2026 ASEE Annual Conference & Exposition

Adaptive Application for Enhancing Feedback in Teaching

Presented at Electrical and Computer Engineering Division (ECE) Technical Session 11

Advancements in artificial intelligence (AI) are transforming engineering education by enabling adaptive and data-driven assessment methods. This paper presents an AI-assisted rubric-based feedback framework designed to enhance learning and evaluation across core Electrical Engineering subjects, including Circuits, Electrical Machines, and Power Systems. The proposed system utilizes natural language processing (NLP) and machine learning techniques to interpret student submissions such as lab reports, design explanations, or numerical problem-solving steps and automatically evaluate them against predefined rubrics. The AI module provides instant, criterion-specific feedback aligned with learning objectives, helping students identify conceptual misunderstandings and improve performance iteratively. Each interaction is logged to build an error database, allowing instructors to analyze trends and target recurring learning gaps. Case studies, including Thevenin’s theorem in Circuits and single-phase transformer tests in Machines, demonstrate measurable improvements in student self-correction, conceptual understanding, and laboratory efficiency. The integration of AI-based rubrics and analytics offers a scalable approach to personalized learning, reduces instructor intervention time, and supports continuous improvement in engineering pedagogy.

Authors
  1. Dr. Theresa Odun-Ayo Missouri University of Science and Technology [biography]
  2. Dr. SHRUTI PANDEY Missouri University of Science and Technology [biography]
Download paper (425 KB)

Are you a researcher? Would you like to cite this paper? Visit the ASEE document repository at peer.asee.org for more tools and easy citations.