Emotion recognition using spectral-spatial attention multi-temporal scale network: EEG study
Zhe Tao, Guanghao Huang, Leilei Ma, Zhuochao Chen, Yinhua Liu, Keum Shik Hong · 2026
Read Emotion recognition using spectral-spatial attention multi-temporal scale network: EEG study by Zhe Tao, Guanghao Huang, Leilei Ma, Zhuochao Chen, Yinhua Liu, Keum Shik Hong (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-13272739.txt.
Description
Zhe Tao and colleagues proposed a neural network for reading emotion from brain waves in a 2026 paper. Electroencephalography, which records scalp signals, is portable and cheap, yet emotion signals mix space, frequency, and time in hard ways. Their model aims to capture all three at once.
The network first uses attention to weigh signal frequencies and links between brain regions while keeping electrode layout. It then applies convolutions at several time scales to catch short and long emotional cues, followed by a memory module for sequence patterns. Tested on three public datasets, the model reached high accuracy across emotion tasks, above ninety percent in each reported test. The authors present it as a strong option for emotion aware computing.
Catalog record
| CREATOR | Zhe Tao, Guanghao Huang, Leilei Ma, Zhuochao Chen, Yinhua Liu, Keum Shik Hong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |