Physiological and wearable signal modeling for emotion recognition.
| Approach/Model | Input signals | Main function | Typical applications | Key challenges | Ref. |
|---|---|---|---|---|---|
| Recurrent and transfer learning models (LSTM, CNN-BiLSTM, transfer learning) | ECG, PPG, GSR, temperature, respiration, accelerometry | Temporal modeling and cross-modal generalization of physiological time series | Emotion recognition, stress detection, cognitive load monitoring, wearable health inference | Motion artifacts, inter-individual variability, non-stationarity, domain shift | [42–47] |
| Signal processing and feature extraction approaches | Primarily PPG and related wearable biosignals | Signal denoising, compression, and improvement of signal quality | Preprocessing for wearable-based monitoring and downstream classification tasks | Sensitivity to real-world noise, reduced robustness under motion, and low signal-to-noise conditions | [48] |
| Multimodal foundation models (e.g., NormWear) | Multivariate physiological signals (e.g., ECG, PPG, GSR, EEG) | Learning transferable representations across tasks and populations | Emotion recognition, stress detection, sleep analysis, zero-shot/few-shot wearable sensing | High training cost, data heterogeneity, potential bias, and limited clinical validation | [49] |
| Self-supervised learning (SSL) | Unlabeled physiological and wearable biosignals, especially PPG | Learning latent representations through reconstruction-based or related pretext tasks | Scalable wearable biosignal modeling with limited annotation requirements | Defining suitable pretext objectives, interpretability, and downstream transferability | [50] |
LSTM: long short-term memory; CNN: convolutional neural network; BiLSTM: bidirectional LSTM; ECG: electrocardiography; PPG: photoplethysmography; GSR: galvanic skin response; EEG: electroencephalography.
MC: Resources, Data curation, Formal analysis, Software. AZ: Resources, Data curation, Formal analysis, Software. OP: Conceptualization, Formal analysis, Data curation. CG: Investigation, Visualization. FDL: Formal analysis, Supervision. V Cerrone and AZ: Validation, Formal analysis, Writing—original draft, Writing—review & editing. AF: Methodology, Investigation. V Conti: Software, Formal analysis. GP and SC: Methodology, Software. FS, RDF, and DE: Conceptualization, Formal analysis. MPB: Validation, Investigation. All authors read and approved the submitted version.
Marco Cascella, who is the Editorial Board Member and Guest Editor of Exploration of Medicine, had no involvement in the decision-making or the review process of this manuscript. The other authors declare no conflicts of interest.
Not applicable.
Not applicable.
Not applicable.
This study does not involve original data; all data analyzed are publicly available and have been appropriately cited.
This research received no external funding.
© The Author(s) 2026.
Open Exploration maintains a neutral stance on jurisdictional claims in published institutional affiliations and maps. All opinions expressed in this article are the personal views of the author(s) and do not represent the stance of the editorial team or the publisher.