CHARACTERIZING RESIDENTIAL BUILDING PATTERNS IN HIGHDENSITY CITIES USING GRAPH CONVOLUTIONAL NEURAL NETWORKS
Document Type
Conference Proceeding
Publication Date
1-1-2024
Abstract
In urban morphology studies, accurately classify ingresidential building patterns is crucial for informed zoning and urban design guidelines. While machine learning, particularly neural networks, has been widely applied to urban form taxonomy, most studies focus on grid-like data from street-view images or satellite imagery. Our paper provides a novel framework for graph classification by extracting features of clustering buildings at different scales and training a spectral-based GCN model on graph-structured data. Furthermore, from the perspective of urban designers, we put forward corresponding design strategies for different building patterns through data visualization and scenario analysis. The findings indicate that GCNhas a good performance and generalization ability in identify ingresidential building patterns, and this framework can aid urban designers or planners in decision-making for diverse urban environments in Asia.
Identifier
85196739783 (Scopus)
ISBN
[9789887891826]
Publication Title
Proceedings of the International Conference on Computer-Aided Architectural Design Research in Asia
External Full Text Location
https://doi.org/10.52842/conf.caadria.2023.2.039
e-ISSN
27104265
ISSN
27104257
First Page
39
Last Page
48
Volume
2
Recommended Citation
Jia, Muxin; Zhang, Kaiheng; and Narahara, Taro, "CHARACTERIZING RESIDENTIAL BUILDING PATTERNS IN HIGHDENSITY CITIES USING GRAPH CONVOLUTIONAL NEURAL NETWORKS" (2024). Faculty Publications. 967.
https://digitalcommons.njit.edu/fac_pubs/967