A Conceptual Teaching Framework For AI-Ready IoT System Design in TVET Education

The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) is reshaping industry expectations of Technical and Vocational Education and Training (TVET) graduates, who are increasingly required to work with connected, data-driven systems. However, many IoT courses remain component-based, emphasizing sensors, microcontrollers, communication, and dashboards in isolation. While this approach enables students to build functional prototypes, it often limits their understanding of overall system architecture and data readiness for future AI integration.
This paper argues that the key challenge lies not in the absence of AI instruction, but in the way foundational IoT concepts are taught. It proposes a shift toward system-oriented and data-driven IoT education, where AI readiness emerges as a natural outcome of sound system design rather than advanced algorithm training. To support this shift, the paper introduces a conceptual teaching framework consisting of four layers: sensing, connectivity, data readiness, and application intelligence to guide the organization of IoT projects and laboratory activities. The proposed framework offers a practical approach for modernizing TVET IoT courses by promoting structured data generation and system-level thinking, while also providing a foundation for future empirical studies on AIoT learning outcomes.

AI-ready IoT, system-oriented IoT education

1. Burd, B., Barker, L., & Divitini, M. (2018). Peer instruction in computer science and software engineering education. IEEE Transactions on Education, 61(3), 185-191. [Google Scholar] [Crossref]

2. Deckker, D., & Sumanasekara, S. (2025). AI in vocational and technical education: Revolutionizing skill-based learning. EPRA International Journal of Multidisciplinary Research (IJMR), 11(3), 9–23. [Google Scholar] [Crossref]

3. Deng, S., Xiang, H., & Yin, J. (2020). When Internet of Things meets Artificial Intelligence: Opportunities and challenges. International Journal of Web and Grid Services, 16(1), 57-75. [Google Scholar] [Crossref]

4. Frank, M. (2006). Knowledge, abilities, cognitive characteristics and behavioral competences of engineers with high capacity for engineering systems thinking (CEST). Systems Engineering, 9(2), 91-103. [Google Scholar] [Crossref]

5. Hmelo-Silver, C. E., & Azevedo, R. (2006). Understanding complex systems: Some core challenges. Journal of the Learning Sciences, 15(1), 53-61. [Google Scholar] [Crossref]

6. Lawrence, N. D. (2017). Data readiness levels. arXiv preprint arXiv:1705.02245. [Google Scholar] [Crossref]

7. Noor, A. A. M., Hussein, S. S., Mustaffa, M., Lokman, A. M., & Alfiansyah, M. W. (2025). Developing understanding of AI-powered personalized learning concept in TVET institutions. Journal of Technical Education and Training, 17(3), 150–166. [Google Scholar] [Crossref]

8. Sambasivan, N., Kapania, S., Highfill, H., Akter, D., Paritosh, P., & Aroyo, L. M. (2021). "Everyone wants to do the model work, not the data work": Data Cascades in High-Stakes AI. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, 1-15. [Google Scholar] [Crossref]

9. Yoddumnern, A. (2024). Establishing an IoT-vocational learning center: A project to investigate the benefits of emerging technologies. TVET@Asia, (23), 1–21. [Google Scholar] [Crossref]

10. Zhang, Y., Sun, S., & Zheng, M. (2025). Closed loop practice of vocational undergraduate field engineer training in the AIoT era. Educational Innovation Research, 3(6), 108–114. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet