Backyard Brains Logo

Neuroscience for Everyone!

+1 (855) GET-SPIKES (855-438-7745)

items ()

Don’t Blink, You Might Miss It! Can Machine Learning Be Our Eyes and Ears?

Can Machine Learning Be Our Eyes - hardware for FOMO glasses

— Written by Ariyana Miri —

Welcome back FOMO gang!

If you’ve been following along with my FOMO glasses journey, then you know I’m trying to build a pair of glasses that capture a photo every time you blink. In my first post, we discussed the idea behind my project, and the implications the success of the project can have. In the second, we discussed the nature of an eye blink signal, and how the data is being processed. Today, we’re talking about hardware and how I’m actually putting the thing together, so check out the other posts if you haven’t had the chance yet!

Can Machine Learning Be Our Eyes - layered blinks

With my project, while the signal of an eye blink is stronger and easier to detect than others, the hardware aspect presents an entirely new challenge. How are we going to get everything to communicate together and fit on a pair of glasses?

Are you not quite sure how it’ll be done? Well, me neither! These kinds of projects are all about solving one problem at a time and moving forward step by step. You never know unless you try!

Right now I have two main goals: To fully deploy the software process onto the local hardware, and the reduce the amount of hardware necessary to do so. This way, the process can be done entirely on a pair of glasses without the wearer needing to plug into any external device, and the hardware on the glasses isn’t so big that it can’t all fit comfortably on the face.

As of now, I have moved from a more complex set-up with several moving parts down to a more simplified board. The initial structure is necessary when you’re switching out parts and trying to see what works best. Once you have all the parts you need to be up and running, you can work on building your own board accustomed to your needs.

old vs new setup - fomo glasses hardware

Now, this hardware is far from complete. The next step will be adding the camera and having it triggered to take a photo by the model. We would then want that photo to either be deleted or stored on an SD card based on the classification of the model, which is an entirely separate process on it’s own. Once that is all deployed and working cohesively, we can begin further optimizing by making the board into the shape of a pair of glasses!

What This Fellowship Has Meant to Me

As we approach the end of the fellowship, I can’t help but think how fast it went. I have learned so much in the relatively short time I have been here, and can’t imagine not having done it. Before coming here, I didn’t even know what EEG or EOG signals were, much less how to detect them or if that was even something I could do! I remember the first few weeks thinking how funny people looked with electrodes on their face and how weird and awesome it was to plug yourself up to a computer and see the electricity generated by your own body. The awesomeness is still very much there, but the weirdness has dissipated, and has left me asking, what more can we do!

I wanted to be a part of Backyard Brains because of the foundational principle through which the company was founded and continues to maintain; accessibility of science. Every project Backyard Brains pursues is in the quest to make neuroscience accessible to anyone and everyone, regardless of age, culture, or socioeconomic background. As someone who has only recently been introduced to the world of neuroscience, I stand as a testament to the importance of access to technology I would otherwise never have been able to use. 

There may be few things you can say this about, but this experience has fundamentally changed my life and career path. Before this fellowship, neuroscience wasn’t even on my radar of things to pursue using computer science, but now it is one of my main goals! Working for a brief time in the field has shown me what a need there is for people well versed in both neuroscience and computer science, and how closely the two fields interact. I fully plan on continuing to pursue neuroscience research projects after this fellowship, and hope it becomes one of the main pursuits of my career.

Now, what about the next steps for the FOMO Glasses? Well, I am pleased to inform you that… I’ve decided to stay for a few more weeks after the fellowship to continue working on them! There is still much to be done even after those extra few weeks, and I wish to be as much a part of the process as I can be! Until then, FOMO gang!

geordi la forge really

No Comments

No comments yet.

RSS feed for comments on this post.

Sorry, the comment form is closed at this time.