← Back to all news
arXiv AI 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.

Related stories

arXiv AI
Sep 16

SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals

SOTER is a generative foundation model designed for wearable physiological time‑series data. It integrates cross‑channel coupling, spectrum‑guided expert specialization, and continuous‑time latent evolution, using a spatial feature‑aware backbone, a PSD‑guided mixture‑of‑experts layer, and a neural controlled differential equation decoder. Trained on 226 billion time points from five public datasets, SOTER outperforms baselines in zero‑shot forecasting, classification, and imputation across six benchmarks, and remains robust to additive noise.

By Fangke Chen, Sirry Chen, Wei Chen, Zhongyu Wei
benchmarks
More like this →
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
llmsbenchmarks
More like this →