3D convolutional neural network based on spatial-spectral feature pictures learning for decoding motor imagery EEG signal
Xiaoguang Li, Yaqi Chu, Xuejian Wu · 2024
Read 3D convolutional neural network based on spatial-spectral feature pictures learning for decoding motor imagery EEG signal by Xiaoguang Li, Yaqi Chu, Xuejian Wu (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-11667157.txt.
Description
Xiaoguang Li, Yaqi Chu, and Xuejian Wu decode imagined movement from brain signals with a 3D neural network in a 2024 paper. Brain-computer interfaces that need no surgery could aid rehabilitation. Imagined-movement signals are weak and blurry, so decoding them well is hard.
Their network learns from maps that fuse where electrodes sit with how much power each frequency band carries at each site. Cubic interpolation builds smooth feature pictures from those maps. The 3D network then learns joint patterns across space and frequency at once. The authors report better decoding than methods using only space or time features. Cleaner decoding means more reliable thought-controlled devices.
Catalog record
| CREATOR | Xiaoguang Li, Yaqi Chu, Xuejian Wu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |