← khoaphamdinh.com

Estimating intra- and inter-subject oxygen consumption in outdoor human gait using multiple neural network approaches

Philipp Müller†,1, Khoa Pham-Dinh†,1, Huy Trinh1, Anton Rauhameri2, Neil J. Cronin3

1Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland · 2Faculty of Medicine and Health Sciences, Tampere University, Tampere, Finland · 3Faculty of Sport and Health Sciences, University of Jyväskylä, Jyväskylä, Finland

†Philipp Müller and Khoa Pham-Dinh contributed equally to this work.

PLOS ONE 19(9): e0303317 — published 27 September 2024.

DOI: 10.1371/journal.pone.0303317

Read the article at PLOS →

Abstract

Oxygen consumption (VO2) is an important measure for exercise test, such as walking and running, that can be measured outdoors using portable spirometers or metabolic analyzers. However, these devices are not feasible for regular use by consumers as they intervene with the user’s physical integrity, and are expensive and difficult to operate. To circumvent these drawbacks, indirect estimation of VO2 using neural networks combined with motion features and heart rate measurements collected with consumer-grade sensors has been shown to yield reasonably accurate VO2 for intra-subject estimation. However, estimating VO2 with neural networks trained with data from other individuals than the user, known as inter-subject estimation, remains an open problem. In this paper, five types of neural network architectures were tested in various configurations for inter-subject VO2 estimation. To analyse predictive performance, data from 16 participants walking and running at speeds between 1.0 m/s and 3.3 m/s were used. The most promising approach was Xception network, which yielded average estimation errors as low as 2.43 ml×min−1×kg−1, suggesting that it could be used by athletes and running enthusiasts for monitoring their oxygen consumption over time to detect changes in their movement economy.

Licence

This article is fully open access. PLOS publishes it under the Creative Commons Attribution 4.0 International licence (CC BY 4.0), which lets anyone read, download, redistribute and build on the work, including commercially, as long as the original authors and source are credited.

BibTeX

@article{muller2024oxygen,
  author  = {M\"{u}ller, Philipp and Pham-Dinh, Khoa and Trinh, Huy and
             Rauhameri, Anton and Cronin, Neil J.},
  title   = {Estimating intra- and inter-subject oxygen consumption in outdoor
             human gait using multiple neural network approaches},
  journal = {PLOS ONE},
  volume  = {19},
  number  = {9},
  pages   = {e0303317},
  year    = {2024},
  doi     = {10.1371/journal.pone.0303317}
}