We worked on the MathNet team at The ASSISTments Foundation to complete five projects: an image cropper and personally identifiable information (PII) blocker for the ASSISTments workbench; a study of the effects of different distance metrics and preprocessing effects on the results of k-means clustering of images; a crop-resistant invisible watermark for images; automating the watermarking and sharing of a 28,000 image dataset; and assessing how much information GPT-4 could gather from images of student math work.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Sowad, Mahir

Subject

• Learning
• Innovation
• Computing
• Project-Based Learning

Publisher

• Worcester Polytechnic Institute

Identifier

• 116540
• E-project-011024-223354

Keyword

• ASSISTments
• Education
• MathNet
• 28k Images Dataset

Advisor

• Heffernan, Neil

Year

• 2024

Sponsor

• The ASSISTments Foundation

UN Sustainable Development Goals

• 4 - Quality Education

Date created

• 2024-01-10

Resource type

• Interactive Qualifying Project

Source

• E-project-011024-223354

Rights statement

• In Copyright

License

• Creative Commons BY Attribution 4.0 International

Last modified

• 2024-02-07