University of Twente Student Theses
Estimating VO2 using peripheral and central measurements of wearable sensor data
Broeder, G. den (2025) Estimating VO2 using peripheral and central measurements of wearable sensor data.
|
PDF
1MB |
| Abstract: | Oxygen uptake (VO2) and its kinetics are important indicators of fitness and health, yet their measurement requires expensive, specialized equipment. This study aimed to validate previously achieved results in predicting VO2 and its kinetics using wearable sensors, as well as evaluating whether peripheral measurements could improve predictive accuracy. Data were collected from 14 participants performing three different pseudorandom binary sequence (PRBS) exercise tests at varying intensities. The model achieved high prediction accuracy for VO2 with a mean and best repeated-measures correlation of 0.928 and 0.943, respectively. Slightly lower than prior results, likely due to sample heterogeneity. However, predicting VO2 kinetics using the Mean Normalized Gain (MNG) method was less successful, showing no meaningful correlation. Incorporating muscle oxygenation (via near-infrared spectroscopy) and body composition data marginally improved prediction accuracy. These findings illustrate the significant potential of wearable sensors for estimating VO2 and consequently accessible fitness and health monitoring, though methodological improvements and larger datasets are still required. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 01 general works, 42 biology, 54 computer science |
| Programme: | Computer Science MSc (60300) |
| Link to this item: | https://purl.utwente.nl/essays/105347 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page