@ARTICLE{Gu_Chun_Optimize_2025,
 author={Gu, Chun},
 volume={vol. 71},
 number={No 1},
 pages={615–629},
 journal={Archives of Civil Engineering},
 howpublished={online},
 year={2025},
 publisher={WARSAW UNIVERSITY OF TECHNOLOGY FACULTY OF CIVIL ENGINEERING and COMMITTEE FOR CIVIL ENGINEERING POLISH ACADEMY OF SCIENCES},
 abstract={With the increasing demand for energy efficiency optimization in the building industry, this study explores the application of machine learning technology in building energy efficiency design and evaluation. By comprehensively analyzing energy consumption data, environmental factors, building characteristics, and user behavior patterns, this paper proposes a machine learning-based approach aimed at accurately predicting and improving the energy efficiency of buildings. The study collected and pre-processed a large amount of data, built and trained multiple models, including neural networks, which showed a high degree of predictive accuracy in cross-validation. The results show that the neural network has obvious advantages in the task of building energy efficiency prediction. In addition, the interpretability of the model in practical applications and future research directions, such as the introduction of real-time monitoring data and in-depth study of the interpretability of the model, are also discussed. This study not only provides a new perspective for building energy efficiency optimization, but also provides a practical tool for intelligent building design and operation.},
 title={Optimize building energy efficiency design and evaluation with machine learning},
 type={Article},
 URL={http://ochroma.man.poznan.pl/Content/134529/PDF-MASTER/37_1k.pdf},
 doi={10.24425/ace.2025.153353},
 keywords={building energy efficiency, energy consumption forecast, energy efficiency design andevaluation, machine learning},
}