Rutgers engineers have developed one of the fastest noninvasive brain-computer communication interfaces of its kind, leveraging artificial intelligence (AI) to translate brain activity into words and phrases at record-level speeds.
The lead researcher said the advance could make brain-based communication considerably faster and less tiring for people with severe movement and speech impairments, including those with advanced ALS, a progressive disease that attacks nerve cells that control muscles throughout the body.
Called ChatBCI-Assist, the system allows users to reproduce sentences nearly twice as fast as a conventional dictionary-based predictive approach, according to the engineers. The interface enables intent-based communication, allowing users to select AI-generated phrases that convey their intended meaning without reproducing every word precisely.
The findings were published in IEEE Transactions on Biomedical Engineering. The research was led by Laleh Najafizadeh, a professor in the Department of Electrical and Computer Engineering at Rutgers School of Engineering and
To read more, click here.