health-monitoring

OpenMHC introduces the largest open-access wearable health dataset with over 60 million hours of data and open-source implementations of wearable foundation models, including a unified benchmark for prediction, imputation, and forecasting.

This paper presents a system for non-contact, real-time heart rate measurement using commodity cameras and image processing with deep learning and AI agents, with future plans for personal AI health monitoring.

Inertia-1 is a fully open exploration of wearable motion foundation models using over 18.2 million hours of accelerometer data, systematically studying data, model, and training choices across 15 datasets for tasks like activity recognition and disease prediction.

Halter's AI-powered collars for cows enable virtual fencing and health monitoring, using GPS and sensors to manage herds remotely and detect illnesses early, now deployed on over 1 million cattle.

The article covers the development of AI-powered contact lenses that combine augmented reality, health monitoring, and AI into a normal-looking lens, with companies like XPANCEO and Mojo Vision pushing the technology forward despite significant challenges.

This paper presents a longitudinal multimodal study of 66 older adults using wearable sensing and clinical assessments to predict physical activity, sleep duration, and sleep apnea severity, finding that behavioral targets are more predictable and historical features are key predictors.

This paper evaluates adaptive data selection strategies for wearable health prediction, finding they significantly improve AUROC for participants with low baseline performance but offer limited gains for strong baselines.

Xiaomi announces the Watch S5 46mm with advanced cycling mode, dual device syncing, improved heart rate monitoring, and smarter health insights built for outdoors.

VCR is a self-supervised framework that learns robust representations from incomplete wearable signals using orthogonal tokenization and missing-aware mixture-of-experts, improving performance under modality missingness.