Using Attentive Network Layers for Identifying Relevant EEG channels for Subject-Independent Emotion Recognition Approaches
Bibliographic record
Abstract
Emotion recognition approaches using electroencephalographic (EEG) signals can be evaluated using two distinct approaches: subject-dependent and subject-independent. While subject-independent models are more generalizable and practical than subject-dependent models, they face challenges due to the high variability of EEG signals among individuals. One solution is identifying shared patterns during emotional processing. As deep learning has become a common practice for emotion recognition, using attentive network layers can help identify shared predictive patterns. This study explores this approach by using attentive network layers to identify brain areas relevant for predicting four emotions evoked by video clips in 15 individuals. The model achieved an average accuracy of 46% (95% CI: 41.3-50.7%) among subjects, indicating that the EEG channels in the right hemisphere were more relevant for predicting happy and neutral emotions, while those in the left hemisphere were more relevant for sadness and fear. These findings highlight the importance of including EEG channels from both hemispheres to ensure the prediction of different emotion types in subject-independent approaches. Clinical relevance- This study identifies shared neuronal patterns in emotion prediction, supporting the development of generalizable emotion recognition systems that can help diagnose and treat disorders such as depression, anxiety, and neurodegenerative diseases.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".