Key result
MRF-CMFT achieves ~0.61 mean AUC for multimodal EEG-ECG affect recognition across benchmark datasets.
Why the study?
The reliability of physiological affect recognition is limited by noisy measurements, heterogeneous representations, and temporally varying signal quality.
The proposed Mamba-based quality-aware multi-view fusion framework (MRF-CMFT) enables physiological affect recognition from EEG and ECG signals with graceful degradation under corrupted sensing conditions and strict leakage-controlled evaluation.
Answers are grounded in this paper and cite their sources.
Supports robust EEG-ECG affect recognition under degradation; leaves open clinical translation in cardiovascular monitoring.
Physiological affect recognition is inherently a multimodal fusion problem, yet its reliability is limited by noisy measurements, heterogeneous representations , and temporally varying signal quality. We propose Multi-view Representation Fusion with Quality-aware Cross-Modal Feature Transformation (MRF-CMFT), a quality-aware framework for EEG–ECG affect recognition. Each modality is represented using three complementary views: short-time Fourier transform power maps, Morlet wavelet scalograms, and compact handcrafted feature representations. These views are encoded by convo-lutional sequence encoders with a Mamba-based backbone and integrated through adaptive quality-aware view fusion. Cross-modal attention captures interactions between EEG and ECG, while a quality-aware modality gate dynamically regulates their contributions according to estimated signal reliability. A temporal Mamba aggregator then integrates consecutive windows to produce trial-level predictions. The MRF-CMFT was evaluated on the DREAMER and AMIGOS datasets using trial-grouped subject-dependent, subject-independent, and leave-one-subject-out protocols to prevent information leakage. On DREAMER, the framework achieves subject-independent AUC of 0.640, 0.534, and 0.581 for valence, arousal, and dominance, respectively ; the corresponding AMIGOS AUC are 0.496, 0.561, and 0.623. The mean subject-dependent AUC is 0.614 on DREAMER and 0.616 on AMI-GOS. Under the evaluated corruption conditions, the quality-aware fusion mechanism exhibits graceful degradation, with dominance AUC on AMIGOS remaining above 0.83 across all tested scenarios. These findings indicate that explicitly modelling representation reliability and cross-modal complementar-ity supports robust physiological affect recognition under subject variability and degraded sensing conditions.
No takes yet. Share an insight, caveat, or question.
Mostafa et al. (2026) studied Physiological affect and emotion recognition. MRF-CMFT (Multi-view Representation Fusion with Quality-aware Cross-Modal Feature Transformation) vs. Baseline models and corrupted signal conditions was evaluated on Mean subject-dependent Area Under the Curve (AUC) for physiological affect recognition (valence, arousal, dominance). MRF-CMFT achieved mean subject-dependent AUCs of 0.614 on DREAMER and 0.616 on AMIGOS for EEG-ECG affect recognition, maintaining AMIGOS dominance AUC >0.83 under degraded signal conditions.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: