Conference Agenda

This paper analyses a Global Shared Learning Classroom (GSL) experience developed between undergraduate students from the Dominican Republic and Puebla, Mexico, focused on collaborative research into the relevance of different vitamins for human health. The study was implemented as a pilot quasi-experimental design, integrating international collaborative learning, digital tools, and regulated artificial intelligence support as part of a structured pedagogical architecture. The intervention was articulated through the Dynamic Table for Research and Dissemination (TABDIM), used to organize, systematize, and synthesize the scientific information generated by binational teams. Students analyzed various vitamins considering physicochemical properties, biochemical functions, health implications, food sources, and practical applications. To support the research process, the specialized chatbot Albiomim was integrated as a cognitive scaffolding tool for consultation and conceptual clarification. The outcomes of the collaborative work were presented through a dynamic digital poster within an immersive virtual environment accessible via avatars, complemented by a reflective phase supported by the Padlet platform. Quantitative analysis of the results revealed a significant increase in conceptual learning, with mean scores rising from 65.68 to 78.18, along with a strong positive correlation between pre- and post-intervention results (r = 0.8006). Overall, the findings suggest that the intentional and structured integration of international collaboration, experiential learning, digital tools, and artificial intelligence contributes positively to conceptual learning, student engagement, and the overall learning experience in science courses for engineering education, providing relevant evidence for the design of innovative learning environments in higher education.

Communication barriers between deaf, nonverbal individuals and hearing people remain significant across various aspects of daily life. This article introduces an application for translating individual hand signs from the alphabet, based on the Puerto Rican Sign Language, into written text, as well as converting spoken language into text through speech recognition technologies. By integrating both gesture-based and voice-based input, the system promotes inclusive communication, especially in educational settings. Its main objective is to reduce communication barriers by offering an intuitive, real-time platform accessible through a standard webcam and microphone. The sign recognition process is based on the use of Artificial Intelligence techniques. The selected architecture combined the strengths of Multi-Layer Perceptron (MLP) and Multi-Layer Perceptron (MLP), allowing the system to learn both spatial patterns from individual frames and temporal dependencies across gesture sequences. To provide users with an accessible and real-time translation experience, a web application was developed using Django, a Python web framework. The system achieved an accuracy exceeding 84%, demonstrating its capacity to recognize both static and dynamic hand gestures with high reliability.

Mature heavy oilfields in the Northern Peruvian Jungle have produced oil for over 40 years under waterdrive mechanism, with a wide range of ultimate recovery factor in between 10% to 60%; a reasonable estimation of recovery factor at an early stage of development and/or production is quite critical for sizing and scheduling development plans, as well as CAPEX investments.

This research article introduces a new approach that integrates empirical correlations, analytical methods and machine learning algorithms to estimate oil recovery factor in water-drive sandstone reservoirs at early development and production.

Preliminary studies showed that the most representative reservoir and fluid parameters, such as reservoir size, porosity, permeability, net thickness, residual oil saturation, API gravity, oil viscosity and initial pressure, which are typically measured during the exploration, appraisal and early development stages, can be correlated to expected recovery factors obtained from mature fields with long production history.

Literature empirical correlations will be initially tested with available information of oilfields of Marañón Basin to estimate correlation coefficient. Different regression ML learning algorithms will be compared using existing data to select the best one providing the most precise predictions. A new empirical correlation that significantly outperforms traditional industry equations will be adjusted with ML algorithms weights and biases.

The results of this comprehensive study will contribute to a better understanding of the water drive mechanism in the oilfields of the Northern Peruvian Jungle, as well as a more reliable Recovery Factor and EUR estimations at early development stages.

This study analyzes the influence of artificial intelligence (AI) on the academic motivation of Peruvian university students, in a context of educational transformation aimed at strengthening retention and academic success. The research was conducted using a quantitative approach and a quasi-experimental design. A non-probabilistic, intentional sample of 180 students was used. Validated instruments (α=0.92) were employed, and an intervention based on the use of generative and analytical AI tools such as ChatGPT, Gemini, and GeoGebra was implemented to promote autonomous learning and self-regulation. The results revealed a significant increase in motivation in the experimental group (76.1%) compared to the control group (13.3%), confirmed by Student's t-test (p< 0.001) and Wilcoxon's t-test (Z=-6.45; p<0.001). These findings demonstrate the potential of AI as an innovative pedagogical resource for fostering intrinsic motivation and student retention, providing useful evidence for strengthening institutional strategies and national programs aimed at improving quality, equity, and innovation in higher education.