TY - GEN
T1 - Machine Learning Predictive Model for Performance Criteria of Energy-Efficient Healthy Building
AU - Sari, Mustika
AU - Berawi, Mohammed Ali
AU - Zagloel, Teuku Yuri
AU - Amatkasmin, Louferinio Royanto
AU - Susantono, Bambang
N1 - Funding Information:
Acknowledgements. The authors would like to thank the Ministry of Education, Culture, Research, and Technology, Republic of Indonesia, for the support given to this research.
Publisher Copyright:
© 2022, Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Energy efficiency and occupant wellbeing are complex concepts increasingly becoming a mainstream building and construction industry focal point. These concepts demand deciding not only the appropriate building materials, techniques, and systems but also abstract qualities, which are challenging to quantify. As recent automation technologies have advanced, the building and construction sector is experiencing rapid progress, bringing about efficient building development methods. However, building design needs an efficient computerized design tool that enables designers to make more reliable decisions to help achieve the intended quality objectives of the buildings. This paper aims to explore the data preparation of energy-efficient and healthy buildings to be utilized in a machine learning (ML) model that can accurately predict the determination of the building variables. The generalized data used in this study were quantified, analyzed, and processed before being utilized in the machine learning model developed using Support Vector Regression (SVR) and Multi Layer Perceptron (MLP) algorithms. The accuracy of the models was evaluated using the Mean Absolute Error (MAE). The outcome of this study shows that the predictive machine learning model could help decision-makers quantitatively predict the healthy building variables to an adequate level of accuracy.
AB - Energy efficiency and occupant wellbeing are complex concepts increasingly becoming a mainstream building and construction industry focal point. These concepts demand deciding not only the appropriate building materials, techniques, and systems but also abstract qualities, which are challenging to quantify. As recent automation technologies have advanced, the building and construction sector is experiencing rapid progress, bringing about efficient building development methods. However, building design needs an efficient computerized design tool that enables designers to make more reliable decisions to help achieve the intended quality objectives of the buildings. This paper aims to explore the data preparation of energy-efficient and healthy buildings to be utilized in a machine learning (ML) model that can accurately predict the determination of the building variables. The generalized data used in this study were quantified, analyzed, and processed before being utilized in the machine learning model developed using Support Vector Regression (SVR) and Multi Layer Perceptron (MLP) algorithms. The accuracy of the models was evaluated using the Mean Absolute Error (MAE). The outcome of this study shows that the predictive machine learning model could help decision-makers quantitatively predict the healthy building variables to an adequate level of accuracy.
KW - Healthy building
KW - Machine learning
KW - Performance criteria
KW - Predictive model
UR - http://www.scopus.com/inward/record.url?scp=85136991127&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-14985-6_8
DO - 10.1007/978-3-031-14985-6_8
M3 - Conference contribution
AN - SCOPUS:85136991127
SN - 9783031149849
T3 - Communications in Computer and Information Science
SP - 112
EP - 132
BT - Innovations in Digital Economy - Third International Scientific Conference, SPBPU IDE 2021, Revised Selected Papers
A2 - Rodionov, Dmitrii
A2 - Kudryavtseva, Tatiana
A2 - Skhvediani, Angi
A2 - Berawi, Mohammed Ali
PB - Springer Science and Business Media Deutschland GmbH
T2 - 3rd International Conference on Innovations in Digital Economy, SPBU IDE 2021
Y2 - 14 October 2021 through 15 October 2021
ER -
