What is it about?
Human Energy Expenditure (EE) is a valuable tool for measuring physical activity and its impact on our body in an objective way. To accurately measure the EE, there are expensive and complex methods suitable only for research and professional sports. EE estimation (EEE) using machine learning from wearable devices is a prolific area of research and this article attempts to explore it in detail.
Featured Image
Photo by John Arano on Unsplash
Why is it important?
- We review and describe the state-of-the-art of energy expenditure estimation (EEE) in sufficient detail to provide a starting point for any researcher wishing to implement such a method. - We make publicly available an EEE dataset, one of the most valuable elements for developing an EEE method and comparing different approaches. - We make recommendations and highlight best practices for designing EEE methods.
Perspectives
I hope this article makes this research area interesting for new researchers, at least Google (buying Fitbit), Apple through the Apple Watch and other big companies are very interested in it. Writing this article was a great pleasure as it has co-authored with Božidara Cvetković and Mitja Luštrek, two experts in machine learning applied to activity recognition and EEE.
PhD Juan Antonio Álvarez-García
Universidad de Sevilla
Read the Original
This page is a summary of: A Survey on Energy Expenditure Estimation Using Wearable Devices, ACM Computing Surveys, October 2020, ACM (Association for Computing Machinery),
DOI: 10.1145/3404482.
You can read the full text:
Resources
Contributors
The following have contributed to this page
