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

Oxygen consumption ([Formula: see text]) 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 [Formula: see text] using neural networks combined with motion features and heart rate measurements collected with consumer-grade sensors has been shown to yield reasonably accurate [Formula: see text] for intra-subject estimation. However, estimating [Formula: see text] 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 [Formula: see text] 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.