de realidad virtual mediante sensores fisiológicos. Como voluntario/a, te sumergirás en un entorno virtual mientras se registran tus señales fisiológicas como:
Frecuencia cardíaca 🫀
Conductancia de la piel ⚡
⏳ ¿Cuánto dura la prueba?
Aproximadamente 20 minutos, incluyendo la firma del consentimiento, la medición de valores iniciales (baseline) y la experiencia en Realidad Virtual.
📍 Ubicación:
Escuela Politécnica Superior
📅 Fechas disponibles:
Desde el martes 4 de febrero hasta el jueves 13 de febrero de 2025.
🕘 Horarios disponibles:
Mañanas: 9:00 – 14:00 Tardes: 16:00 – 19:00
⚠️ Importante: La participación es voluntaria y se requerirá la firma de un consentimiento informado antes del inicio del experimento.
@article{Ramírez-Sanz2026,
title = {Semi-Supervised Rotation Forest},
author = {José Miguel Ramírez-Sanz and David Martínez-Acha and Álvar Arnaiz-González and César García-Osorio and Juan J. Rodríguez},
doi = {10.1016/j.jocs.2025.102777},
issn = {1877-7503},
year = {2026},
date = {2026-02-00},
urldate = {2026-02-00},
journal = {Journal of Computational Science},
volume = {94},
publisher = {Elsevier BV},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@article{guillen2025,
title = {Can Immersive Virtual Reality Environments Improve Stress Reduction? Experimental Design with Progressive Muscle Relaxation Training},
author = {Henar Guillen-Sanz and María del Camino Escolar-Llamazares and Itziar Quevedo-Bayona and María Ángeles Martínez-Martín and Andrés Bustillo},
editor = {IEEE},
url = {https://ieeexplore.ieee.org/document/11034975},
doi = {10.1109/ACCESS.2025.3579493},
issn = {2169-3536 },
year = {2025},
date = {2025-06-13},
urldate = {2025-06-13},
journal = {IEEE Access},
abstract = {Psychological relaxation techniques are now fundamental in stress-management and anxiety-disorder prevention training. Progressive Muscle Relaxation (PMR) stands out among various other training programmes. However, some limitations restrict its widespread usage, such as the requirements for a therapist to be in attendance and for patients to close their eyes during treatment. In such cases, support through immersive Virtual Reality (iVR) during the training procedure may be a suitable solution. In this study, an iVR application was developed for individuals undergoing PMR training, and an experimental design with both independent and subjective measures was conducted to compare this novel approach with conventional PMR training. The study was validated in two population groups: nursing undergraduates (one training session, n=63) and undergraduates following a test anxiety programme (complete training procedure: 7 sessions, n=13). The results pointed to high satisfaction and relaxation levels across all groups. No significant differences were found between the two methodologies, suggesting that the iVR application could be a useful tool in both educational and clinical contexts. In the long experience group (7 sessions), the iVR students showed higher interest which may have contributed to adherence to the entire training procedure. Furthermore, the iVR tool demonstrated potential suitability users unable to follow conventional procedures, exemplified by a student who, due to her own anxiety-related symptoms, felt very uncomfortable when instructed to close her eyes during the relaxation training.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Psychological relaxation techniques are now fundamental in stress-management and anxiety-disorder prevention training. Progressive Muscle Relaxation (PMR) stands out among various other training programmes. However, some limitations restrict its widespread usage, such as the requirements for a therapist to be in attendance and for patients to close their eyes during treatment. In such cases, support through immersive Virtual Reality (iVR) during the training procedure may be a suitable solution. In this study, an iVR application was developed for individuals undergoing PMR training, and an experimental design with both independent and subjective measures was conducted to compare this novel approach with conventional PMR training. The study was validated in two population groups: nursing undergraduates (one training session, n=63) and undergraduates following a test anxiety programme (complete training procedure: 7 sessions, n=13). The results pointed to high satisfaction and relaxation levels across all groups. No significant differences were found between the two methodologies, suggesting that the iVR application could be a useful tool in both educational and clinical contexts. In the long experience group (7 sessions), the iVR students showed higher interest which may have contributed to adherence to the entire training procedure. Furthermore, the iVR tool demonstrated potential suitability users unable to follow conventional procedures, exemplified by a student who, due to her own anxiety-related symptoms, felt very uncomfortable when instructed to close her eyes during the relaxation training.
PID2023-150694OA-I00 funded by MICIU/AEI/ 10.13039/501100011033 and by “ERDF/EU”
Usamos cookies para asegurar que te damos la mejor experiencia en nuestra web. Si continúas usando este sitio, asumiremos que estás de acuerdo con ello.
