aiqbench analysis
This study evaluates deep learning architectures including LSTMs, TCNs, and Transformers for recognizing emotions from physiological signals like wrist and chest sensor data. The research demonstrates that an ensemble fusion strategy combining these models achieves superior accuracy compared to single-modality or early-fusion approaches on the WESAD dataset. These findings advance affective computing by establishing robust methods for multimodal stress detection using wearable technology.
Deep Temporal Modeling and Ensemble Fusion for Multimodal Emotion Recognition from Physiological Signals
arXiv:2606.15026v1 Announce Type: new Abstract: Physiological stress and emotion recognition are important for health monitoring and affective computing. In this work, we present a comprehensive evaluation of deep learning models such as Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Transformer on the WESAD dataset for multimodal affect recognition using wrist and chest sensor signals. We perform ablation studies to assess the individual contributions of each modality by training models on wrist-only and chest-only inputs. In addition, we implement a late-fusion ensemble strategy that combines predictions from all three architectures trained on multimodal input. We also employ early fusion at the sensor level by concatenating wrist and chest signals before feeding them into each model. Our results show that Transformer models consistently achieve the highest accuracy in multimodal settings, while TCN models perform best in the wrist-only configuration. The ensemble method yields the highest overall accuracy (98.91 +/- 0.13%) and macro-F1 score (98.56 +/- 0.17%). These findings demonstrate the effectiveness of sensor fusion and ensemble-based fusion in developing robust systems for physiological emotion recognition.
Abstract:Physiological stress and emotion recognition are important for health monitoring and affective computing. In this work, we present a comprehensive evaluation of deep learning models such as Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Transformer on the WESAD dataset for multimodal affect recognition using wrist and chest sensor signals. We perform ablation studies to assess the individual contributions of each modality by training models on wrist-only and chest-only inputs. In addition, we implement a late-fusion ensemble strategy that combines predictions from all three architectures trained on multimodal input. We also employ early fusion at the sensor level by concatenating wrist and chest signals before feeding them into each model. Our results show that Transformer models consistently achieve the highest accuracy in multimodal settings, while TCN models perform best in the wrist-only configuration. The ensemble method yields the highest overall accuracy (98.91 +/- 0.13%) and macro-F1 score (98.56 +/- 0.17%). These findings demonstrate the effectiveness of sensor fusion and ensemble-based fusion in developing robust systems for physiological emotion recognition.
Accepted for publication in the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (ACM BCB 2026). DOI: this https URL
Computation and Language (cs.CL)
arXiv:2606.15026 [cs.CL]
(or arXiv:2606.15026v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.15026 arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1145/3807503.3819363 DOI(s) linking to related resources
Full text under the publisher's open licence · 218 words
Related coverage
Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based Fusion
arXiv · Sep 7, 2026
From Stress to Affect: Multimodal Deep Learning for Physiological Emotion Recognition Across Wearable Sensor Modalities
arXiv · Sep 21, 2026
Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions
arXiv · Oct 5, 2026
Multimodal Wearable-Based Olfactory-Induced Emotion Recognition in Arousal-Valence Dimensions
arXiv · Aug 5, 2026