Scholarlink

<p>Smartwatches enable longitudinal and continuous data acquisition. This has the potential to remotely monitor (changes) of the health of users. However, differences among subjects (inter-subject variability) limit a model to generalize to unseen subjects. This study focused on binary classification tasks using heart rate and step counter from smartwatches, including night/day and inactive/active classification, as well as sleep and SpO2-related (oxygen saturation) tasks. To address inter-subject variability, we explored different transforming and normalization regimes for time series including per-subject and population-based strategies. We propose a modified factorized autoencoder, which separates the data into two latent spaces capturing class-specific and subject-specific information. Our proposed generalized factorized autoencoder and triplet factorized autoencoder improved classification accuracy over the baseline from 74.8 (±&#xa0;10.5) to 83.1 (±&#xa0;5.1) and 83.4 (±&#xa0;5.3), respectively, for night/day classification, gains for inactive/active classification were modest, improving from 84.3 (±&#xa0;9.4) to 86.9 (±&#xa0;4.4) and 86.6 (±&#xa0;4.3), respectively. Our study highlights challenges of handling inter-subject variability in smartwatch data and how factorization models can be used to enable more robust and personalized health monitoring solutions for diverse populations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Tackling inter-subject variability in smartwatch data using factorization models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月23日

查看全文
  • Arman Naseri,
  • David M. J. Tax,
  • Ivo van der Bilt,
  • Marcel Reinders

摘要

Smartwatches enable longitudinal and continuous data acquisition. This has the potential to remotely monitor (changes) of the health of users. However, differences among subjects (inter-subject variability) limit a model to generalize to unseen subjects. This study focused on binary classification tasks using heart rate and step counter from smartwatches, including night/day and inactive/active classification, as well as sleep and SpO2-related (oxygen saturation) tasks. To address inter-subject variability, we explored different transforming and normalization regimes for time series including per-subject and population-based strategies. We propose a modified factorized autoencoder, which separates the data into two latent spaces capturing class-specific and subject-specific information. Our proposed generalized factorized autoencoder and triplet factorized autoencoder improved classification accuracy over the baseline from 74.8 (± 10.5) to 83.1 (± 5.1) and 83.4 (± 5.3), respectively, for night/day classification, gains for inactive/active classification were modest, improving from 84.3 (± 9.4) to 86.9 (± 4.4) and 86.6 (± 4.3), respectively. Our study highlights challenges of handling inter-subject variability in smartwatch data and how factorization models can be used to enable more robust and personalized health monitoring solutions for diverse populations.