Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908455852310528 |
|---|---|
| author | Ahmed, Abdullah Gummeson, Jeremy |
| author_facet | Ahmed, Abdullah Gummeson, Jeremy |
| contents | Latent spaces offer an efficient and effective means of summarizing data while implicitly preserving meta-information through relational encoding. We leverage these meta-embeddings to develop a modality-agnostic, unified encoder. Our method employs sensor-latent fusion to analyze and correlate multimodal physiological signals. Using a compressed sensing approach with autoencoder-based latent space fusion, we address the computational challenges of biosignal analysis on resource-constrained devices. Experimental results show that our unified encoder is significantly faster, lighter, and more scalable than modality-specific alternatives, without compromising representational accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices Ahmed, Abdullah Gummeson, Jeremy Signal Processing Machine Learning Latent spaces offer an efficient and effective means of summarizing data while implicitly preserving meta-information through relational encoding. We leverage these meta-embeddings to develop a modality-agnostic, unified encoder. Our method employs sensor-latent fusion to analyze and correlate multimodal physiological signals. Using a compressed sensing approach with autoencoder-based latent space fusion, we address the computational challenges of biosignal analysis on resource-constrained devices. Experimental results show that our unified encoder is significantly faster, lighter, and more scalable than modality-specific alternatives, without compromising representational accuracy. |
| title | Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2507.14185 |