Two Fairfax County students used AI to create an algorithm that can be used to classify brainwave signals that can be used to control prosthetic limbs.
About seven months ago, Chantilly High School student Gowtham Ramachandran came across a man in a wheelchair on the sidewalk.
Ramachandran said he was inspired by a man who lived his life without a leg. Ramachandran approached him and they exchanged pleasantries.
Over the next few days, Ramachandran reflected on his desire to help people like the man he spoke to.
“I was wrestling with a pressing problem: How can we leverage technology to provide autonomy and empower individuals like him?” he said.
Ramachandran and his classmate Shriram Nalini realized that the answer to that question involved artificial intelligence. They used his AI to create algorithms that can be used to classify electroencephalogram (EEG) signals, which can be used to control prosthetics.
“This is the key to a new realm of interaction, where your thoughts are seamlessly translated into action, where technology is an invisible and intuitive extension of the human experience,” Ramachandran said. He told WTOP.
Ramachandran started programming in third grade, creating video games using HTML and JavaScript. But instead of playing video games, he said he became “obsessed with making games” and spent hours coding.
Ramachandran said that when he was in middle school, he released a game on a platform called Steam. But that's nothing compared to his recent efforts.
Ramachandran and Nalini said they looked at the different types of techniques available to analyze brain signals. In some cases, patients receive implants, which Ramachandran said is innovative but “requires a level of invasiveness that is not ideal for everyone.”
Traditional EEG headsets are another option, but Ramachandran said they are “complicated because they require so many electrodes, and frankly, they're not as accurate as you'd hope, especially when it comes to classifying movement.” Ta.
So the two students adopted EEG technology to streamline it.
“We basically used this AI algorithm to bring this vision to life,” Ramachandran said. “It's designed to work with just a few electrodes.”
This innovation helps improve accuracy, he said. Previously, the highest accuracy he had seen was 98%, “which means for every 100 movements he makes two mistakes.”
Ramachandran said that thanks to this algorithm, “classification accuracy reaches the highest points, up to 100%. This is not just an improvement, it is a revolution.”
Ramachandran said the technology “essentially allows people to control prosthetic limbs and devices using brain signals.”
The two published their research results in a research paper.
Their efforts are helping “to provide cost-effective solutions for prosthetic limbs,” he said.
Sign up here to get the latest news and daily headlines delivered to your email inbox.
© 2024 WTOP. All rights reserved. This website is not directed to users within the European Economic Area.