arXiv AI August 26, 2026 By Skye Goodman, Roussel Desmond Nzoyem, Leandro Junges, Peter Kissack, Yasser Qureshi, Amberly Brigden, Jeff Clark, Nawid Keshtmand

Evaluating Deep Multivariate Imputation Models on Wearable Device Data

Read the original on arXiv AI →

The paper introduces a new evaluation protocol for deep multivariate imputation models on wearable device data, addressing the issue of structured missingness where sensor features drop out together. Using a Garmin smartwatch dataset from an epilepsy patient, the authors generate realistic block-missing patterns from training data and show that matching the training protocol to this distribution reduces BRITS’ mean absolute error by 43%. They also extend BRITS with time‑of‑day encoding and compare it to linear interpolation and SAITS, finding that no single model dominates and that model rankings vary with evaluation design.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 5

PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data

arXiv:2606. 06328v1 Announce Type: new Abstract: In healthcare, multimodal time series tasks often operate on incomplete observations in practice, for example when ECG segments are lost because electrodes detach or an entire respiratory channel is unavailable during overnight monitoring.

By Ziwen Kan, Wugeng Zheng, Tianlong Chen, Song Wang

rag diffusion multimodal benchmarks

arXiv Machine Learning

Jul 23

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

arXiv:2607. 20027v1 Announce Type: new Abstract: Short-term Heart Rate Variability (HRV) forecasting could provide clinicians with actionable lead time for detecting autonomic dysfunction and adverse cardiac events.

By Luukas Per\"akyl\"a, Fahad Sohrab, Ville Hautam\"aki, Merja Hein\"aniemi, Sui Huang, Pekka Abrahamsson

fine-tuning

arXiv AI

Aug 24

Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness

The paper introduces Curriculum‑Aware Interpolate‑then‑Refine (CAIR), a two‑stage framework for imputing physiological time‑series data. CAIR first learns a coarse base curve with a bidirectional‑GRU interpolator and then refines it through three Transformer passes, trained under a random‑gap curriculum that mimics realistic missingness. Evaluations on continuous glucose monitoring and arterial pressure datasets show CAIR outperforms all baselines across MCAR, MAR, and NMAR mechanisms, especially for long gaps and value‑dependent dropout, while also preserving clinically relevant burden metrics.

By Yu-Chao Huang, Haochen Zhang, Nicholas Konz, Tianlong Chen

llms benchmarks

arXiv AI

Jul 21

OpenMHC: Accelerating the Science of Wearable Foundation Models

arXiv:2607. 16235v1 Announce Type: cross Abstract: Mobile and wearable devices offer an unprecedented opportunity for continuous, passive health monitoring and active health coaching.

By Narayan Schuetz, Yuze Bai, Lianggang Pan, Edgar Eggert, Favour Nerrise, Juan Delgado-SanMartin, Max Rosenblattl, Milana Gurbanova, Mohammad Asadi, Anders Johnson, Paul Schmiedmayer, Dennis Wang, Allan Lawrie, Daniel Seung Kim, Xin Liu, Akshay Paruchuri, Ehsan Adeli, Euan Ashley, Kelly W. Zhang

benchmarks

arXiv Machine Learning

Jul 31

HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data

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.

By Xiaotong Yu, Joshua Y. Kim, HaeJin Lee, Kalina Yacef

llms safety

arXiv Machine Learning

Aug 7

MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health

arXiv:2506. 02260v5 Announce Type: replace-cross Abstract: Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data.

By Howon Ryu, Yuliang Chen, Yacun Wang, Andrea Z. LaCroix, Chongzhi Di, Loki Natarajan, Yu Wang, Jingjing Zou

llms multimodal benchmarks

One email a morning, machine-written

Related stories

PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data

Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models

Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness

OpenMHC: Accelerating the Science of Wearable Foundation Models

HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data

MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health