Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network
Davidson, P., Trinh, H., Vekki, S., & Müller, P. (2023). Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network. Sensors, 23(4), Article 2249. https://doi.org/10.3390/s23042249
Published in
SensorsDate
2023Copyright
© 2023 by the authors. Licensee MDPI, Basel, Switzerland.
Oxygen uptake (V̇O2) is an important metric in any exercise test including walking and running. It can be measured using portable spirometers or metabolic analyzers. Those devices are, however, not suitable for constant use by consumers due to their costs, difficulty of operation and their intervening in the physical integrity of their users. Therefore, it is important to develop approaches for the indirect estimation of V̇O2 -based measurements of motion parameters, heart rate data and application-specific measurements from consumer-grade sensors. Typically, these approaches are based on linear regression models or neural networks. This study investigates how motion data contribute to V̇O2 estimation accuracy during unconstrained running and walking. The results suggest that a long short term memory (LSTM) neural network can predict oxygen consumption with an accuracy of 2.49 mL/min/kg (95% limits of agreement) based only on speed, speed change, cadence and vertical oscillation measurements from an inertial navigation system combined with a Global Positioning System (INS/GPS) device developed by our group, worn on the torso. Combining motion data and heart rate data can significantly improve the V̇O2 estimation resulting in approximately 1.7–1.9 times smaller prediction errors than using only motion or heart rate data.
...
Publisher
MDPI AGISSN Search the Publication Forum
1424-8220Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/176980876
Metadata
Show full item recordCollections
- Liikuntatieteiden tiedekunta [3148]
Additional information about funding
This work was supported in part by the Academy of Finland, grants 287295 (under consortium “OpenKin: Sensor fusion for kinesiology research”) and 323472 (under consortium “GaitMaven: Machine learning for gait analysis and performance prediction").License
Related items
Showing items with similar title or keywords.
-
Recent advances in machine learning for maximal oxygen uptake (VO2 max) prediction : A review
Ashfaq, Atiqa; Cronin, Neil; Müller, Philipp (Elsevier, 2022)Maximal oxygen uptake ( max) is the maximum amount of oxygen attainable by a person during exercise. max is used in different domains including sports and medical sciences and is usually measured during an incremental ... -
A New Fitness Test of Estimating VO2max in Well-Trained Rowing Athletes
Gao, Wei Dong; Nuuttila, Olli-Pekka; Fang, Hai Bo; Chen, Qian; Chen, Xi (Frontiers Media SA, 2021)Background: This study was designed to investigate the validity of maximal oxygen consumption (VO2max) estimation through the Firstbeat fitness test (FFT) method when using submaximal rowing and running programs for ... -
Technical Performance Metrics of a Security Operations Center
Forsberg, Joonas; Frantti, Tapio (Elsevier, 2023)This research introduces a novel framework for creating metrics intended for security operations centers (SOCs). The framework is developed using the design science research methodology and has been validated by generating ... -
Estimating intra- and inter-subject oxygen consumption in outdoor human gait using multiple neural network approaches
Müller, Philipp; Pham-Dinh, Khoa; Trinh, Huy; Rauhameri, Anton; Cronin, Neil J. (Public Library of Science, 2024)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 ... -
Evaluating the predictive performance of presence–absence models : Why can the same model appear excellent or poor?
Abrego, Nerea; Ovaskainen, Otso (John Wiley & Sons, 2023)When comparing multiple models of species distribution, models yielding higher predictive performance are clearly to be favored. A more difficult question is how to decide whether even the best model is “good enough”. Here, ...