N2G calibrator: a cross-subject adversarial learning framework for neural signal-driven gait tracking in Parkinson’s disease
Jin Woo Choi, Helen M. Bronte-Stewart · 2026
Read N2G calibrator: a cross-subject adversarial learning framework for neural signal-driven gait tracking in Parkinson’s disease by Jin Woo Choi, Helen M. Bronte-Stewart (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13443168.txt.
Description
Jin Woo Choi and Helen Bronte-Stewart present a learning system, in a paper published in 2026, that reads walking from brain signals in Parkinson's disease. Brain stimulation that adapts to a patient's state needs a steady read of movement. Gathering labeled brain and motion data from each new patient is slow, and brain signals differ from person to person.
Their framework learns from other patients' labeled data and aligns a new patient's unlabeled signals to that shared pool. This removes the need for special motion gear during setup, so training can happen outside a fitted clinic. Error rates fell sharply versus models used without this step, and scores came close to models trained on the patient's own labeled data. The signal could guide adaptive stimulation in daily settings.
Catalog record
| CREATOR | Jin Woo Choi, Helen M. Bronte-Stewart |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 92 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |