Emotion recognition based on 3D-EEGU-Net and differential entropy features for small sample EEG and embedded applications
Bibliographic record
Abstract
To address the limitations of traditional emotion recognition methods in terms of timeliness, high-dimensional data processing, and small sample scenarios, this paper proposes an EEG-based emotion recognition method using 3D-EEGU-Net. This method combines differential entropy (DE) features with high-dimensional spectral mapping, effectively improving emotion classification performance. By performing Fast Fourier Transform (FFT) to decompose EEG (Electroencephalography) signals into delta, theta, alpha, beta, and gamma frequency bands, the differential entropy features of each frequency band are extracted and integrated with the original signal to construct a three-dimensional feature matrix (M×N×L×6). The designed 3D-U-Net architecture (3D-EEGU-Net) utilizes an encoder-decoder structure to mine spatiotemporal features, achieving a recognition accuracy of 92.34% on the SEED (SJTU Emotion EEG Dataset) dataset, significantly outperforming existing methods. Experiments found that abnormal fluctuations in the β band of subjects were associated with ADHD (Attention Deficit Hyperactivity Disorder) symptoms. Further, the model was deployed on the Huawei A2 development board, validating the feasibility of real-time emotion classification. This study provides a new approach for small sample EEG emotion recognition and embedded applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".