TFA-Net: A Temporal-Frequency-Adversarial Network with Few-Shot Calibration for Robust ECG-Based Emotion Recognition
Bibliographic record
Abstract
Emotion recognition based on physiological signals plays a critical role in advancing human-machine interaction, particularly in intelligent transportation and affective computing. However, existing deep learning models often struggle to generalize across subjects, limiting their practical deployment. To address this challenge, we propose a Temporal-Frequency-Adversarial Network (TFA-Net), a novel few-shot calibration framework that mitigates subject dependency in ECG-based emotion recognition. The framework integrates contextual representations from the Electrocardiogram (ECG) foundation model (ECG-FM) with spectral features derived via short-time Fourier transform (STFT). These multi-view representations are fused through a Nested Mixture of Experts (NMoE) module and refined using a learnable Fractional Fourier Transform (FrFT)-based attention pooling mechanism, which dynamically emphasizes salient temporal-frequency patterns. A Dual-Phase Adversarial Learning (DPAL) scheme further disentangles emotion-relevant and subject-specific components using gradient reversal. Evaluated on the driving dataset manD 1.0 and two benchmark datasets, DREAMER and WESAD, the proposed TFA-Net achieves 3-7% accuracy improvements over state-of-the-art methods under few-shot crosssubject protocols, demonstrating its potential for robust deployment in ITS and mental health monitoring 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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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 teacher head, 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".