Development of Occupant Pose Classification Model Using Deep Neural Network for Personalized Thermal Conditioning
Open Access
Abstract
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 office. 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 office, respectively. Thus, the potential of the pose classification model was verified for providing a more comfortable and personalized thermal environment to the occupant.Keywords
Funding Information
- Korea Institute of Energy Technology Evaluation and Planning (20182010600010)
- Chung-Ang University (Graduate Research Scholarship in 2019)
This publication has 8 references indexed in Scilit:
- Development of a Human Pose Classifying Model to Estimate the Metabolic Rate of OccupantKIEAE Journal, 2018
- A new method to study human metabolic rate changes and thermal comfort in physical exercise by CO2 measurement in an airtight chamberEnergy and Buildings, 2018
- Preferred temperature with standing and treadmill workstationsBuilding and Environment, 2018
- MEASURING METABOLIC RATE TO IMPROVE COMFORT MANAGEMENT IN BUILDINGSEnvironmental Engineering and Management Journal, 2018
- Research Trends for the Deep Learning-based Metabolic Rate CalculationKIEAE Journal, 2017
- Performance tests on the ANN model prediction accuracy for cooling load of buildings during the setback periodKIEAE Journal, 2017
- Sensitivity study for the PMV thermal comfort model and the use of wearable devices biometric data for metabolic rate estimationBuilding and Environment, 2016
- Real-time METs estimation for effective indoor amenity control in HEMS2013