Leveraging Tripartite Tier Convolutional Neural Network for Human Emotion Recognition: A Multimodal Data Approach
Bibliographic record
Abstract
In the recent past, significant strides have been made in the field of deep learning and data fusion, enabling computers to comprehend, identify, and analyse human emotions with remarkable precision.However, reliance on external biological features for emotion recognition can be misleading, as individuals may consciously or unconsciously mask their true emotions.Consequently, an objective and reliable approach is sought, one that draws on physiological markers for emotion recognition.This paper introduces a novel model, the Tripartite Tier Convolutional Neural Network (TTCNN), specifically designed to leverage deep learning methods for the extraction and classification of significant features in multimodal emotion recognition.Amongst various physiological features, this study prioritizes eye movement and Electroencephalogram (EEG) data due to their robust potential to reflect emotional states.The multimodal data-based feature extraction facilitated by the TTCNN model yields a comprehensive set of features, enhancing the effectiveness of emotion classification into categories such as disgust, fear, sadness, happiness, and neutrality.This innovative cognitive approach has been evaluated using two established datasets, SEED and DEAP.The performance of the TTCNN model demonstrates its efficacy, achieving an impressive 95.84% classification accuracy on the SEED dataset and 87.01% on the DEAP dataset.These results significantly outperform existing state-of-theart methods, underscoring the TTCNN model's potential as a robust tool for human emotion recognition.This research contributes to the advancement of computer-aided emotion analysis, presenting a significant step forward in the field and opening up potential applications in diverse areas such as psychology, healthcare, and human-computer interaction.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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".