Empirical study on the efficacy of engineering education via an AI-driven adaptive learning environment for architectural structural analysis

Abstract

The advent of artificial intelligence (AI) has seen burgeoning applications in architectural structural analysis, ushering in both opportunities and complexities for engineering education. Emphasis has recently been placed on adaptive learning environments, which are posited to augment student outcomes and satisfaction, especially in complex engineering domains. Notwithstanding this shift, a considerable fraction of the scholarly discourse on adaptive learning is rooted in conventional educational paradigms, with scant attention to the fusion of fuzzy extreme learning machine (ELM) techniques for analysis and prediction, or the employment of knowledge maps and spaces for streamlined adaptive learning systematization. This study aims to address this lacuna, delving into the efficacy analysis of engineering education, underpinned by fuzzy ELM. Methodologies for sculpting adaptive learning atmospheres using knowledge structures, such as maps and spaces, are also examined, suggesting refined and precise pedagogical strategies for the field. An innovative adaptive learning environment framework specifically designed for the field of engineering education is proposed through the fusion of the predictive analytics capabilities of fuzzy ELM and the efficient construction strategies of knowledge maps and spaces. This research outcome not only furnishes the engineering education sector with an inventive teaching strategy but also significantly enhances learning outcomes and student satisfaction through the optimization of highly personalized learning paths. Its profound impact is manifested in providing educators with a scientific, data-driven decision-making tool, enabling them to predict and respond to students’ learning needs more accurately, thereby fostering engineers with greater innovation capacity and practical skills in the complex environment of engineering education. This study not only propels the development of educational technology but also offers students a more personalized, efficient, and dynamic learning experience, promising to substantially elevate teaching quality and learning effectiveness in the engineering domain.