arXiv Machine Learning

Autoencoder Architectures for Athlete Performance Scoring from Wearable Telemetry

arXiv:2606. 28145v1 Announce Type: new Abstract: Wearable devices produce large, high dimensional training logs for everyday runners, and interpretation rather than data collection is now the limiting step.

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

arXiv AI

Aug 26

Evaluating Deep Multivariate Imputation Models on Wearable Device Data

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.

By Skye Goodman, Roussel Desmond Nzoyem, Leandro Junges, Peter Kissack, Yasser Qureshi, Amberly Brigden, Jeff Clark, Nawid Keshtmand

multimodal benchmarks

Hugging Face Trending Papers

Sep 15

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

Time-series foundation models have demonstrated strong cross-domain transfer, yet their common architectural assumptions remain poorly aligned with wearable physiological signals, which are multichann...

benchmarks

arXiv AI

Jun 2

Adaptive data selection improves wearable prediction under low baseline performance

arXiv:2606. 00141v1 Announce Type: cross Abstract: Adaptive sensing strategies that selectively sample data are increasingly used in wearable health systems to improve prediction performance under limited data budgets, yet their benefits across individuals remain poorly understood.

By Ali Kargarandehkordi

arXiv Machine Learning

Jul 31

ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders

arXiv:2607. 27404v1 Announce Type: new Abstract: Existing benchmarks for electrocardiogram foundation models primarily evaluate downstream predictive performance, providing limited insight into whether their internal representations can be faithfully decomposed, clinically interpreted, or reproduced across independent analyses.

By Yixuan Duan, Wei Qiu

efficiency benchmarks safety

arXiv AI

Jun 2

A Foundation Model for Wearable Movement Data in Mental Health Research

arXiv:2411. 15240v5 Announce Type: replace-cross Abstract: Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, reflecting fine-grained temporal behavioral trends.

By Franklin Y. Ruan, Aiwei Zhang, Jenny Y. Oh, SouYoung Jin, Nicholas C. Jacobson

llms rag

arXiv AI

Aug 10

Omni-modal decomposition autoencoders learn full-stack wearable disentangled representations

arXiv:2608. 07385v1 Announce Type: cross Abstract: Learning disentangled representations is a key requirement for developing versatile, general-purpose, and sustainable models in multi-modal wearable computing.

By Ioannis Ziogas, Ensieh Khazaei, Bilal Taha, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis, Dimitrios Hatzinakos

llms multimodal

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

Jun 8

A robust PPG foundation model using multimodal physiological supervision

arXiv:2606. 07365v1 Announce Type: cross Abstract: Photoplethysmography (PPG), a non-invasive measure of changes in blood volume, is widely used in both wearable devices and clinical settings.

By Eloy Geenjaar, Vince Calhoun, Scott Daly, Gouthaman KV, Lie Lu, Trisha Mittal, Daniel P. Darcy

multimodal 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

Sep 1

Target-Aware State-Adaptive $p$-Dirichlet Graph Neural Regression for Non-Invasive Body-Composition Estimation

arXiv:2608.29496v1 Announce Type: new Abstract: Accurate estimation of body-composition outcomes, including body fat percentage (BFP), bone mineral density (BMD), and appendicular lean mass (ALM), is...

By Nadejda Drenska, Matthew Lemoine, Gowri Priya Sunkara, Yu Wang, Sri Lakshmi Sravani Devarakonda, Steven B. Heymsfield

arXiv AI

Aug 11

CFD-Guided Detection of Concept Drift in Multimodal Physiologic Signals

arXiv:2608. 07759v1 Announce Type: cross Abstract: Cardiovascular AI models can classify clean elec- trocardiogram (ECG) signals, but real wearable signals change because of motion, breathing, posture, sensor contact, and true clinical deterioration.

By Farouk Ganiyu Adewumi, Timothy Oladunni, Rochak Ghimire, Kosisochukwu Ogbuanya, Sanaa Reeves, Sandy Akoy

multimodal

Related stories