Convolution and Wavelet Neural Networks Applied to EEG Brain-Control Interface

Undergraduate Research Conference Poster

OURE Final Report

I performed EEG research as part of the Missouri S&T program Opportunities for Undergraduate Research Experiences (OURE). I worked with Dr. Donald C. Wunsch and the Missouri S&T Applied Computational Intelligence Laboratory for this project exploring the possibility of using wavelet or convolution neural networks for motor-imagery classification. These types of neural networks are becoming very popular in image analysis for object tagging or facial recognition, so I though to apply them to the challenging problem of the EEG brain-control interface. In the end, these algorithms did not perform better than the best work out there, but I provided a few ideas I had moving forward with this approach.

This project resulted in a follow-on project where I’m working with a senior design group to implement an EEG-BCI on an FPGA. The final result would be a portable BCI that could be carried to hospitals or other places where patients could use it.

I also had some ideas of where to take the research next, so hopefully I’ll get a chance to write about that!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s