Integrating Machine Learning Into Activity-Based Learning: A Critical Review Of Emerging Frameworks In Engineering Education

Abstract

Active learning has emerged as a transformative approach in engineering education, emphasizing student-centred pedagogy, real-world problem-solving, and the development of critical and transferable skills. This review critically analyses of the recent studies focusing on Problem-Based Learning (PBL), Project-Based Learning (PjBL), and Collaborative Learning (CL) to evaluate their implementation, strategies, and outcomes in higher engineering education. The review synthesizes methods, tools, and learning environments used to facilitate active learning, highlighting benefits such as enhanced engagement, teamwork, creativity, and conceptual understanding. Key trends include the integration of technology, gamification, and interdisciplinary projects to foster self-directed learning. Limitations identified include small sample sizes, contextual constraints, and lack of longitudinal evidence on long-term skill retention. The review identifies research gaps related to scalability, instructor preparedness, and curriculum-wide applications, offering insights for future studies and practical recommendations for optimizing active learning approaches in engineering programs.