Utilizing Online & Open-Source Machine Learning Toolkits to Leverage the Future of Sustainable Engineering
- Conference
- Location
-
Baltimore , Maryland
- Publication Date
-
June 25, 2023
- Start Date
-
June 25, 2023
- End Date
-
June 28, 2023
- Conference Session
-
Environmental Engineering Division (ENVIRON) Technical Session 2
- Tagged Division
-
Environmental Engineering Division (ENVIRON)
- Page Count
-
17
- DOI
-
10.18260/1-2--44595
- Permanent URL
-
https://strategy.asee.org/44595
- Download Count
-
115
Paper Authors
Andrew Schulz Georgia Institute of Technology
Andrew Schulz is a postdoctoral researcher at Max Planck Institute for Intelligent Systems in Stuttgart, Germany. Andrew received his Ph.D. in Mechanical Engineering from Georgia Tech in August of 2022, studying the bio-inspired design of elephant trunks and conservation technology. Andrew is a member of the Engineering for One Planet (EOP) Network and is working to educate the next generation of conservation technology practitioners.
Suzanne Stathatos The California Institute of Technology
Suzanne’s drive to protect the natural world led her to graduate school at Caltech. She is a Computing and Mathematical Sciences PhD student, advised by Pietro Perona. Her interests include leveraging machine learning and computer vision techniques to enable large-scale biodiversity monitoring and solve conservation-oriented issues. Suzanne holds an B.A. in History and an M.S. in Computer Science from Stanford University. Prior to Caltech, Suzanne worked as a software engineer at Amazon and NASA’s JPL. These experiences have sharpened her appreciation for interdisciplinary perspective and the real world impact of precise computational techniques.
Cassandra Shriver Georgia Institute of Technology
Cassie Shriver is a PhD student in Quantitative Biosciences in the College of Sciences at Georgia Institute of Technology. Shriver earned a B.S.E. in Mechanical Engineering from Duke University, along with a Minor in Biology and a Certificate in Marine Science Conservation and Leadership. She is intimately familiar with the value of interdisciplinary education and is interested in how it can enhance the efficacy of conservation initiatives and technology.
Roxanne Moore Georgia Institute of Technology
Roxanne Moore is a Senior Research Engineer in the G.W. Woodruff School of Mechanical Engineering and the Center for Education Integrating Science, Mathematics, and Computing (CEISMC) at the Georgia Institute of Technology. Her research focuses on design and engineering education with a focus on promoting diversity and inclusion. She has served as PI and co-PI for grants from multiple sponsors including NSF and Amazon totaling more than $9M. In addition, her STEM outreach programs and curricula have impacted hundreds of thousands of K-12 students nationwide. She is the cofounder and director of Georgia Tech’s K-12 InVenture Prize, a statewide invention competition, open to all students and teachers in Georgia. She earned her BS in Mechanical Engineering from the University of Illinois at Urbana Champaign in 2007, and her Masters and PhD in Mechanical Engineering from Georgia Tech in 2009 and 2012. Dr. Moore received the Georgia Tech Teaching Effectiveness Award in 2018.
Abstract
The United Nations Sustainable Development Goals (SDGs) have become a foundational metric for advancing engineering education in non-traditional ways, similar to the NSF’s Big 10 Ideas and the Grand Challenges. Recently, there has also been a national push to use machine learning (ML) and artificial intelligence (AI) to advance engineering techniques in all disciplines ranging from advanced fracture mechanics in materials science to soil and water quality testing in the civil and environmental engineering fields. Using AI, specifically machine learning, engineers can automate and decrease the processing or human labeling time while maintaining statistical repeatability via trained models and sensors. Edge Impulse has designed an open-source TinyML-enabled Arduino education tool kit for engineering disciplines. This paper discusses the various applications and approaches engineering educators have taken to utilize ML toolkits in the classroom. We provide in-depth implementation guides and associated learning outcomes focused on the Environmental Engineering Classroom. We discuss five specific examples of four standard Environmental Engineering courses for freshman and junior-level engineering. There are currently few programs in the nation that utilize machine learning toolkits to prepare the next generation of ML & AI-educated engineers for industry and academic careers. This paper will guide educators to design and implement ML/AI into engineering curricula (without a specific AI or ML focus within the course) using simple, cheap, and open-source tools and technological aid from an online platform in collaboration with Edge Impulse. Specific examples include 1) facial recognition technologies and the biases involved, 2) air quality detection using an accelerometer, 3) roadside litter detector, 4) automated bird identifier, and 5) wildlife camera trap detection.
Schulz, A., & Stathatos, S., & Shriver, C., & Moore, R. (2023, June), Utilizing Online & Open-Source Machine Learning Toolkits to Leverage the Future of Sustainable Engineering Paper presented at 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland. 10.18260/1-2--44595
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2023 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015