ADMIRABLE

@article{Miguel-Alonso2025,

title = {Identifying users of immersive virtual-reality serious games through machine-learning techniques},

author = {Ines Miguel-Alonso and Juan J. Rodríguez and Ana Serrano-Mamolar and Andres Bustillo},

doi = {10.1007/s10055-025-01232-y},

issn = {1434-9957},

year  = {2025},

date = {2025-12-00},

urldate = {2025-12-00},

journal = {Virtual Reality},

volume = {29},

number = {4},

publisher = {Springer Science and Business Media LLC},

abstract = {<jats:title>Abstract</jats:title>

          <jats:p>User identification is currently an open issue in immersive Virtual Reality (iVR) environments. Three main goals are usually associated with the use of tracking-data and Machine-Learning (ML) techniques: safeguarding privacy, user authentication, and user-experience customization. However, research to date has only involved very limited recordings of user data (<jats:italic>e</jats:italic>.<jats:italic>g</jats:italic>., on a single session and for low-interactive situations), rare in real iVR environments. So, the research gap between real iVR data and ML techniques for user identification is addressed in this paper. To do so, a 3-session iVR experience of operating a bridge crane is considered. In this simple yet highly interactive learning action, the dataset records of user performance show rapid changes between one experience and another. Eye, head, and hand movements of 64 users of similar age and with comparable previous experience were all recorded while engaged with the experience. The final raw dataset had a size of approximately 50 M data points with 25 attributes that were mainly temporal series values. Secondly, different ML algorithms were used for user identification: Decision Tree, Random Forest, XGBoost, k-Nearest Neighbors, Support Vector Machines, and Multilayer Perceptron. The results showed that ML ensemble learning techniques, particularly Random Forest, were the most suitable solutions on the basis of different measures for the prediction of user identity. Additionally, the inclusion of stress and no-stress conditions significantly enhanced model performance, highlighting the importance of data diversity. Temporal segmentation revealed that user identification during later phases of the exercise was slightly more effective, due to increased individual variability. Finally, a minimum duration of the iVR experience was identified as a requirement to assure high identification rates.</jats:p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{maestro-prieto2025,

title = {Semi-supervised techniques to address the scarcity of experimental data: a case study of single point incremental forming},

author = {José Alberto Maestro-Prieto and Pablo E. Romero and José Miguel Ramírez Sanz},

url = {https://doi.org/10.1007/s10845-025-02704-3},

doi = {10.1007/s10845-025-02704-3},

issn = {0956-5515},

year  = {2025},

date = {2025-10-31},

urldate = {2025-10-31},

journal = { Journal of Intelligent Manufacturing},

abstract = {A lack of experimental data can be especially critical in new manufacturing processes. Although experimental datasets for industrial processes are reported in various research works, their lack of homogeneity complicates any fitting with conventional numerical models. Artificial Intelligence (AI) models can be an optimal alternative to extract useful information from those unconnected datasets, while generating models that can help explain the hidden patterns within datasets and interpret the predictions of the model for final users. Moreover, an AI algorithm that could be trained with limited labeled datasets would be in high demand, as it could effectively lower implementation costs. Semi-Supervised Learning (SSL) techniques might therefore be a promising solution to respond to industrial demand for the analysis of manufacturing processes. In this research, the use of SSL techniques is proposed in a case study of surface quality prediction in single point incremental forming, a promising new manufacturing technique. Datasets were extracted from the existing bibliography to generate a 234-instance dataset with 4 different industrial specifications of roughness. The best results were obtained using a semi-supervised Co-Training algorithm. Semi-supervised methods systematically improved the results obtained with the reference supervised methods, although statistical significance has not been mainly achieved due to the limited dataset size. The results obtained with the unbalanced dataset were very promising for its industrial implementation with an extended training dataset optimized for the range of process conditions of each end-user.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{maestro-prieto2025b,

title = {Semi-supervised tapping wear detection in nodular cast-iron workpieces under real industrial condition},

author = {José Alberto Maestro-Prieto and Alain Gil-Del-Val and Andrés Bustillo},

url = {https://link.springer.com/article/10.1007/s00170-025-16491-x},

doi = {10.1007/s00170-025-16491-x},

issn = {0268-3768},

year  = {2025},

date = {2025-09-19},

urldate = {2025-09-19},

journal = {International Journal of Advanced Manufacturing Technology },

abstract = {The tapping of metal components is a manufacturing task with great potential for automation, because the conditions affecting the industrial components are of limited variability. However, automation encounters two main problems: both the human- and the time-related costs associated with the manual classification of threads are excessive, and thread quality can vary greatly, due to tapping tool wear. In this study, the use of semi-supervised algorithms is proposed to improve the performance of machine learning–based models trained on real industrial datasets. The strategy was validated on a dataset of more than 7000 threads produced with 36 different tapping tools under the same working conditions involving nodular cast iron workpieces. Several algorithms were trained using datasets with different features and data processing. The best results were obtained with datasets using linear regression in which sinusoidal fluctuations in the raw signals were replaced by linear regressions and the slope of an 11-element rolling window was applied to extend the raw dataset. Algorithms were trained with different percentages of labeled datasets. The co-training-based algorithms almost systematically obtained the best results, yielding better results than the reference algorithms using a 100% labeled dataset. Besides, the proposed solution also achieved higher performance with 50% of labeled instances in the training dataset, drastically reducing the costs of manual labeling for that sort of industrial dataset.},

