dc.description.abstract | Software that provides automated teaching assistance and instantaneous feedback for
students has revolutionized the modern classroom. In addition to helping instructors manage
large classes, the interactive experience can also benefit students. For instance, several
existing systems incorporate recognition of student’s hand-drawn solutions to problems.
In these cases, the instructor sketches the solution to the problem and the student’s sketches
are expected to match this template. While this framework provides immediate feedback
to students, it is still a constraint on instructors’ time; additionally, it can be difficult to
test conceptual understanding through only a small number of problems. There remains a
strong need to generate questions automatically based on templates drawn by instructors
so as to promote greater customization and variation in problems for students.
The focus of our research is to develop a novel method that can automatically generate
new valid problems from a given reference problem. We have chosen linear spring-based
truss systems as our domain. Another outcome of our research is to develop a method for
recognizing a spring network sketched naturally by the user with commonly used symbols.
We also generate different types of questions and boundary conditions from the recognized
and auto-generated truss structures using the finite element method (FEM) in a novel way.
Our system has been integrated with Mechanix, a tool developed at Texas A&M University
which supports free body diagrams (FBDs) and the creative design of truss structures.
Mechanix supports engineering learning by providing intelligent and immediate
feedback on hand-drawn sketches, and it has already been actively deployed in a number
of university classrooms. We build a problem generator on top of Mechanix to leverage
its capabilities for instantaneous, personalized feedback while enabling more thorough
testing of student abilities and providing them a limitless pool of practice problems. | en |