Leveraging Foundational Models and Simple Fusion for Multi-modal Physiological Signal Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912770830630912 |
|---|---|
| author | Ghallab, Youssef Iraqy, Omar Kandil, Mohamed Ashraf, Mohamed Eletter, Saadeldine Ghazal, Morougue Khalafallah, Ayman El-Makky, Nagwa |
| author_facet | Ghallab, Youssef Iraqy, Omar Kandil, Mohamed Ashraf, Mohamed Eletter, Saadeldine Ghazal, Morougue Khalafallah, Ayman El-Makky, Nagwa |
| contents | Physiological signals such as electrocardiograms (ECG) and electroencephalograms (EEG) provide complementary insights into human health and cognition, yet multi-modal integration is challenging due to limited multi-modal labeled data, and modality-specific differences . In this work, we adapt the CBraMod encoder for large-scale self-supervised ECG pretraining, introducing a dual-masking strategy to capture intra- and inter-lead dependencies. To overcome the above challenges, we utilize a pre-trained CBraMod encoder for EEG and pre-train a symmetric ECG encoder, equipping each modality with a rich foundational representation. These representations are then fused via simple embedding concatenation, allowing the classification head to learn cross-modal interactions, together enabling effective downstream learning despite limited multi-modal supervision. Evaluated on emotion recognition, our approach achieves near state-of-the-art performance, demonstrating that carefully designed physiological encoders, even with straightforward fusion, substantially improve downstream performance. These results highlight the potential of foundation-model approaches to harness the holistic nature of physiological signals, enabling scalable, label-efficient, and generalizable solutions for healthcare and affective computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15250 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Foundational Models and Simple Fusion for Multi-modal Physiological Signal Analysis Ghallab, Youssef Iraqy, Omar Kandil, Mohamed Ashraf, Mohamed Eletter, Saadeldine Ghazal, Morougue Khalafallah, Ayman El-Makky, Nagwa Machine Learning Artificial Intelligence Physiological signals such as electrocardiograms (ECG) and electroencephalograms (EEG) provide complementary insights into human health and cognition, yet multi-modal integration is challenging due to limited multi-modal labeled data, and modality-specific differences . In this work, we adapt the CBraMod encoder for large-scale self-supervised ECG pretraining, introducing a dual-masking strategy to capture intra- and inter-lead dependencies. To overcome the above challenges, we utilize a pre-trained CBraMod encoder for EEG and pre-train a symmetric ECG encoder, equipping each modality with a rich foundational representation. These representations are then fused via simple embedding concatenation, allowing the classification head to learn cross-modal interactions, together enabling effective downstream learning despite limited multi-modal supervision. Evaluated on emotion recognition, our approach achieves near state-of-the-art performance, demonstrating that carefully designed physiological encoders, even with straightforward fusion, substantially improve downstream performance. These results highlight the potential of foundation-model approaches to harness the holistic nature of physiological signals, enabling scalable, label-efficient, and generalizable solutions for healthcare and affective computing. |
| title | Leveraging Foundational Models and Simple Fusion for Multi-modal Physiological Signal Analysis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.15250 |