Innovation in neurotechnology
Traditional BMIs are often bulky and energy-intensive. The new Miniaturized Brain-Machine Interface (MiBMI), developed at EPFL's Integrated Neurotechnologies Laboratory (INL), on the other hand, is small, energy-efficient and highly precise. These properties make it particularly suitable for implantable applications. The system consists of two tiny chips with a total surface area of just 8 mm², on which both the recording and processing of the brain signals take place.
How does MiBMI work?
The MiBMI can convert complex neuronal activities into text. Electrodes in the brain record the neuronal signals that are generated when a person mentally simulates writing letters or words. The system decodes these signals in real time and converts them into readable text.
- Size and efficiency: MiBMI requires little space and energy.
- Real-time processing: 192-channel recording system combined with a 512-channel decoder.
- High accuracy: Up to 31 characters have been decoded with an impressive accuracy of 91%.
"MiBMI allows us to convert intricate neural activity into readable text with high accuracy and low power consumption. This advancement brings us closer to practical, implantable solutions that can significantly enhance communication abilities for individuals with severe motor impairments," says Mahsa Shoaran, Assistant Professor at the EPFL Integrated Neurotechnologies Laboratory.
Applications and future prospects
The research at MiBMI is promising as it is one of the first systems that can decode so many characters. Future applications could go beyond handwriting and include areas such as speech decoding and motion control. Collaborations with other research teams at EPFL promise to further develop this technology for a variety of neurological disorders.
The MiBMI marks a milestone in neurotechnology and could significantly improve the lives of many people with severe motor impairments.
COMPAMED-tradefair.com; Source: Ecole Polytechnique Fédérale de Lausanne
