Enhancing Calculus Learning Outcomes for Engineering Students through the ADAB Framework and AI Tools

Mastering calculus is vital for engineering students, yet many struggle due to inadequate basic mathematical knowledge. Weaknesses in mastering the theory and basic concepts of mathematics significantly hinder calculus learning outcomes, as evidenced by a clear positive relationship between basic mathematics proficiency and calculus achievement. Common failure factors include an inability to understand question requirements or translate them into appropriate calculations, alongside fundamental conceptual gaps that negatively impact topics like differentiation. To address these challenges, this study explores an innovative pedagogical intervention combining the ADAB framework with AI-assisted learning technologies like NotebookLM. The primary objective is to evaluate how integrating structured frameworks and AI tools can minimize conceptual errors, bridge foundational gaps, and improve overall performance in calculus courses. The methodology implements a blended learning design utilizing the ADAB framework to structure student engagement, supported by NotebookLM to provide personalized, interactive guidance and targeted practice on complex calculus topics. Preliminary findings indicate that integrating these AI-driven tools enhances students' comprehension of mathematical rules and significantly reduces procedural errors. Ultimately, these results demonstrate that combining structured pedagogical frameworks with modern AI technologies can transform calculus education, offering educators scalable strategies to cultivate deeper analytical skills and support academic success across engineering disciplines.

Mathematics anxiety, ADAB framework, AI tools, blended learning, mathematics education.

1. Pekrun, R., Stephens, E. J., & Fraser, J. (2025). Impact of math anxiety and general anxiety on academic achievement: An integration of control-value theory and stress models. Journal of Educational Psychology, 117(2), 210–224. [Google Scholar] [Crossref]

2. Robinson, T., Shoitan, M., Molina, R., & Medina, A. (2026). Source-grounded AI and learner autonomy in higher education: A NotebookLM case study. Journal of Artificial Intelligence in Education, 14(3), 89–104. [Google Scholar] [Crossref]

3. Salinas Frencia, J. (2025). NotebookLM: An LLM with RAG for active learning and collaborative tutoring in STEM. ResearchGate Preprint, doi:10.13140/RG.2.2.39077.2640. [Google Scholar] [Crossref]

4. Smith, K., & Peterson, L. (2025). Transforming STEM education: A case study on the pedagogical implementation of Google's NotebookLM. International Journal of EdTech Innovation, 8(4), 312–327. [Google Scholar] [Crossref]

5. Sobel, M., & Sarmiento, L. (2025). Mathematical anxiety’s mediating significance in the relationship between self-efficacy and mathematical efficiency. International Journal of Research and Innovation in Social Science, 9(8), 1142–1155. [Google Scholar] [Crossref]

6. Taylor, H., & Evans, M. (2025). Understanding mathematics anxiety: The role of social-emotional skills and perceived lesson quality. Cogent Education, 12(1), 2609386. [Google Scholar] [Crossref]

7. Uzun, A., & Hoxha, B. (2026). Latent profiles of perfectionism and mathematics anxiety among university students. Higher Education Research & Development, 45(4), 712–729. [Google Scholar] [Crossref]

8. Zhao, Y., & Wang, L. (2026). Mathematics anxiety and its impact on students' learning outcomes: A comprehensive meta-analysis review (2014–2024). Educational Review, 78(1), 45–62. [Google Scholar] [Crossref]

• Interplay of Students’ Emotional Intelligence and Attitude toward Mathematics on Performance in Grade 10 Algebra
• Numerical Simulation of Fitzhugh-Nagumo Dynamics Using a Finite Difference-Based Method of Lines
• Fixed Point Theorem in Controlled Metric Spaces
• Usage of Moving Average to Heart Rate, Blood Pressure and Blood Sugar
• Exploring Algebraic Topology and Homotopy Theory: Methods, Empirical Data, and Numerical Examples