Everyone learns in a different way. Whether it be from watching that YouTube tutorial series or scouring the textbook, each person responds to and processes knowledge very differently. We hoped to identify students’ learning styles and tailor educational material to the learner for two main reasons: one, so that students can learn more efficiently, and two, so that educators may understand a student’s style and use it to motivate or teach a concept to a student more effectively.
What it does
EduWave takes live feedback from the Muse Headband while a person is undergoing a learning process using visual, auditory, or haptic educational materials, and it recognizes when the brain is more responsive to a certain method of learning than others. Using this data, we then create a learning profile of the user.
With this learning profile, EduWave tailors educational material to the user by taking any topic that the user wants to learn and finding resources that apply to the type of learner they are. For instance, if the user is a CS major learning different types of elementary sorts and wants to learn specifically how insertion sort works, and if EduWave determines that the user is a visual learner, EduWave will output resources and lesson plans that teach insertion sort with visual aids (e.g. with diagrams and animations).
How we built it
We used the Muse API and Muse Direct to obtain the data from the user while they were solving the initial assessment tests and checked for what method the brain was more responsive to using data analysis with Python. We added an extra layer to this by using the xLabs Gaze API which tracked eye movements and was able to contribute to the analysis. We then sent this data back with a percentage determination of a learning profile. We then parsed a lesson plan on a certain topic and outputted the elements based on the percentage split of learning type.
Challenges we ran into
The Muse Headband was somewhat difficult to use, and we had to go through a lot of testing and make sure that the data we were using was accurate. We also ran into some roadblocks proving the correlation between the data and specific learning types. Besides this, we also had to do deep research on what brain waves are most engaged during learning and why, and then subsequently determine a learning profile. Another significant challenge was the creation of lesson plans as we not only had to keep in mind the type of learner but also manage the content itself so that it could be presented in a specific way.
Accomplishments that we're proud of
We are most proud of learning how to use the Muse data and creating a custom API that was able to show the data for analysis.
What we learned
How to use Muse API, Standard Library, Muse Direct, how brainwaves work, how people learn and synthesizing unrelated data.
What's next for EduWave
Our vision for EduWave is to improve it over time. By determining one's most preferred way of learning, we hope to devise custom lesson plans of learning for the user for any topics that they wish to learn – that is, we want a person to be able to have resources for whatever they want to learn made exclusively for them. In addition, we hope to use EduWave to benefit educators, as they can use the data to better understand their students' learning styles,