Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 29994
Metabolic Predictive Model for PMV Control Based on Deep Learning

Authors: Eunji Choi, Borang Park, Youngjae Choi, Jinwoo Moon

Abstract:

In this study, a predictive model for estimating the metabolism (MET) of human body was developed for the optimal control of indoor thermal environment. Human body images for indoor activities and human body joint coordinated values were collected as data sets, which are used in predictive model. A deep learning algorithm was used in an initial model, and its number of hidden layers and hidden neurons were optimized. Lastly, the model prediction performance was analyzed after the model being trained through collected data. In conclusion, the possibility of MET prediction was confirmed, and the direction of the future study was proposed as developing various data and the predictive model.

Keywords: Deep learning, indoor quality, metabolism, predictive model.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1317252

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF

References:

REFERENCES
[1] Bo Rang Park, Eun Ji Choi, Young Kwon Yang, Jin Woo Moon, “Preliminary study on the PMV contents using ANN-Based MET Estimation”, EES2017, 2017.
[2] ASHRAE, ANSI/ASHRAE Standard 55, 2013.
[3] Artificial Neural Network and Machine Learning, NVIDIA, http://nvidia.co.kr.
[4] Yea Eun. Ku, Tae Kyung. Kwon, “Research Trend of Next-Generation User Authentication based on Machine Learning”, The Korean Institute of Information Scientists and Engineers, Vol. 36, No. 2, 2018, pp. 43-48.
[5] Bo Rang Park, Eun Ji Choi, Hyo Eun Lee, Tae Won Kim, Jin Woo Moon, “Research Trends for the Deep Learning-based Metabolic Rate Calculation”, KIEAE, Vol. 17, No. 5, 2017, pp.95-100.
[6] Matthew D. Zeiler, “Adadelta: an adaptive learning rate method”, arXiv:1212.5701, 2012.