2026 ASEE Annual Conference & Exposition

Work in Progress: Survey-Based Insights into Engineering Student Design Tendencies

Presented at Design in Engineering Education Division (DEED) Postcard Technical Session

Understanding how students engage with design processes and problem-solving is a critical area of research in engineering design and education. Existing studies have explored cognitive tendencies, problem-solving strategies, and predictive modeling in educational contexts to enhance instructional methods. Prior research highlights the use of machine learning to predict student grades and learning styles, which can inform data-driven approaches to curriculum design. Building upon this work, the present study focuses on collecting survey data from students regarding their cognitive tendencies and prior experiences. This dataset provides a foundation for developing and validating predictive models that aim to capture how students’ design approaches align with their responses and observed behaviors in structured design tasks. The study establishes a survey-based method for identifying design process tendencies. Data were collected from 220 engineering students enrolled in a sophomore-level, design-focused course. This poster presents the survey results, discusses their implications, and outlines how they inform ongoing research. Future work will explore different types of predictive models—including regression, classification, and hybrid approaches—compare predicted versus observed design behaviors and examine broader implications for engineering education and curriculum design.

Authors

Mr. James Fletcher Shetter III Florida Polytechnic University [biography]

James Shetter is a Master’s student in Mechanical Engineering at Florida Polytechnic University and also earned his BS in Electrical Engineering. His research focuses on engineering education, design cognition, and the application of machine learning to understand and predict student design behaviors. His work centers on developing predictive frameworks that leverage survey-based constructs, such as cognitive style, self-efficacy, and risk propensity, to model how students approach and execute engineering design tasks.
Dr. Apurva Patel http://orcid.org/0009-0002-5860-5267 Florida Polytechnic University [biography]

Apurva Patel is an Assistant Professor of Mechanical Engineering at Florida Polytechnic University. He earned his BS in Mechanical Engineering from Clemson University. He also completed his graduate studies at Clemson University, earning his MS in Mechanical Engineering (modeling behavior in function structures) in May 2018, and his PhD in Mechanical Engineering (individual differences in function modeling) in August 2021. Apurva’s research interests include human behavior in engineering design (system modeling and interpretation, influence of individual differences, and collaboration in engineering teams), manufacturing automation and assembly behaviors, graph-based complexity analysis of products and systems, and prediction using artificial neural networks. In particular, his current explorations are focused on modeling student design approach using machine learning, and understanding the effects of AI integration in the design process on human designers.

Download paper (557 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.

» Download paper

« View session