Stone, J. E., & Milner, F., & Guicheteau, A. (2024, July), Full Paper: A Cloud-Based Approach to Introducing Machine Learning in Project-Based Learning Environments  Paper presented at 15th Annual First-Year Engineering Experience Conference (FYEE), Boston, Massachusetts. 10.18260/1-2--48595

\bibitem{asee_peer_48595}
  Stone, J. E., \& Milner, F., \& Guicheteau, A. (2024, July), \emph{Full Paper: A Cloud-Based Approach to Introducing Machine Learning in Project-Based Learning Environments}
  Paper presented at 15th Annual First-Year Engineering Experience Conference (FYEE), Boston, Massachusetts.
  10.18260/1-2--48595

Joshua Eron Stone, Forrest Milner, and Abigail Guicheteau.  "Full Paper: A Cloud-Based Approach to Introducing Machine Learning in Project-Based Learning Environments".  15th Annual First-Year Engineering Experience Conference (FYEE), Boston, Massachusetts, 2024, July.  ASEE Conferences, 2024.  https://peer.asee.org/48595 Internet.  22 Jan, 2025

\bibitem{asee_peer_48595}
  Joshua Eron Stone, Forrest Milner, and Abigail Guicheteau.
  "Full Paper: A Cloud-Based Approach to Introducing Machine Learning in Project-Based Learning Environments".
  \emph{15th Annual First-Year Engineering Experience Conference (FYEE), Boston, Massachusetts, 2024, July}.
  ASEE Conferences, 2024.
  https://peer.asee.org/48595 Internet.  22 Jan, 2025

@INPROCEEDINGS{asee_peer_48595
author = "Joshua Eron Stone, Forrest Milner, and Abigail Guicheteau"
title = "Full Paper: A Cloud-Based Approach to Introducing Machine Learning in Project-Based Learning Environments"
booktitle = "15th Annual First-Year Engineering Experience Conference (FYEE)"
year = "2024"
month = "July"
address = "Boston, Massachusetts"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/48595}
number = {10.18260/1-2--48595}
}

TY  - CPAPER
AB  - Machine learning (ML) has seen a drastic increase in relevance across all engineering
disciplines. As such, engineering students must explore this emerging technology early
in their engineering journey to provide students with the necessary background and
tools to undertake this new dawn of technological advancement. By introducing
machine learning during first-year coursework, engineering educators are provided a
unique position to properly and effectively introduce students to the unique
problem-solving capabilities of ML.

The University of Maryland’s Introduction to Engineering class is a 3-credit
project-based, introductory engineering course that challenges first-year students to
develop and employ skills such as modeling, prototyping, manufacturing,
troubleshooting, project management, coding, electronics, and teamwork, to ultimately
build an Over-Terrain Vehicle (OTV) capable of autonomous navigation and completing
mission-specific tasks. Through a pilot semester, the course exposed students to
machine learning using NVIDIA Jetson Nanos. However, the steep learning curve
required to operate the Jetson Nanos coupled with integration complexities ultimately
impeded students from fully grasping machine learning concepts. Because of this, a
cloud-based instructional approach using Google Colab was adopted to bridge the gap
for students without prior programming knowledge whilst still allowing them to get
hands-on machine learning experience.

Around 420 first-year engineering students interacted directly with machine learning by
first completing an introductory lesson via Google Colab that provided the necessary
background information and creative autonomy to explore fundamental machine
learning concepts. Student teams were then able to apply the lesson by creating custom
image-based ML models for their project’s design. To make decisions autonomously, the
teams’ OTVs would transmit live images via a wireless camera that their trained model
then processed to form a prediction. Full technical support was provided to facilitate
machine learning integration as a project solution.
Students were surveyed on their knowledge of machine learning before and after the
initial lesson and at the end of the semester. The efficacy of the curriculum was
evaluated through these surveys, instructor observations, and student feedback. This
paper explores the details of the material, the technical efforts and support necessary,
and the student learning outcomes from the renovated machine learning curriculum.
AU  - Joshua Eron Stone
AU  - Forrest Milner
AU  - Abigail Guicheteau
CY  - Boston, Massachusetts
DA  - 2024/07/28
PB  - ASEE Conferences
TI  - Full Paper: A Cloud-Based Approach to Introducing Machine Learning in Project-Based Learning Environments
UR  - https://peer.asee.org/48595
DO  - 10.18260/1-2--48595
ER  -