| Full text | |
| Author(s): |
Salinas, Karelia
;
Goncalves, Thales
;
Barella, Victor
;
Vieira, Thales
;
Nonato, Luis Gustavo
;
DeCarvalho, BM
;
Goncalves, LMG
Total Authors: 7
|
| Document type: | Journal article |
| Source: | 2022 35TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2022); v. N/A, p. 6-pg., 2022-01-01. |
| Abstract | |
The current availability of urban big data provides novel opportunities to perform data-rich urban planning and to handle a variety of issues in a city. However, the way multiple data sources are provided, represented and integrated is one of the main challenges to developing intelligent urban analytic tools. In this context, we present CityHub, a library to handle multiple urban datasets. Specifically, CityHub integrates distinct urban data types in a layer-based architecture that considers four different types of layers. The integrated data is preprocessed to a common spatial domain: the set of nodes of a city street graph. The resulting data structure may be easily used to export feature vectors associated to the nodes of a street graph, enabling a multitude of analytical procedures. To demonstrate the potential of the proposed library, we propose an interactive visualization tool that may be used to perform several visual analytic tasks. We also present cases studies to demonstrate how the proposed library and visualization tool can be used to uncover complex urban data patterns in the city of Sao Paulo. (AU) | |
| FAPESP's process: | 18/24516-0 - Graph signal processing and deep learning for crime prediction in São Paulo City |
| Grantee: | Thales de Oliveira Gonçalves |
| Support Opportunities: | Scholarships in Brazil - Doctorate |
| FAPESP's process: | 20/07012-8 - Visual analytics for crime analysis |
| Grantee: | Karelia Alexandra Vilca Salinas |
| Support Opportunities: | Scholarships in Brazil - Doctorate (Direct) |