Development of metabolic rate prediction model using deep learning via Kinect camera in an indoor environment

Hooseung Na, Taeyeon Kim

Research output: Contribution to journalConference article

Abstract

Currently, there are only a few conventional methods to measure individual factors affecting metabolic rate (MET) based on the thermal comfort of occupants in residential buildings. In this work, a deep learning based MET prediction using a Kinect camera, which is a non-contact sensor, was developed. The root mean squared error (RMSE) and the coefficient of variation (CV) of the RMSE were used as indicators to predict MET accuracy. A total of 31 subjects participated in the experiment (16 men and 15 women). The METs of eight representative activities in the ASHRAE Standard 55 were measured (lying down, sitting, cooking, walking, eating, house cleaning, folding clothes, and handling 50 kg of books). The predicted results for all eight activities were significantly high. (RMSE: 0.26, CV: 13%). Further, METs were analyzed according to the gender and body mass index (BMI). Results of the analysis based on gender reveal that METs of men are higher than those of women. Analysis based on BMI showed that MET increased with higher BMI. However, with respect to sitting and eating food, the higher the BMI, the lower is the MET. This paper suggest that, a creative method was developed herein for predicting MET in an indoor environment with fairly high accuracy. Moreover, the difference in MET considering behavior as a factor was analyzed according to gender and BMI; these results can be used to develop guidelines for more accurate thermal comfort control.

Original languageEnglish
Article number042036
JournalIOP Conference Series: Materials Science and Engineering
Volume609
Issue number4
DOIs
Publication statusPublished - 2019 Oct 23
Event10th International Conference on Indoor Air Quality, Ventilation and Energy Conservation in Buildings, IAQVEC 2019 - Bari, Italy
Duration: 2019 Sep 52019 Sep 7

Fingerprint

Thermal comfort
Cameras
Cooking
Cleaning
Sensors
Deep learning
Experiments

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Engineering(all)

Cite this

@article{29a5f8ee9428449dac28117cdac69653,
title = "Development of metabolic rate prediction model using deep learning via Kinect camera in an indoor environment",
abstract = "Currently, there are only a few conventional methods to measure individual factors affecting metabolic rate (MET) based on the thermal comfort of occupants in residential buildings. In this work, a deep learning based MET prediction using a Kinect camera, which is a non-contact sensor, was developed. The root mean squared error (RMSE) and the coefficient of variation (CV) of the RMSE were used as indicators to predict MET accuracy. A total of 31 subjects participated in the experiment (16 men and 15 women). The METs of eight representative activities in the ASHRAE Standard 55 were measured (lying down, sitting, cooking, walking, eating, house cleaning, folding clothes, and handling 50 kg of books). The predicted results for all eight activities were significantly high. (RMSE: 0.26, CV: 13{\%}). Further, METs were analyzed according to the gender and body mass index (BMI). Results of the analysis based on gender reveal that METs of men are higher than those of women. Analysis based on BMI showed that MET increased with higher BMI. However, with respect to sitting and eating food, the higher the BMI, the lower is the MET. This paper suggest that, a creative method was developed herein for predicting MET in an indoor environment with fairly high accuracy. Moreover, the difference in MET considering behavior as a factor was analyzed according to gender and BMI; these results can be used to develop guidelines for more accurate thermal comfort control.",
author = "Hooseung Na and Taeyeon Kim",
year = "2019",
month = "10",
day = "23",
doi = "10.1088/1757-899X/609/4/042036",
language = "English",
volume = "609",
journal = "IOP Conference Series: Materials Science and Engineering",
issn = "1757-8981",
publisher = "IOP Publishing Ltd.",
number = "4",

}

Development of metabolic rate prediction model using deep learning via Kinect camera in an indoor environment. / Na, Hooseung; Kim, Taeyeon.

In: IOP Conference Series: Materials Science and Engineering, Vol. 609, No. 4, 042036, 23.10.2019.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Development of metabolic rate prediction model using deep learning via Kinect camera in an indoor environment

AU - Na, Hooseung

AU - Kim, Taeyeon

PY - 2019/10/23

Y1 - 2019/10/23

N2 - Currently, there are only a few conventional methods to measure individual factors affecting metabolic rate (MET) based on the thermal comfort of occupants in residential buildings. In this work, a deep learning based MET prediction using a Kinect camera, which is a non-contact sensor, was developed. The root mean squared error (RMSE) and the coefficient of variation (CV) of the RMSE were used as indicators to predict MET accuracy. A total of 31 subjects participated in the experiment (16 men and 15 women). The METs of eight representative activities in the ASHRAE Standard 55 were measured (lying down, sitting, cooking, walking, eating, house cleaning, folding clothes, and handling 50 kg of books). The predicted results for all eight activities were significantly high. (RMSE: 0.26, CV: 13%). Further, METs were analyzed according to the gender and body mass index (BMI). Results of the analysis based on gender reveal that METs of men are higher than those of women. Analysis based on BMI showed that MET increased with higher BMI. However, with respect to sitting and eating food, the higher the BMI, the lower is the MET. This paper suggest that, a creative method was developed herein for predicting MET in an indoor environment with fairly high accuracy. Moreover, the difference in MET considering behavior as a factor was analyzed according to gender and BMI; these results can be used to develop guidelines for more accurate thermal comfort control.

AB - Currently, there are only a few conventional methods to measure individual factors affecting metabolic rate (MET) based on the thermal comfort of occupants in residential buildings. In this work, a deep learning based MET prediction using a Kinect camera, which is a non-contact sensor, was developed. The root mean squared error (RMSE) and the coefficient of variation (CV) of the RMSE were used as indicators to predict MET accuracy. A total of 31 subjects participated in the experiment (16 men and 15 women). The METs of eight representative activities in the ASHRAE Standard 55 were measured (lying down, sitting, cooking, walking, eating, house cleaning, folding clothes, and handling 50 kg of books). The predicted results for all eight activities were significantly high. (RMSE: 0.26, CV: 13%). Further, METs were analyzed according to the gender and body mass index (BMI). Results of the analysis based on gender reveal that METs of men are higher than those of women. Analysis based on BMI showed that MET increased with higher BMI. However, with respect to sitting and eating food, the higher the BMI, the lower is the MET. This paper suggest that, a creative method was developed herein for predicting MET in an indoor environment with fairly high accuracy. Moreover, the difference in MET considering behavior as a factor was analyzed according to gender and BMI; these results can be used to develop guidelines for more accurate thermal comfort control.

UR - http://www.scopus.com/inward/record.url?scp=85074411491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074411491&partnerID=8YFLogxK

U2 - 10.1088/1757-899X/609/4/042036

DO - 10.1088/1757-899X/609/4/042036

M3 - Conference article

AN - SCOPUS:85074411491

VL - 609

JO - IOP Conference Series: Materials Science and Engineering

JF - IOP Conference Series: Materials Science and Engineering

SN - 1757-8981

IS - 4

M1 - 042036

ER -