#wearable-sensors News & Analysis

5 articles tagged with #wearable-sensors. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AINeutralarXiv – CS AI · Jun 256/10

🧠

BCoughBench: Benchmarking Respiratory Acoustic Foundation Models Under Body-Coupled Wearable Sensor Conditions

BCoughBench introduces a standardized evaluation framework for respiratory acoustic foundation models deployed on body-coupled wearable sensors, revealing significant performance degradation compared to smartphone recordings. The study demonstrates that existing models fail to meet clinical thresholds for disease detection when adapted to wearable conditions, though demographic tasks like age regression remain robust.

AINeutralarXiv – CS AI · Jun 95/10

🧠

A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumatic and Non-Phonotraumatic Vocal Hyperfunction

Researchers developed a hierarchical feature engineering framework to classify vocal hyperfunction subtypes using non-invasive neck-surface acceleration monitoring. The machine learning approach achieved 89.1% AUC for phonotraumatic cases and 72.8% for non-phonotraumatic cases, with coupling features proving crucial for distinguishing both conditions from healthy controls.

AINeutralarXiv – CS AI · May 126/10

🧠

WavesFM: Hierarchical Representation Learning for Longitudinal Wearable Sensor Waveforms

Researchers introduce WavesFM, a foundation model using hierarchical self-supervised learning to extract health insights from continuous wearable sensor data. Trained on 6.8M hours of physiological recordings from 324k individuals, the model captures both local waveform patterns and long-term behavioral dynamics, demonstrating strong performance across 58 health-related prediction tasks.

AIBullishGoogle Research Blog · Jul 286/107

🧠

SensorLM: Learning the language of wearable sensors

SensorLM represents a breakthrough in generative AI applied to wearable sensor data, enabling AI systems to understand and process the complex language of sensor inputs from devices like smartwatches and fitness trackers. This development could revolutionize how AI interprets biometric and movement data for healthcare, fitness, and human-computer interaction applications.

AINeutralGoogle Research Blog · Jul 224/105

🧠

LSM-2: Learning from incomplete wearable sensor data

LSM-2 is a research development focused on learning from incomplete wearable sensor data using generative AI approaches. This represents an advancement in handling sparse or missing data from wearable devices through machine learning techniques.