This is actually an improvement on the lead electrode technology, making them smaller and improving the scalp adhesion for better fidelity. Ostensibly, you would still need an array of them for medical diagnoses, like isolating and/or monitoring a seizure to a particular portion of the brain.
The brain machine interface concept seems very useful. My question is the AI part. Aside from the machine learning likely needed to decode brain signals meaningfully at all, why would we want to hook up something with any resemblance to current AI to a brain directly?
The current AI stuff can easily be described as a breakthrough in natural language interfaces. A field engineers have been working on for many years. It easy to imagine that the methods used to develop current AI could be used for different types of interfaces we've been stuck on.
Terrible headline. The single hair-like electrode outperforms the connection performance (longevity/signal to noise) of a single electrode from a 21-lead EEG.
It's not just the headline. "... a single electrode that looks just like a strand of hair and is more reliable than the standard, multi-electrode version." "The researchers tested the device’s long-term adhesion and electrical performance and compared it to the current, standard EEG using multiple electrodes."
I read the story three times and I'm still confused. But I'm sure you're right, and I think it's the author who's confused.
Better link from Penn State. My reading of this seems to suggest that these electrodes are better than the standard one, NOT that one electrode is better than 24 leads.
15 comments
[ 4.1 ms ] story [ 47.4 ms ] threadI read the story three times and I'm still confused. But I'm sure you're right, and I think it's the author who's confused.
Better link from Penn State. My reading of this seems to suggest that these electrodes are better than the standard one, NOT that one electrode is better than 24 leads.