Fine-tuning the UniTS time-series foundation model with context and masking yields a wearable health anomaly detector that claims about 22% F1 improvement over 12 anomaly detection baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AI on the Pulse: Real-Time Health Anomaly Detection with Wearable and Ambient Intelligence
Fine-tuning the UniTS time-series foundation model with context and masking yields a wearable health anomaly detector that claims about 22% F1 improvement over 12 anomaly detection baselines.