<![CDATA[This study aims to optimize Internet of Things-based hands-on learning using a multi-objective approach with Non-dominated Sorting Genetic Algorithm II and Reference Point–based Non-dominated Sorting Genetic Algorithm II. The optimization targets three objectives: learning efficiency, learner engagement, and practical skill improvement. A modeling-based approach is employed, and simulations are conducted to evaluate the effects of key parameters, including the number of Internet of Things devices, practicum duration, and task complexity, on learning outcomes. The results show that Reference Point–based Non-dominated Sorting Genetic Algorithm II achieves higher learning efficiency (0.571) and learner engagement (0.090), producing more balanced solutions across objectives, whereas Non-dominated Sorting Genetic Algorithm II performs better on skill improvement (0.184), particularly for high-complexity tasks. Pareto front visualizations illustrate the distribution of optimal solutions, with Reference Point–based Non-dominated Sorting Genetic Algorithm II demonstrating faster convergence and more consistent solution quality. This study contributes to the design of more efficient, effective, and adaptive Internet of Things-based learning models and provides guidance for educational institutions in selecting optimization methods aligned with specific learning priorities.]]>
Copyrights © 2026
