STEM-In-Action Spring Scoop: Psychologigals

Happy Friday, time for the scoop! If you're just tuning into the eCYBER Blog, it's about time! No really, welcome. The U.S. Army Educational Outreach Program (AEOP) STEM-In-Action Grant awards eCYBERMISSION teams up to $5,000 to develop their projects into mature and scalable solutions in their community. Typically, we award this honorary grant to five teams, but in 2020 ten lucky teams took home the prestigious award. Each week we catch up with teams on Wednesday and Friday and today we're seeing how team Psychologigals have furthered their mission to helping people suffering from depression in their community.

--

Our project was screening for depression in people’s voices using statistical analysis and machine learning.

Our team has made decent progress since receiving the Stem-In-Action Grant. After communicating with members of our community, we refocused our efforts into creating a webapp instead of a mobile app because we realized that our solution is better suited for a single use platform. We completed an online course about using the Flask API to create interactive web pages. This brought us closer to our goal of bringing our solution to our community. We also are in the process of reaching out to clinical psychologists and the IDVA to establish a strong connection with our target audience.

Making an app seemed like a really daunting goal that we would not be able to overcome. We didn’t have experience in app development, and finding tutorials and mentors was also hard. To overcome this speed bump, we changed our focus and decided we were going to create a web app instead because it was more feasible and practical for users of our product.

Our other speed bump was the time management aspect. We all have really big exams coming up in school this year, and it is hard to meet consistently while we have these and our regular extracurriculars. We are going to try to overcome this by creating and sticking to a rigid and consistent meeting schedule.

We are most excited about improving the accuracy of our program as well as developing our webapp. After taking the Flask class, we are ready to write the code for our app and develop its features. We’ve divided the sections of our web app amongst ourselves to work on remotely. Additionally, we were able to contact the DAIC Corpus database once more and now have many more voice samples to train our machine learning models with. Once we finish the training, we hope to improve our accuracy so that others can successfully use it once we integrate it into our app.

We would want our neural network accuracy to be near perfect. We think we could achieve this by getting as many voice samples as possible using high quality equipment. We also want our app to be as widely accessible as possible so that people of all ages can use it. Additionally, we hope that in the future, our method can be used in clinical diagnosis.

--

With how many people, not only just nationally but globally, that are affected by depression, this revolutionary idea is sure to set Psychologigals apart in tackling this crisis. Mental health is so important and their innovated platform is sure to help many people all across the country, not just in their own backyards.

-Mission Control

Colleen Minan
AEOP Communications & Marketing Specialist
cminan@nsta.org