Researchers Can Use Brain Activity to Measure How Well You Understand a Concept

The new method utilizes a machine learning algorithm to find patterns in the brain.

Properly understanding a concept and internalizing it is how you grow in an academic or professional setting. As an engineer, no matter the field, you are constantly learning and picking up new concepts to better hone your craft. The way you usually demonstrate the understanding of a new concept can usually be boiled down to how well to can teach that same idea to someone else.

RELATED: WHAT IS DEEP LEARNING AND WHY IS IT MORE RELEVANT THAN EVER?

Yet, researchers from Dartmouth have developed a machine learning algorithm that can be used to measure how well a student understands a concept based on their brain activity. This study is a fascinating one as it is one of the first studies to take a look at how knowledge is learned in school. In the study, researchers focused on STEM topics.

Learning STEM topics

For the research, the Dartmouth team examined how novices and intermediate learners' knowledge and brain activity compared when testing mechanical engineering and physics concepts. Using this, the team proceeded to then develop a new method to assess their conceptual understanding.

Senior author David Kraemer, an assistant professor of education at Dartmouth College, described why the team chose to focus on STEM topics. "Learning about STEM topics is exciting but it can also be quite challenging. Yet, through the course of learning, students develop a rich understanding of many complex concepts.

“Presumably, this acquired knowledge must be reflected in new patterns of brain activity. However, we currently don't have a detailed understanding of how the brain supports this kind of complex and abstract knowledge, so that's what we set out to study."

Breaking Down the Study

Researchers Can Use Brain Activity to Measure How Well You Understand a Concept
"Neural score localizations by group. Regions contributing to neural scores in engineering students are shown in red. Regions contributing to neural scores in novices are shown in light blue. Regions contributing to neural scores in both engineering students and novices are shown in purple" Source: Dartmouth College

The study involved twenty-eight Dartmouth students, equally separated into two groups of engineering students and novices. Engineering students have taken at least one mechanical engineering course and an advanced physics course, while novices had not taken any college-level engineering or physics classes.

Students were given tests that focused on how structures are built and assessed participants' understanding of Newton's third law as well as a brief overview of the different types of forces in mechanical engineering. Then students were then asked to identify the Newtonian forces in real-world structures.

Interestingly, students who scored higher on the tests tended to use the visual cortex similarly when applying concept knowledge about engineering, they use the rest of the brain very differently to process the same visual image.

Advertisement

As stated in the paper, “Consistent with prior research, the results demonstrated that the engineering students' conceptual knowledge was associated with patterns of activity in several brain regions, including the dorsal frontoparietal network that helps enable spatial cognition, and regions of ventral occipitotemporal cortex that are implicated in visual object recognition and category identification”.

Advertisement