Non-pathological mental fatigue is a recurring, but undesirable condition among people in the fields of office work, industry, and education. This type of mental fatigue can often lead to negative outcomes, such as performance reduction and cognitive impairment in education; loss of focus and burnout syndrome in office work; and accidents leading to injuries or death in the transportation and manufacturing industries. Reliable mental fatigue assessment tools are promising in the improvement of performance, mental health and safety of students and workers, and at the same time, in the reduction of risks, accidents and the associated economic loss (e.g., medical fees and equipment reparations). The analysis of biometric (brain, cardiac, skin conductance) signals has proven to be effective in discerning different stages of mental fatigue; however, many of the reported studies in the literature involve the use of long fatigue-inducing tests and subject-specific models in their methodologies. Recent trends in the modeling of mental fatigue suggest the usage of non subject-specific (general) classifiers and a time reduction of calibration procedures and experimental setups. In this study, the evaluation of a fast and short-calibration mental fatigue assessment tool based on biometric signals and inter-subject modeling, using multiple linear regression, is presented. The proposed tool does not require fatigue-inducing tests, which allows fast setup and implementation. Electroencephalography, photopletismography, electrodermal activity, and skin temperature from 17 subjects were recorded, using an OpenBCI helmet and an Empatica E4 wristband. Correlations to self-reported mental fatigue levels (using the fatigue assessment scale) were calculated to find the best mental fatigue predictors. Three-class mental fatigue models were evaluated, and the best model obtained an accuracy of 88% using three features, $\beta /\theta$ (C3), and the $\alpha /\theta$ (O2 and C3) ratios, from one minute of electroencephalography measurements. The results from this pilot study show the feasibility and potential of short-calibration procedures and inter-subject classifiers in mental fatigue modeling, and will contribute to the use of wearable devices for the development of tools oriented to the well-being of workers and students, and also in daily living activities.

New trends on brain-computer interface (BCI) design are aiming to combine this technology with immersive virtual reality in order to provide a sense of realism to its users. In this study, we propose an experimental BCI to control an immersive telepresence system using motor imagery (MI). The system is immersive in the sense that the users can control the movement of a NAO humanoid robot in a first person perspective (1PP), i.e., as if the movement of the robot was his/her own. We analyze functional brain connectivity between 1PP and 3PP during the control of our BCI using graph theory properties such as degree, betweenness centrality, and efficiency. Changes in these metrics are obtained for the case of the 1PP, as well as for the traditional third person perspective (3PP) in which the user can see the movement of the robot as feedback. As proof-of-concept, electroencephalography (EEG) signals were recorded from two subjects while they performed MI to control the movement of the robot. The graph theoretical analysis was applied to the binary directed networks obtained through the partial directed coherence (PDC). In our preliminary assessment we found that the efficiency in the α brain rhythm is greater in 1PP condition in comparison to the 3PP at the prefrontal cortex. Also, a stronger influence of signals measured at EEG channel C3 (primary motor cortex) to other regions was found in 1PP condition. Furthermore, our preliminary results seem to indicate that α and β brain rhythms have a high indegree at prefrontal cortex in 1PP condition, and this could be possibly related to the experience of sense of agency. Therefore, using the PDC combined with graph theory while controlling a telepresence robot in an immersive system may contribute to understand the organization and behavior of brain networks in these environments.

Understanding the neural mechanisms underlying interest in Science, Technology, Engineering, and Mathematics (STEM) and learning is crucial for fostering creativity and problem-solving skills, key drivers of technological and educational growth. Traditional methods of assessing STEM interest are often limited by cultural and human biases, highlighting the need for more objective approaches. This study utilizes Electroencephalography (EEG) to identify neural markers linked to STEM interest and course-specific cognitive demands in young learners enrolled in a specialized private STEM program, including courses such as 3D Design, Programming, and Robotics. Specifically, Power Spectral Density (PSD) and Functional Connectivity (FC) were analyzed within theta, alpha, and beta frequency bands, which are associated with performance monitoring, creativity, and executive functioning. The findings reveal a significant negative correlation between STEM interest and brain activity in the frontal (F3, F4) and prefrontal regions (FP1, FP2) in the theta (r = -0.44, p = 0.2732; r = -0.77, p = 0.0268; r = -0.84, p = 0.0096; r = -0.62, p = 0.0990) and beta bands (r = 0.43, p = 0.2843; r = -0.56, p = 0.1524; r = -0.83, p = 0.0110; r = -0.75, p = 0.0328), indicating engagement in working memory and executive processing. Additionally, course-specific brain activity patterns reveal that Robotics is characterized by denser long-range FC networks, associated with problem-solving, while 3D Design exhibits more sparse yet efficient networks, indicative of creative ideation. A consistent beta band FC pattern between central and left-frontal areas reflects cognitive synchronicity and lateralization. These findings contribute to understanding the neurocognitive markers involved in STEM interest and learning, offering a framework for assessing and fostering engagement in STEM education through objective, neuroscience-based approaches.

Data analysis and machine learning have become essential cross-disciplinary skills for engineering students and professionals. Traditionally, these topics are taught through lectures or online courses using pre-existing datasets, which limits the opportunity to engage with the full cycle of data analysis and machine learning, including data collection, preparation, and contextualization of the application field. To address this, we designed and implemented a learning activity that involves students in every step of the learning process. This activity includes multiple stages where students conduct experiments to record their own electroencephalographic (EEG) signals and use these signals to learn data analysis and machine learning techniques. The purpose is to actively involve students, making them active participants in their learning process. This activity was implemented in six courses across four engineering careers during the 2023 and 2024 academic years. To validate its effectiveness, we measured improvements in grades and self-reported motivation using the MUSIC model inventory. The results indicate a positive development of competencies and high levels of motivation and appreciation among students for the concepts of data analysis and machine learning.