Palm sEMG-based user identification during doorknob rotation using a convolutional neural network
Yeonjung Shin, Junghun Kim, Sang-Il Choi · 2026
Read Palm sEMG-based user identification during doorknob rotation using a convolutional neural network by Yeonjung Shin, Junghun Kim, Sang-Il Choi (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-13369756.txt.
Description
Yeonjung Shin and co-authors turn a doorknob into a password in a 2026 biometrics paper. The system identifies people by the electrical signals in their palm muscles as they twist a knob, an everyday action that needs no extra device or deliberate gesture, suiting smart-home settings.
Sensors on two palm muscles recorded signals from five volunteers, cleaned and converted into time-frequency pictures by wavelet analysis. A DenseNet classifier learned each person's pattern, reaching about ninety-four percent accuracy on held-out trials. Cross-validation stayed near ninety-two percent. The authors pitch the approach as seamless, on-device authentication woven into ordinary life.
Catalog record
| CREATOR | Yeonjung Shin, Junghun Kim, Sang-Il Choi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |