Shulou(Shulou.com)11/24 Report--

CTOnews.com, August 25 (Xinhua) according to a new paper published in the academic journal Nature, researchers have developed a new brain-computer interface device (BCI) that can convert brain signals into words faster than before, which is of great significance to help severely paralyzed people restore their communication skills.

According to the journal Nature, people with neurological diseases, including brainstem stroke or amyotrophic lateral sclerosis, often lose language due to muscle paralysis, and researchers are able to decode language from the brain activity of the paralyzed. But the relevant output form can only be text, and the speed, accuracy and vocabulary are limited.

The ▲ map is from the journal Nature, and this new brain-computer interface device, developed by the Stanford University team in the United States, can collect the neural activity of a single cell by inserting an array of fine electrodes in the brain. The researchers decode the neural activity of a single cell by using AI, and then deduce what the patient wants to say. Compared with the existing technology, the new brain-computer interface device can decode brain activity into language faster and more accurately. And cover a larger vocabulary.

With the help of the device, a patient with amyotrophic lateral sclerosis can communicate at a rate of 62 words per minute, 3.4 times faster than previous devices and closer to the speed of natural conversation (about 160 words per minute).

According to the article queried by CTOnews.com, the error rate of the device with a vocabulary of 50 words is 9.1%, which is 1x3 lower than that of the previous state-of-the-art language brain-computer interface device. When using 12500 vocabulary, the error rate of the device is 23.8%.

The technology is still in the proof-of-concept stage and is not ready for commercial use, but it still represents "significant progress" in restoring "fast-paced communication" for patients who have lost the ability to speak, said Dr Frank Willett, lead author of the study.

Frank Willett also said that before possible commercialization, the technology must be tested on more people to prove its reliability, and the team claimed that "in the future they will further improve the speed and accuracy of the brain-computer interface devices they have developed."

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.