abstract
- This study explores the integration of artificial intelligence (AI) in modeling pollutant particle behavior within the Modeling of Motion in Bioengineering and Chemical Processes course for first-semester engineering students at XX. The methodology builds upon principles of kinematics and dynamics to analyze the movement of airborne particles (PM 10 and PM 2.5) emitted from point sources. The project follows a constructivist and project-based learning approach, where students design and build prototypes to simulate these physical phenomena, comparing experimental and control conditions. Two student groups participated in the study: an experimental group, which incorporated AI-assisted predictive modeling tools to enhance analysis, and a control group, which employed traditional methods without AI intervention. The evaluation encompassed both conceptual understanding (measured through pre- and post-tests) and cognitive engagement (assessed via student self-reports and instructor observations). Findings indicate that students in the AI-assisted group demonstrated a deeper comprehension of complex motion dynamics, particularly in predicting emergent particle behavior patterns. However, the study acknowledges that long-term retention and transferability of competencies require further longitudinal assessment. The results contribute to the broader discourse on AI-enhanced learning in engineering education, providing insights into its potential for augmenting analytical skills and problem-solving capabilities. Future research will examine the scalability and adaptability of this approach in different STEM disciplines to refine its pedagogical effectiveness. © 2025 IEEE.