Robust displacement estimation from filament-based soft sensors using a parallel attention-enhanced LSTM for rehabilitation monitoring
Quang-Huy Do Ba, Minh Tri Phan, Mai Thanh Thai · 2026
Read Robust displacement estimation from filament-based soft sensors using a parallel attention-enhanced LSTM for rehabilitation monitoring by Quang-Huy Do Ba, Minh Tri Phan, Mai Thanh Thai (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-13482130.txt.
Description
Do Ba and co-authors present a neural network in 2026 that reads displacement, how far something has flexed, from soft filament pressure sensors used in rehabilitation wearables. These bendy sensors drift over time and echo past readings, which corrupts the signal that standard prediction models rely on. Their design pairs a memory network that tracks sequences with a parallel pathway and an attention mechanism that highlights the informative moments in each signal.
On pressure and displacement data from a rehabilitation-style test rig, the model predicted displacement with a root mean square error of 0.047 and a mean error of 0.028 alongside it. It explained 96.3 percent of the signal's variation, a fit the authors report as a substantial gain over every baseline tried in the study. Standard memory networks, gated networks, hybrid convolutional models, and attention-only designs all trailed it, supporting use in real-time rehab monitoring and soft robotics.
Catalog record
| CREATOR | Quang-Huy Do Ba, Minh Tri Phan, Mai Thanh Thai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 124 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |