EEG-based dynamic emotion recognition using multi-scale wavelet transform with a Spatio-Temporal neural network
R. S. Soundariya, P. Thangaraj · 2026
Read EEG-based dynamic emotion recognition using multi-scale wavelet transform with a Spatio-Temporal neural network by R. S. Soundariya, P. Thangaraj (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-13473498.txt.
Description
Soundariya and Thangaraj built an emotion-reading system for brainwave signals that chains wavelet signal cleaning, reinforcement-learned channel selection, and an ensemble of graph and memory networks. Their 2026 paper tests the pipeline on three public EEG datasets for classifying emotional states.
Reported accuracy was high across the board: 94.5% on the DEAP dataset, 98.5% on the EEG Brainwave dataset, and 97.6% on an emotion EDA dataset, each split 60% training, 20% testing, and 20% validation. The DEAP benchmark itself comes from 32 participants rating 40 music videos on arousal, valence, and dominance. Spectral entropy analysis locates emotional peaks to slice the signal into meaningful epochs before classification, an addition the authors credit for cleaner features.
Catalog record
| CREATOR | R. S. Soundariya, P. Thangaraj |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |