Conference Agenda

This study aimed to analyze the influence of psychosocial factors on the responsible adoption/appropriation of generative AI chatbots among students from public universities in northern Peru using an extended UTAUT2 framework. A quantitative, non-
experimental, cross-sectional design was applied to a sample of 430 students from five departments (Piura, Tumbes, Lambayeque, La Libertad, and Cajamarca), gathered through quota and convenience procedures. Constructs were assessed with adapted Likert-type
reflective indicators and tested through a structural equation model, showing adequate psychometric properties (loadings 0.74–0.91; AVE 0.62–0.80; α 0.84–0.92) and acceptable model fit (SRMR = 0.073; NFI = 0.915; χ²/df = 2.18). All hypotheses were supported: AI learning
self-efficacy emerged as the strongest predictor (β = 0.34; p < 0.001), followed by social influence (β = 0.28; p < 0.001), while performance expectancy, AI readiness/anxiety, perceived enjoyment, and ethical awareness had significant but smaller effects. The findings indicated that
appropriation was driven more by perceived agency and social legitimation than by instrumental usefulness alone. Recommendations emphasized prioritizing training to strengthen self-efficacy and critical AI literacy, complemented by institutional and teaching guidelines to
foster ethical use and reduce anxiety.

The expansion of online education in engineering programs has been accompanied by persistently high failure rates, making data-driven early warning systems urgently needed. This article presents and evaluates a quantitative, interpretable, and reproducible methodological framework for predicting the risk of failing introductory engineering courses delivered online, based on learning analytics obtained from the Learning Management System (LMS) and the academic system. The approach was applied to a group of 200 students and included variables such as platform activity (number of active days, logins, resource views, and submissions); performance at a later stage (cumulative GPA and percentage of assessments submitted); and prior academic performance (GPA and number of course re-enrollments). Supervised logistic regression, random forest, and gradient reinforcement models were compared and evaluated based on AUC, sensitivity, specificity, F1 score, and Brier score. The probabilities of failure were transformed into a risk score (low/medium/high). The best-performing model showed an AUC of 0.84 at week 5 for the logistic regression model and approached 0.90 for gradient boosting with very good calibration. Risk categorization was able to accurately group approximately 60% of all students who ultimately failed into the high-risk category. (This high-risk category represented only about 25% of the cohort.) These results demonstrate the potential operational capability of the early warning system. The framework provides an interpretable tool for faculty and administrators to categorize risk levels in an effort to improve early intervention practices based on student performance data, as well as to enhance data-driven decision-making in the field of virtual engineering education.

The COVID-19 pandemic caused unprecedented disruption in higher education, forcing institutions to rapidly shift from face-to-face instruction to remote learning. At the Technological University of Panama (UTP), this transition highlighted both structural challenges and adaptive practices. A quantitative survey was conducted with 320 participants (210 students, 85 faculty, and 25 administrative staff), using a validated instrument (Cronbach’s α = 0.87) to measure access to technology, digital competencies, teaching–learning processes, and institutional support. Results revealed connectivity limitations among 42% of students, demand for digital-pedagogical training among 68% of faculty, and concerns about assessment overload reported by 54% of students. Despite these constraints, innovative practices such as hybrid course redesign, authentic assessment strategies, and strengthened communication channels fostered resilience. Based on these findings, the study proposes a three-dimensional framework—governance and leadership, pedagogy and assessment, and digital infrastructure with knowledge management—tailored to the Latin American context. This contribution is original in demonstrating how universities with limited resources can institutionalize resilience and hybrid learning as sustainable post-pandemic models, offering transferable lessons for higher education in similar environments.

This paper presents a Python-based simulator for pressure transmitter calibration training, designed to replicate industrial processes with configurable errors (zero offset, span error, random noise, hysteresis). The tool features a multilingual interface (ES/EN/PT), real-time performance analysis, and CSV data export. Theoretical validation against ISA RP25.1 standards confirms its accuracy (±0.5% error). Controlled tests demonstrate its potential to reduce training costs by 60% compared to physical labs.

Artificial intelligence (AI) is both a challenge and an opportunity in today's university education. The development of educational innovations in this area allows us to identify alternatives for incorporating its use in an ethical and responsible manner. This contribution aims to present the experience of implementing an educational innovation based on the integration of AI to enhance research skills in architecture students. To this end, a teaching activity was developed focusing on the use of AI research assistants to search for bibliographic and documentary sources. This activity was applied to two groups of students from the same first-year architecture course at the Technological Institute of Costa Rica. The educational innovation was complemented by an initial diagnosis of the use of AI among some teachers in the program and by conducting questionnaires before and after the educational activity. The main results highlight the need for training for teachers and students in the appropriate use of AI technologies, as well as the importance of using tools that are appropriate to the needs of the discipline.

This study aimed to model and predict the daily maximum solar radiation in the city of Puno (Peru) using meteorological variables associated with extreme temperatures through machine learning techniques. Records obtained from a DAVIS Vantage Pro 2.0 meteorological station were used, covering the period 2017–2024 and comprising 2,060 daytime observations. Three tree-based models were developed: Random Forest, XGBoost, and LightGBM, whose performance was evaluated using error and goodness-of-fit metrics, including root mean square error, mean absolute error, and the coefficient of determination. Exploratory analysis revealed a strong positive correlation between observed solar radiation and extraterrestrial radiation, confirming its role as the main physical forcing of the system. Among the evaluated models, Random Forest achieved the best predictive performance, with a root mean square error of 124.24 W/m², a mean absolute error of 96.50 W/m², and a coefficient of determination of 0.5135, outperforming XGBoost and LightGBM, which obtained coefficients of determination of 0.4482 and 0.3679, respectively. Variable importance analysis consistently identified extraterrestrial radiation and daily thermal amplitude as the most influential predictors. Overall, the results demonstrate that artificial intelligence approaches constitute effective and reliable tools for local solar radiation estimation in high-altitude regions, with potential applications in energy planning, environmental management, and climate studies.