A Novel and Powerful Dual-Stream Multi-Level Graph Convolution Network for Emotion Recognition
Guoqiang Hou, Qiwen Yu, Guang Chen, Fan Chen, Wataru Sato · 2024
Read A Novel and Powerful Dual-Stream Multi-Level Graph Convolution Network for Emotion Recognition by Guoqiang Hou, Qiwen Yu, Guang Chen, Fan Chen, Wataru Sato (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-11598385.txt.
Description
Guoqiang Hou and co-authors present a 2024 computer model that reads emotion from brain signals. Machines that sense a user's feelings could respond in more personal and natural ways. Brain activity follows set patterns during thought, so the team built a network that maps links between brain regions at several levels. The model has two streams and aims to capture those links while staying fast.
One part of the model learns emotion related patterns in layered graphs of brain links. The other part blends features from early and late stages to form the final picture. In tests on four public data sets of brain recordings, the model beat many strong rival methods on accuracy. Gains over the best rivals ranged from small to a few points. Tests also confirmed each part of the model helped.
Catalog record
| CREATOR | Guoqiang Hou, Qiwen Yu, Guang Chen, Fan Chen, Wataru Sato |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 96 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |