EPOC aware energy expenditure estimation with machine learning

Soljee Kim, Kyoungwoo Lee, Junga Lee, Justin Y. Jeon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In 2014, 39 % of adults were overweight, and 13 % were obese. Clearly, knowing exact energy expenditure (EE) is important for sports training and weight control. Furthermore, excess post-exercise oxygen consumption (EPOC) must be included in the total EE. This paper presents a machine learning-based EE estimation approach with EPOC for aerobic exercise using a heart rate sensor. On a dataset acquired from 33 subjects, we apply machine learning algorithms using Weka machine learning toolkit. We could achieve 0.88 correlation and 0.23 kcal/min root mean square error (RMSE) with linear regression. The proposed model could be applied to various wearable devices such as a smartwatch.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1585-1590
Number of pages6
ISBN (Electronic)9781509018970
DOIs
Publication statusPublished - 2017 Feb 6
Event2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Budapest, Hungary
Duration: 2016 Oct 92016 Oct 12

Publication series

Name2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings

Other

Other2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016
Country/TerritoryHungary
CityBudapest
Period16/10/916/10/12

Bibliographical note

Funding Information:
This research was supported in part by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and future Planning (NRF-2015R1A2A1A15053435), by Next-Generation Information Computing Development Program through the NRF funded by the Ministry of Science, ICT Future Planning (NRF-2015M3C4A7065522), by MSIP under the Research Project on High Performance and Scalable Manycore Operating System (#14-824-09-011), by Samsung Electronics Co. Ltd., and by LG Electronics Mobile Communications Company.

Publisher Copyright:
© 2016 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Control and Optimization
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'EPOC aware energy expenditure estimation with machine learning'. Together they form a unique fingerprint.

Cite this