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}

}

@article{martineez-sanllorente2025,

title = {InvIPM: Toolbox for segmentation optimization of images of metallic objects using illumination-invariant transforms},

author = {Jonás Martínez-Sanllorente and Carlos López-Nozal and Pedro Latorre-Carmona and Raúl Marticorena-Sánchez},

editor = {ELSEVIER},

url = {https://www.sciencedirect.com/science/article/pii/S2352711025001669?via%3Dihub},

doi = {10.1016/J.SOFTX.2025.102199},

issn = {2352-7110},

year  = {2025},

date = {2025-06-02},

urldate = {2025-06-02},

journal = {SoftwareX},

volume = {31},

pages = {102199},

abstract = {The automation of industrial quality control based on artificial (computer) vision can avoid some of the problems associated with tedious and repetitive manual procedures that will often originate operator errors. Automatic quality control can also be applied uninterruptedly. However, strategies of that sort have some drawbacks. One is associated with image acquisition under controlled illumination conditions. The material characteristics of an object for analysis will also influence the final result. For example, the illumination of metallic objects or objects with metallic finishes will generate specular reflection and shadow, which must be minimized. The illumination effect on subsequent processing stages may be analysed by applying segmentation techniques (based, for instance, on clustering strategies), to identify the number of objects. In this study, a MATLAB desktop application for image processing was developed, where illumination-invariant transforms were applied prior to image segmentation, to improve the quality of segmentation results. A set of illumination-invariant transforms and clustering-based segmentation methods were applied and the segmentation quality (if there was a groundtruth image) was quantified. The experimental results obtained with 4 illumination-invariant algorithms, 4 clustering-based segmentation algorithms, and 29 images of metal parts acquired by factory operators and manually segmented by researchers, demonstrated significant improvement to image segmentation following the application of illumination-invariant transforms.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rodriguez-garcia2025,

title = {LoDCalculator: A level of detail classification software for 3D models in the Blender environment},

author = {Bruno Rodriguez-Garcia and Ines Miguel-Alonso and Henar Guillen-Sanz and Andres Bustillo},

url = {https://doi.org/10.1016/j.softx.2025.102107},

doi = {10.1016/j.softx.2025.102107},

issn = {2352-7110},

year  = {2025},

date = {2025-02-19},

urldate = {2025-02-19},

journal = {SoftwareX},

volume = {30},

pages = {102107},

abstract = {The use of Level of Detail (LoD), a crucial technique in the development of 3D models, implies lower cost graphics and resource economies. These savings are evident in contexts where technical resources are limited, such as immersive Virtual Reality and whenever LoD is critical for accurate representation, such as Cultural Heritage dissemination. Consequently, various systems are used to classify 3D models based on their LoD. However, those systems have several shortcomings that hinder their widespread use. In this research, LoDCalculator, an add-on for Blender open-source modelling software, is presented to address such shortcomings. LoDCalculator ensures unambiguous, universal, and accessible classification of 3D models. It was tested by classifying 12 3D models. The scores were then compared with the evaluations of a group of students and professional 3D modelers in a subjective evaluation. The results of the comparison were satisfactory, showing minimal significant differences between the software and the evaluation group classifications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Garrido-Labrador2025,

title = {SSLearn: A Semi-Supervised Learning library for Python},

author = {José L. Garrido-Labrador and Jesús M. Maudes-Raedo and Juan J. Rodríguez and César I. García-Osorio},

doi = {10.1016/j.softx.2024.102024},

issn = {2352-7110},

year  = {2025},

date = {2025-02-00},

urldate = {2025-02-00},

journal = {SoftwareX},

volume = {29},

publisher = {Elsevier BV},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{marticorena2025,

title = {Unveiling the Differences in Early Performance Prediction Between Online Social Sciences and STEM Courses Using Educational Data Mining},

author = {Raúl Marticorena-Sánchez and Antonio Canepa-Oneto and Carlos López-Nozal and José A. Barbero-Aparicio},

editor = {Wiley},

url = {https://doi.org/10.1111/exsy.13837

https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.13837},

doi = {10.1111/exsy.13837},

year  = {2025},

date = {2025-01-20},

journal = {Expert Systems},

volume = {42},

number = {3},

pages = {e13837},

abstract = {Educational Data Mining and Learning Analytics in virtual environments can be used to diagnose student performance problems at an early stage. Information that is useful for guiding the decisions of teachers managing academic training, so that students can successfully complete their course. However, student interaction patterns may vary depending on the knowledge domain. Our aim is to design a framework applicable to online Social Sciences and STEM courses, recommending methods for building accurate early performance prediction models. A large-scale comparative study of the accuracy of multiple classifiers applied to classify the interaction logs of 32,593 students from 9 Social Sciences and 13 STEM courses is presented. Corroborating the results of other works, it was observed that high early performance prediction accuracy was obtained based on nothing other than student logs: accuracies of 0.75 in the 10th week, 0.80 in the 20th week, 0.85 in the 30th week and 0.90 in the 40th week. However, accuracy rates were observed to vary significantly, in relation to the classification algorithm and the knowledge domain (Social Sciences vs. STEM). These predictions are generally less accurate for Social Sciences compared to STEM courses, especially at the beginning of the course, with fewer differences observed in the final weeks. Additionally, this research identifies instances of low-accuracy outliers in the prediction of Social Sciences courses over time. These findings highlight the complex challenges and variations in early performance prediction across different domains in online education.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Guillen-Sanz2025,

title = {Can Immersive Virtual Reality Environments Improve Stress Reduction? Experimental Design With Progressive Muscle Relaxation Training},

author = {H. Guillen-Sanz and M. C. Escolar-Llamazares and I. Quevedo Bayona and M. A. Martínez-Martín and A. Bustillo},

doi = {10.1109/access.2025.3579493},

issn = {2169-3536},

year  = {2025},

date = {2025-01-13},

urldate = {2025-00-00},

journal = {IEEE Access},

volume = {13},

pages = {104312--104329},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}