Transformer encoder with multiscale deep learning for pain classification using physiological signals
Zhenyuan Lu, Burcu Ozek, Sagar Kamarthi · 2023
Read Transformer encoder with multiscale deep learning for pain classification using physiological signals by Zhenyuan Lu, Burcu Ozek, Sagar Kamarthi (2023) 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-10730685.txt.
Description
Lu, Ozek, and Kamarthi build a deep learning model that scores pain from body signals. Self-reported pain scales can be uneven and biased, so a signal-based tool could help. Their model, PainAttnNet, aims to sort pain levels more precisely.
The model joins multi-scale networks, a squeeze-and-excitation block, and a transformer encoder. That mix pulls features across time spans and weights how features relate. Tests used the BioVid heat pain dataset, a standard set for this task. PainAttnNet beat prior models on that data. The authors see it as a step toward more personal, exact pain checks.
Catalog record
| CREATOR | Zhenyuan Lu, Burcu Ozek, Sagar Kamarthi |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |