Ferriell, W. D. (2024, June),  Complete Evidence-Based Practice: Analysis of Machine Vision in a First-Year Engineering Project  Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. https://strategy.asee.org/46394

\bibitem{asee_peer_46394}
  Ferriell, W. D. (2024, June), \emph{ Complete Evidence-Based Practice: Analysis of Machine Vision in a First-Year Engineering Project}
  Paper presented at 2024 ASEE Annual Conference \& Exposition, Portland, Oregon.
  https://strategy.asee.org/46394

William Davis Ferriell.  " Complete Evidence-Based Practice: Analysis of Machine Vision in a First-Year Engineering Project".  2024 ASEE Annual Conference & Exposition, Portland, Oregon, 2024, June.  ASEE Conferences, 2024.  https://strategy.asee.org/46394 Internet.  30 Jul, 2024

\bibitem{asee_peer_46394}
  William Davis Ferriell.
  " Complete Evidence-Based Practice: Analysis of Machine Vision in a First-Year Engineering Project".
  \emph{2024 ASEE Annual Conference \& Exposition, Portland, Oregon, 2024, June}.
  ASEE Conferences, 2024.
  https://strategy.asee.org/46394 Internet.  30 Jul, 2024

@INPROCEEDINGS{asee_peer_46394
author = "William Davis Ferriell"
title = " Complete Evidence-Based Practice: Analysis of Machine Vision in a First-Year Engineering Project"
booktitle = "2024 ASEE Annual Conference \& Exposition"
year = "2024"
month = "June"
address = "Portland, Oregon"
publisher = "ASEE Conferences"
note = {https://strategy.asee.org/46394}
}

TY  - CPAPER
AB  - This is a Complete Evidence-based Practice paper submission. Creating a team-based design project for a multi-disciplinary first year engineering class means meeting a variety of constraints and goals.  At the University of Kentucky, projects are required to include content from a variety of engineering disciplines—such as mechanical, electrical, materials and computer science. Projects must also motivate student curiosity and enable students to meet learning objectives required for success in subsequent discipline specific coursework. These projects are designed to require all student team members to perform mathematical modeling to understand design constraints, computer programming, computer aided design, and prototyping to bring design concepts to reality.  Working on the project also allows for professional skills such as practice of team interaction processes, communication skills, and basic project management skills. Another goal in project creation is to give students a design project that addresses aspects of engineering and computer science that: represent recent trends in engineering, are not normally covered in their high school background, are inexpensive to implement, and presents these in a way that is both challenging—yet attainable—to students with a semester or less of MATLAB programming. Machine vision uniquely fit this list of goals.

Vison systems are used by many engineering disciplines in an array of applications. For example, vision systems may be used by: manufacturing engineers for the inspection and monitoring of manufacturing processes; mining engineers for inspecting hazardous areas using remote/autonomous vehicles; biomedical engineers for medical imaging; and biosystems, environmental, and civil engineers for environmental monitoring. The decrease in camera hardware cost brought about by smart phones, the increase in image processing capabilities brought about by a combination of computer hardware improvements, and the rise of machine learning algorithms are opening new machine vision applications in nearly every area of society. Students are familiar with consumer uses for machine vision, such as sorting tomatoes and drones following skateboarders. The universality of machine vision across disciplines is evident to students; thus, the utility value of machine vision-related projects may be motivating to students.

This study seeks to evaluate the efficacy of machine vision-related deliverables as part of a 10-week project in a second semester first year engineering course. Similar to the goals of the first-year engineering sequence, the inclusion of machine vision in first year engineering projects is intended to: increase self-efficacy in first year engineering students by enabling students to learn and apply a new technical skill; improve the motivation of students by emphasizing the utility value of machine vision applications; result in successful student attainment of learning objectives; and result in the completion of successful semester projects. These metrics for success are evaluated by comparing student project submissions and teacher course evaluations from two course sections from the Spring 2023 semester. Additionally, the data presented include an analysis of student performance on project deliverables specific to machine vision which may suggest the attainment—or not—of course learning objectives. The methods may be used by engineering educators to motivate the design of similar activities in their programs. Furthermore, educators may utilize a similar curricular framework to engage students. Future work will investigate the ways in which students later engage with machine vision concepts learned in the first-year program in their major-specific coursework. Additionally, two necessary improvements to the analysis methods are survey specific questions related to the machine vision portion of the projects and the inclusion of data from multiple instructors over multiple academic years, as the conclusions drawn in this study are limited. 
AU  - William Davis Ferriell
CY  - Portland, Oregon
DA  - 2024/06/23
PB  - ASEE Conferences
TI  -  Complete Evidence-Based Practice: Analysis of Machine Vision in a First-Year Engineering Project
UR  - https://strategy.asee.org/46394
ER  -