In recent years, brain-computer interfaces (BMIs) have emerged as a promising solution to restore communication and control in patients with severe movement disorders. Traditionally, these BCI systems have been limited in size and power consumption.

Recently, researchers at the Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland have developed a new type of small thin-chip chip that dwarfs those larger devices, which is not only smaller in size, but also very good in performance. According to the researchers, the device is the first high-performance miniature brain-computer interface (MiBMI), which offers an extremely small, low-power, high-precision, and versatile solution.

The device, called the Micro Brain-Computer Interface (MiBMI), is a fully integrated system consisting of two extremely small chips. This means that all the recording and processing is made up of these two small thin chips with a total area of only 8 square millimeters. In comparison, Elon Musk's Neuralink device (about 23 x 8 mm) is relatively large.

"MiBMI allows us to convert complex neural activity into readable text with high accuracy and low power consumption," said researcher Shoaran. This advancement brings us one step closer to practical, implantable solutions that can significantly improve the communication skills of individuals with severe movement impairments. ”

The brain-to-text conversion involves decoding the neural signals that are produced when a person imagines writing letters or words. During this process, electrodes implanted in the brain record neural activity associated with the movement of writing. The MiBMI chipset then processes these signals in real time to convert the brain's expected hand movements into the corresponding digital text.

The entire brain-computer interface on the chip: converts brain activity into text on a very small integrated system. Source: EPFL / Lundi13 - CC-BY-SA 4.0

This technology allows patients, especially those with locked-in syndrome and other severe movement disorders, to communicate simply by thinking about writing, and brain-computer interface devices convert their thoughts into on-screen readable text.

Mohammed Ali Shaeri, lead ··author of the study, said: "While the chip has not yet been integrated into the BMI at work, it has processed data from previous field recordings, such as those in Stanford's Xenoy lab, with an impressive 91 percent accuracy in converting handwriting activity into text." ”

The number of characters that can be processed

The chip can currently decode up to 31 different characters, an achievement unmatched by any other integrated system.

Shaeri added: "We are confident that we can decode up to 100 characters, but there is currently no handwritten dataset with more characters. ”

The current BMI records data through electrodes implanted in the brain, and then sends these signals to another computer for decoding. The MiBMI chip not only records data, but also processes the information in real time – integrating a 192-channel neural recording system and a 512-channel neural decoder.

In order to be able to process the vast amount of information collected by the electrodes on the miniature BMI, the researchers had to employ a completely different approach to data analysis.

They found that when patients imagined writing by hand, the brain activity of each letter contained very specific markers, which the researchers named a distinctive neural code (DNC). The microchip only needs to process about 100 bytes of DNC, rather than thousands of bytes of data for each letter.

This makes the system fast, accurate, and low in power consumption. This breakthrough also shortens training time, making it easier and more convenient to learn how to use BMI.

This breakthrough in neurotechnology is a feat of extremely miniaturization of expertise in the fields of integrated circuits, neural engineering, and artificial intelligence. In the BMI space, integration and miniaturization are the focus, an innovation that is particularly exciting in the emerging era of neurotech start-ups. EPFL's MiBMI offers promising insights and potential for the future of the field.

This article is from Xinzhi self-media and does not represent the views and positions of Business Xinzhi.If there is any suspicion of infringement, please contact the administrator of the Business News Platform.Contact: system@shangyexinzhi.com