arXiv:2608. 02946v1 Announce Type: new Abstract: Accurate detection of sedentary behavior is important for studying health risks related to prolonged sitting, but posture-based classification remains challenging with wearable sensors, especially at the wrist.
arXiv:2607. 27635v1 Announce Type: cross Abstract: Wearable sensors continuously capture fine-grained multivariate time-series data, providing opportunities to model behavioural patterns associated with health outcomes.
arXiv:2608. 15861v1 Announce Type: new Abstract: Fine-grained wrist activity recognition can support applications such as procedural step guidance and context-aware assistance, yet acquiring labeled data for every new task, user, and activity granularity remains a bottleneck.
arXiv:2608. 13316v1 Announce Type: cross Abstract: Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking.
The paper introduces Sensori, a self‑supervised foundation model that learns health representations from 24‑hour raw tri‑axial wrist movement data. Trained on 122,640 participants across the UK, China, and the US, Sensori captures diverse movement behaviours, demographics, health axes, and physical function. In independent cohorts, the model improved disease classification for 52 of 102 conditions and incident disease risk prediction for 26 of 87 conditions, especially for neurological and psychiatric disorders.
arXiv:2607. 06617v1 Announce Type: cross Abstract: Wearable motion sensing provides a continuous and scalable window into human behavior and health, making it a natural fit for foundation models, yet its pretraining and scaling principles remain poorly understood.
arXiv:2607. 26631v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments.
arXiv:2606. 04798v1 Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and sensor placement.
Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments. Yet, existing deep learning approaches require dataset-specific training, large labeled corpora, and repeated adaptation to new sensor settings or activity taxonomies.
arXiv:2411. 15240v5 Announce Type: replace-cross Abstract: Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, reflecting fine-grained temporal behavioral trends.
arXiv:2608. 15621v1 Announce Type: new Abstract: Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching inertial measurement units (IMUs) across sessions.
arXiv:2507. 21018v2 Announce Type: replace-cross Abstract: Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress.
The paper investigates the use of Zero Cost Proxies (ZCPs) to identify high‑performing wearable Human Activity Recognition (HAR) models without full training. Eight ZCPs were evaluated across six benchmark HAR datasets, showing that the top‑predicted architectures achieve performance within 7% of fully trained models, and training the top‑10 predictions reaches within 2% of full training. This demonstrates that ZCPs can significantly reduce computational costs while maintaining competitive accuracy in sensor‑based HAR tasks.