Domain adaptation spatial feature perception neural network for cross-subject EEG emotion recognition
Wei Lu, Xiaobo Zhang, Lingnan Xia, Hua Ma, Tien-Ping Tan · 2024
Read Domain adaptation spatial feature perception neural network for cross-subject EEG emotion recognition by Wei Lu, Xiaobo Zhang, Lingnan Xia, Hua Ma, Tien-Ping Tan (2024) 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-11685119.txt.
Description
Wei Lu, Xiaobo Zhang, Lingnan Xia, Hua Ma, and Tien-Ping Tan published a 2024 paper on recognizing emotions from brain waves of people the system has never seen. EEG based emotion tools work well on familiar users but drop in accuracy on new ones, since brain signals vary by person. Their network targets that cross subject gap.
A special extractor module first pulls two kinds of spatial features from the signal: where activity sits, and how the layout connects. A domain adaptation layer then aligns feature patterns across people, so a model trained on some users transfers to others. The authors report accuracy above prior state of the art methods on cross subject tests. Such transfer matters for real products, where per user training is impractical.
Catalog record
| CREATOR | Wei Lu, Xiaobo Zhang, Lingnan Xia, Hua Ma, Tien-Ping Tan |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |