Data-Efficient EEG-Based Person Identification via Time-Interval-Based Multi-Positive Contrastive Learning
Xinghan Shao, Haixian Wang, Zhengping Wu · 2026
Read Data-Efficient EEG-Based Person Identification via Time-Interval-Based Multi-Positive Contrastive Learning by Xinghan Shao, Haixian Wang, Zhengping Wu (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-13611343.txt.
Description
Xinghan Shao and co-authors proposed in 2026 a way to identify people by brain waves without mountains of training data. EEG signals make attractive biometrics because they are hard to steal and come only from living subjects. Most systems, though, demand large enrollment sets. Their framework learns from time slices of each one-second recording, treating overlapping, neighboring, and distant slices as matching examples.
Contrastive training pulls one person's samples together and pushes others apart, with an alignment step sharpening both effects. On a 109-person public dataset, accuracy reached about ninety-nine percent with full training data. With only ten seconds per person it still topped eighty-three percent. A second dataset tested robustness across recording sessions. The authors aim at practical biometric systems that enroll users quickly.
Catalog record
| CREATOR | Xinghan Shao, Haixian Wang, Zhengping Wu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 73 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |