{"ID":2895119,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14185","arxiv_id":"2507.14185","title":"Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.14185","url_pdf":"https://arxiv.org/pdf/2507.14185v1","authors":"[\"Abdullah Ahmed\",\"Jeremy Gummeson\"]","published":"2025-07-13T02:58:48Z","proceeding":"eess.SP","tasks":"[\"eess.SP\",\"cs.LG\"]","methods":"[]","has_code":false}