Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Accurate estimation of Energy Expenditure (EE) in ambulatory settings provides greater insight into the underlying relation between different human physical activity and health. This paper describes the development and validation of energy expenditure estimation algorithms. A total of 4 healthy subjects and 3 suffering from multiple sclerosis were monitored using a gold-standard energy expenditure measurement system, a heart rate monitor and accelerometry. We demonstrated that greater improvements can be achieved by estimating energy expenditure during normal activities of daily living by combining both whole body acceleration estimates, vertical body acceleration estimates, body posture and heart rate data as part of a flex heart rate algorithm in subject specific models when compared to using accelerometry or heart rate data alone. This will allow more accurate EE estimation during normal activities of daily living.
Felix Naef, Nicholas Edward Phillips