Swiss engineers from the Federal Polytechnic School of Lausanne have developed a neuromodulation system with
The device uses a 256-channel touchscreenhigh-resolution matrix and a power-efficient machine learning processor. To train the system, we used biomarkers collected by observing real patients with epilepsy and Parkinson's disease and reconstructing these diseases in animal model organisms. Similarly, you can train the chip to recognize other diseases.
NeuralTree extracts models from brain waveselectrical signals (biomarkers) that are associated with certain neurological disorders. The system's AI categorizes signals and indicates whether they portend, for example, an impending epileptic seizure or tremor in Parkinson's disease. When symptoms are detected in a particular patient, a neurostimulator located on a chip is activated, which sends an electrical impulse to block this symptom.
The authors of the study note that the uniquenessneural interface in an energy-efficient multichannel chip. Previous similar devices had only 32 sensor channels, which greatly limited its performance. Engineers will continue to work to achieve self-actualization of the device: the ability to adapt following changes in the neural network of the patient's brain.
Read more:
Scientists have named the top 6 ways to "save" the memory of older people
A mysterious imprint underground surprised scientists. He is over 1000 years old
Sword thought to be fake turns out to be a 3,000-year-old Bronze Age artifact