Metraipolis › archive › dc_7ab47a0aaa07

EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition — arXiv:2609.14498

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.14498
License (as archived): CC0-1.0
Archived: 2026-10-15T22:51:10.461Z
SHA-256 of the archived text: af1891c924bf2bd9240011591b7ec86f72ab08856d9d331f2c911e3744fb7b76
Stable URL of this page: https://metraipolis.com/documento/dc_7ab47a0aaa07

How to cite

EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition — arXiv:2609.14498 — arXiv (en), https://arxiv.org/abs/2609.14498 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ab47a0aaa07 (Metraipolis archive dc_7ab47a0aaa07, sha256 af1891c924bf2bd9240011591b7ec86f72ab08856d9d331f2c911e3744fb7b76)

BibTeX

@misc{dc7ab47a0aaa07,
  title = {EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition — arXiv:2609.14498},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14498},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ab47a0aaa07; sha256 af1891c924bf2bd9240011591b7ec86f72ab08856d9d331f2c911e3744fb7b76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14498. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sensor-based human activity recognition (HAR) is fundamental to ubiquitous and wearable computing, yet existing foundation models are largely designed for cloud-scale deployment and struggle with real-world sensing shifts, including unseen users, devices, sampling rates, and sensor placements. We present \textbf{EdgeHAR}, an edge-native compact sensor foundation model designed for wearable intelligence. Unlike conventional models that entangle activity knowledge with acquisition variations, EdgeHAR learns transferable representations by factorizing sensor signals into three latent codes: an \textbf{(i)Activity-Semantic Code} capturing reusable activity knowledge, a \textbf{(ii)Motion-Dynamics Code} modeling temporal patterns, and an \textbf{(iii)Acquisition-Context Code} representing sensor-specific variations. This disentangled design enables efficient adaptation to new users, devices, placements, and activity classes with limited target-domain data. By incorporating lightweight adaptation modules, EdgeHAR achieves foundation-model-level transferability while satisfying edge constraints in computation, memory, latency, and privacy. Experiments across heterogeneous HAR datasets demonstrate that EdgeHAR maintains competitive recognition performance under distribution shifts with substantially reduced deployment cost. EdgeHAR establishes a practical paradigm for compact, edge-first foundation models for ubiquitous sensing systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14498 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.680Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).