Development of occupant pose classification model using deep neural network for personalized thermal conditioning

  • Choi E.J.; 
  • Yoo Y.; 
  • Park B.R.; 
  • Choi Y.J.; 
  • Moon J.W.
Citations

WEB OF SCIENCE

11
Citations

SCOPUS

17

초록

This study aims to propose a pose classification model using indoor occupant images. For developing the intelligent and automated model, a deep learning neural network was employed. Indoor posture images and joint coordinate data were collected and used to conduct the training and optimization of the model. The output of the trained model is the occupant pose of the sedentary activities in the indoor space. The performance of the developed model was evaluated for two different indoor environments: Home and offce. Using the metabolic rates corresponding to the classified poses, the model accuracy was compared with that of the conventional method, which considered the fixed activity. The result showed that the accuracy was improved by as much as 73.96% and 55.26% in home and offce, respectively. Thus, the potential of the pose classification model was verified for providing a more comfortable and personalized thermal environment to the occupant. © 2019 by the authors.

키워드

Deep neural network; Pose classification; Thermal environment; Computer science; Energy management; Automated modeling; Conventional methods; Indoor environment; Joint coordinates; Learning neural networks; Pose classifications; Thermal conditioning; Thermal environment; Deep neural networks
제목
Development of occupant pose classification model using deep neural network for personalized thermal conditioning
저자
Choi E.J.; Yoo Y.; Park B.R.; Choi Y.J.; Moon J.W.
DOI
10.3390/en13010045
발행일
2020-01
유형
Article
저널명
Energies
권
13
호
1

파일 다운로드

Thumbnail