A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Detection of Urban Socio-economic Patterns Using Clustering Techniques
Modern urban planning needs efficient descriptors of the distribution of socio-economic features in space and time. Knowledge about residential patterns and distribution of services can help the decision makers for future strategies of cities’ development. In order to facilitate this process, clustering of urban features is a very efficient tool, because it allows the reduction of the information from a very high-dimensional and complex input space to a low dimensional and visualizable output space. In this chapter, an unsupervised clustering method and a cluster detection method are discussed and applied to analyze the socio-economic structure of the Swiss regions of Vaud and Geneva. The unsupervised method, based on self-organized maps and hierarchical ascending classification, groups the spatial units by their similarity measured between socio-economic variables. The self-organizing map allows to account for nonlinear similarity. The cluster detection method, the spatial scan statistics, is used to find hot spots in the distribution of the residential patterns of professions. The method is applied to the distribution of business manager and workers in the region of Vaud. Moreover, the distribution of hotels and restaurant services has been studied at the intra-urban scale, to detect over- and under-densities of services and compare them to the residential patterns observed previously. Results show the effect of peri- and sub-urbanization in the region and are discussed in both transportation and social terms.
Detection of Urban Socio-economic Patterns Using Clustering Techniques
Modern urban planning needs efficient descriptors of the distribution of socio-economic features in space and time. Knowledge about residential patterns and distribution of services can help the decision makers for future strategies of cities’ development. In order to facilitate this process, clustering of urban features is a very efficient tool, because it allows the reduction of the information from a very high-dimensional and complex input space to a low dimensional and visualizable output space. In this chapter, an unsupervised clustering method and a cluster detection method are discussed and applied to analyze the socio-economic structure of the Swiss regions of Vaud and Geneva. The unsupervised method, based on self-organized maps and hierarchical ascending classification, groups the spatial units by their similarity measured between socio-economic variables. The self-organizing map allows to account for nonlinear similarity. The cluster detection method, the spatial scan statistics, is used to find hot spots in the distribution of the residential patterns of professions. The method is applied to the distribution of business manager and workers in the region of Vaud. Moreover, the distribution of hotels and restaurant services has been studied at the intra-urban scale, to detect over- and under-densities of services and compare them to the residential patterns observed previously. Results show the effect of peri- and sub-urbanization in the region and are discussed in both transportation and social terms.
Detection of Urban Socio-economic Patterns Using Clustering Techniques
Murgante, Beniamino (editor) / Borruso, Giuseppe (editor) / Lapucci, Alessandra (editor) / Tuia, Devis (author) / Kaiser, Christian (author) / Da Cunha, Antonio (author) / Kanevski, Mikhail (author)
2009-01-01
18 pages
Article/Chapter (Book)
Electronic Resource
English
clustering , self-organizing maps , spatial scan statistics , urban features Geography , Geographical Information Systems/Cartography , Urban Geography / Urbanism (inc. megacities, cities, towns) , World Regional Geography (Continents, Countries, Regions) , Mathematical and Computational Engineering , Landscape/Regional and Urban Planning , Artificial Intelligence , Engineering
Socio-economic urban environmental research
| British Library Conference Proceedings | 1998
From indices to impacts using environmental and socio-economic clustering in Kenya
| DOAJ | 2025
From indices to impacts using environmental and socio-economic clustering in Kenya
| Elsevier | 2025
Urban hydrology, watershed management and socio-economic aspects
| TIBKAT | 2016