Abstract:

In modern STEM education, the increasing integration of digital technologies, including screen-based learning and immersive environments such as virtual reality, introduces new challenges related to student cognitive load and adaptability. While traditional educational approaches focus on performance outcomes, the introduction of modern technologies provides a new horizon for adaptive and personalized learning. The study of dynamic physiological responses of students and their ability to adapt to different levels of cognitive demand and technological complexity has been insufficiently studied so far.

The present study proposes a new interdisciplinary framework for modeling student adaptability using heart rate variability (HRV) digital twins. The concept of a digital twin enables the creation of a dynamic physiological representation of each student, allowing for continuous tracking and analysis of individual responses to cognitive load and different learning environments.

The proposed approach integrates real-time physiological data collection via wearable devices with HRV-based modeling to characterize each student’s individual response to new learning technologies. Students are observed during various STEM educational scenarios, including screen-based tasks and technologically enhanced environments, such as virtual and augmented reality. Physiological responses are analyzed over time to identify patterns of adaptation, resilience, and sensitivity to increased cognitive load.

The methodology focuses on assessing how students adapt to repeated or prolonged exposure to immersive technologies. By analyzing temporal changes in physiological indicators, the approach explores adaptive physiological regulation. This allows for a deeper insight into individual learning capacity and tolerance to complex or technology-rich educational settings.

The results show that students exhibit different adaptive profiles, with some individuals showing stable physiological regulation under increased cognitive load, while others show signs of overload and reduced adaptability. Furthermore, immersive and screen-based learning environments lead to measurable differences in physiological responses, highlighting the need for personalized approaches in technology-enhanced education.

From an educational perspective, the proposed digital twin framework provides a powerful tool for understanding learner variability and supports the development of adaptive, personalized, and human-centered learning environments. This allows educators to design learning experiences that are tailored to students’ physiological and cognitive abilities, especially in STEM contexts characterized by high complexity.

The main contribution of this study lies in introducing HRV-based digital twins as a new paradigm for modeling student adaptability in educational settings, bridging the gap between physiological observation and learning analytics. The approach goes beyond static assessment and offers a dynamic and predictive framework for optimizing learning processes.

The integration of wearable IoT technologies and HRV digital twins represents a promising direction for the development of adaptive and intelligent STEM education, providing new opportunities to increase both learning effectiveness and student well-being in increasingly digitalized learning environments.

Keywords:

Digital twins, STEM education, adaptability, cognitive load.