As a PhD candidate in Columbia University’s Biomedical Engineering Department, I was a member of Paul Sajda’s Laboratory for Intelligent Imaging and Neural Computing (LIINC). During that time, I worked on the following projects:
- Closing the Loop: Using EEG and Computer Vision in a Closed Loop to Identify Images of Interest
Computers are not very good at identifying what is in a picture. People, on the other hand, can look at an image and easily say “there’s a man, a horse, and a fence in that picture,” but this takes time. There are billions of unlabeled images on the internet – people don’t have time to label them, and computers just aren’t that good at it. How can we use what we know about the brain to better connect a person with the images they’re looking for?
- Brain-Cam: An Automated Memory Assistant using a Portable EEG System and Streaming Video
As you walk around during your day, you frequently come across things you see that you’d like to remember. You can make a note, take a picture, or record a video to capture these moments. But sometimes you forget to write down your new friend’s address, or the pink limousine you wanted a picture of is gone before you can take out your camera. We could record everything around us all the time, but that would take unreasonable amounts of memory storage. But what if we could make a device that would detect when you were interested in something and automatically capture the moment on film?
- NEDE: An Experimental Design Environment for Realistic Virtual Settings
Neuroscience endeavors to understand everyday human experience, but under the controlled conditions that make for good science. Running experiments in a virtual environment is a great way to balance realism and control, but the startup costs for virtual environment experiments are relatively high, as most people need to build a 3D environment and stimulus presentation scripting from scratch. To help lower the barrier to entry in this important field, we have created a suite of experimental design-focused programs on top of a user-friendly 3D game engine.
- Decision-Building: Studying the Integration of Information over Rapid Eye Movements using EEG and Eye Tracking
When we look at an object, we subconsciously make multiple eye movements to different parts of the object, building up information about it until we can decide what it is. These tiny bursts of information create important activity in our brains, but it’s difficult to see this activity because eye movements happen so quickly that responses overlap, and because eye movements create lots of noise in our EEG measurements. We are trying to solve both of these problems by applying techniques from fMRI to EEG activity, helping us see how information builds up in the brain like never before.
- Indecision-Making: Testing a Spatiotemporal Map of Visual Decision-Making with Transcranial Magnetic Stimulation
When you see something approaching from across the street, you’ll react very differently if it’s your mother, your boss, or a bear. Visual decision-making is the process that makes this possible: identifying an image and acting on that information. It’s obviously very important, and we use it all the time. When people can no longer make visual decisions (for example, in cases of dementia and visual agnosia), it’s extremely debilitating. If we know more about when and where in the brain visual decision-making takes place, it will be a great first step to learning how to fix it when it fails.
For More Information: