Inferring building function : a novel geo-aware neural network supporting building-level function classification
- Author
- Xucai Zhang (UGent) , Xiaoping Liu, Kai Chen, Fangli Guan (UGent) , Miao Luo (UGent) and Haosheng Huang (UGent)
- Organization
- Abstract
- Buildings are fundamental components of urban areas and they play a vital role in supporting human activities in daily life. Understanding the actual building functions is essential for many urban applications, such as city management, urban planning, and optimization of transportation systems. Existing studies for inferring building functions are mainly based on a building's own features, and ignore its "geographic context" (e.g., the influences of nearby buildings). This paper introduces a novel geo-aware neural network to infer the functions of individual buildings. To this end, the proposed model integrates information about the built environment and human ac-tivity of a target building and its "geographic context". The model further includes a geo-aware position embedding generator and transformer encoders to better capture the complex relationships between buildings. The evaluation results demonstrate that the proposed model outperforms all baselines and achieves a classifi-cation accuracy of 90.8%. Meanwhile, the proposed model works well even with a small amount of training dataset and has a good transferability to another urban area. In summary, the proposed model is an effective and reliable approach for inferring the functions of individual buildings and has high potential for city management and sustainable urban planning.
- Keywords
- Transportation, Renewable Energy, Sustainability and the Environment, Civil and Structural Engineering, Geography, Planning and Development, Building function, Classification, Geographic context, Social sensing, Neural network, URBAN LAND-USE, SOCIAL MEDIA DATA, MOBILE PHONE, POINTS, REMOTE, MODEL
Downloads
-
manuscript withoutMarking.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 1.51 MB
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 3.21 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01GMDTXMXCWCN5Z9E5XMFCHKRH
- MLA
- Zhang, Xucai, et al. “Inferring Building Function : A Novel Geo-Aware Neural Network Supporting Building-Level Function Classification.” SUSTAINABLE CITIES AND SOCIETY, vol. 89, 2023, doi:10.1016/j.scs.2022.104349.
- APA
- Zhang, X., Liu, X., Chen, K., Guan, F., Luo, M., & Huang, H. (2023). Inferring building function : a novel geo-aware neural network supporting building-level function classification. SUSTAINABLE CITIES AND SOCIETY, 89. https://doi.org/10.1016/j.scs.2022.104349
- Chicago author-date
- Zhang, Xucai, Xiaoping Liu, Kai Chen, Fangli Guan, Miao Luo, and Haosheng Huang. 2023. “Inferring Building Function : A Novel Geo-Aware Neural Network Supporting Building-Level Function Classification.” SUSTAINABLE CITIES AND SOCIETY 89. https://doi.org/10.1016/j.scs.2022.104349.
- Chicago author-date (all authors)
- Zhang, Xucai, Xiaoping Liu, Kai Chen, Fangli Guan, Miao Luo, and Haosheng Huang. 2023. “Inferring Building Function : A Novel Geo-Aware Neural Network Supporting Building-Level Function Classification.” SUSTAINABLE CITIES AND SOCIETY 89. doi:10.1016/j.scs.2022.104349.
- Vancouver
- 1.Zhang X, Liu X, Chen K, Guan F, Luo M, Huang H. Inferring building function : a novel geo-aware neural network supporting building-level function classification. SUSTAINABLE CITIES AND SOCIETY. 2023;89.
- IEEE
- [1]X. Zhang, X. Liu, K. Chen, F. Guan, M. Luo, and H. Huang, “Inferring building function : a novel geo-aware neural network supporting building-level function classification,” SUSTAINABLE CITIES AND SOCIETY, vol. 89, 2023.
@article{01GMDTXMXCWCN5Z9E5XMFCHKRH,
abstract = {{Buildings are fundamental components of urban areas and they play a vital role in supporting human activities in daily life. Understanding the actual building functions is essential for many urban applications, such as city management, urban planning, and optimization of transportation systems. Existing studies for inferring building functions are mainly based on a building's own features, and ignore its "geographic context" (e.g., the influences of nearby buildings). This paper introduces a novel geo-aware neural network to infer the functions of individual buildings. To this end, the proposed model integrates information about the built environment and human ac-tivity of a target building and its "geographic context". The model further includes a geo-aware position embedding generator and transformer encoders to better capture the complex relationships between buildings. The evaluation results demonstrate that the proposed model outperforms all baselines and achieves a classifi-cation accuracy of 90.8%. Meanwhile, the proposed model works well even with a small amount of training dataset and has a good transferability to another urban area. In summary, the proposed model is an effective and reliable approach for inferring the functions of individual buildings and has high potential for city management and sustainable urban planning.}},
articleno = {{104349}},
author = {{Zhang, Xucai and Liu, Xiaoping and Chen, Kai and Guan, Fangli and Luo, Miao and Huang, Haosheng}},
issn = {{2210-6707}},
journal = {{SUSTAINABLE CITIES AND SOCIETY}},
keywords = {{Transportation,Renewable Energy, Sustainability and the Environment,Civil and Structural Engineering,Geography, Planning and Development,Building function,Classification,Geographic context,Social sensing,Neural network,URBAN LAND-USE,SOCIAL MEDIA DATA,MOBILE PHONE,POINTS,REMOTE,MODEL}},
language = {{eng}},
pages = {{13}},
title = {{Inferring building function : a novel geo-aware neural network supporting building-level function classification}},
url = {{http://doi.org/10.1016/j.scs.2022.104349}},
volume = {{89}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: