Prediction of the human metabolic rate based on AI and the Kinect camera

Hooseung Na, Hoseong Kim, Hyungkeun Kim, Hyeran Byun, Taeyeon Kim

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

Abstract

Human thermal comfort is evaluated based on the air temperature, humidity, air velocity, radiative temperature, clothing condition, and metabolic rate. Among these, the metabolic rate is determined by various human behaviors, such as sleep, rest, and exercise. It is difficult to measure the metabolic rate, however, using the conventional sensors, and expensive equipment is needed for precise measurement. Many studies have been conducted of late to come up with an easier method of predicting the metabolic rate. In this paper, a method of estimating the metabolism using a Kinect camera and artificial intelligence (AI), which can measure the metabolic rate easily, is proposed. In the experiment in this study, the subjects were made to assume the positions of lying down, sitting, walking, and running. The results of the measurement and prediction through AI are compared in this paper.

Original languageEnglish
Title of host publication15th Conference of the International Society of Indoor Air Quality and Climate, INDOOR AIR 2018
PublisherInternational Society of Indoor Air Quality and Climate
ISBN (Electronic)9781713826514
Publication statusPublished - 2018
Event15th Conference of the International Society of Indoor Air Quality and Climate, INDOOR AIR 2018 - Philadelphia, United States
Duration: 2018 Jul 222018 Jul 27

Publication series

Name15th Conference of the International Society of Indoor Air Quality and Climate, INDOOR AIR 2018

Conference

Conference15th Conference of the International Society of Indoor Air Quality and Climate, INDOOR AIR 2018
CountryUnited States
CityPhiladelphia
Period18/7/2218/7/27

Bibliographical note

Funding Information:
In this paper, a method of predicting the metabolic rate using a Kinect camera and artificial intelligence (AI) is proposed. The metabolic rate obtained from the heart rate measurement was in good agreement with the predicted value, but there was some difference at a high metabolic rate. If the number of experimenters and the learning time will be increased and made sufficient, the prediction of the indoor metabolic rate is expected to be more precise. ACKNOWLEDGEMENT This research was supported by Basic Science Research Program through a National Research Foundation of Korea (NRF) grant funded by the Ministry of Science and ICT (NRF-2017R1A2B3012914). 5. REFERENCES ASHRAE. 1992. ANSI/ASHRAE Standard 55-1992. Atlanta: ASHRAE, Inc. Fanger PO. 1970. Thermal Comfort. Copenhagen: Danish Technical Press. ISO 8996 2004, Spitzer et al. Validation and calibration of physical activity monitors in children. Obesity, 10(3), 150-157. S.M.Ceesay et al. 1989. British Journal of Nutrition, vol.61, no 2,pp.175-786.

Publisher Copyright:
© 2018 15th Conference of the International Society of Indoor Air Quality and Climate, INDOOR AIR 2018. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Pollution

Fingerprint Dive into the research topics of 'Prediction of the human metabolic rate based on AI and the Kinect camera'. Together they form a unique fingerprint.

Cite this