Multidimensional urban segregation: toward a neural network measure

Abstract

We introduce a multidimensional, neural-network approach to reveal and measure urban segregation phenomena, based on the Self-Organizing Map algorithm (SOM). The multidimensionality of SOM allows one to apprehend a large number of variables simultaneously, defined on census or other types of statistical blocks, and to perform clustering along them. Levels of segregation are then measured through correlations between distances on the neural network and distances on the actual geographical map. Further, the stochasticity of SOM enables one to quantify levels of heterogeneity across census blocks. We illustrate this new method on data available for the city of Paris.

Measuring and Visualizing Patterns of Ethnic Concentration: The Role of Distortion Coefficients

“…The idea of bespoke neighborhoods was first introduced in studies of contextual effects (Macallister et al 2001), and the concept is a basic dimension of properly analyzing segregation patterns. Empirical analyses of segregation across multiple scales further emphasized the value of multiscale analysis (Clark et al 2015; Fowler 2016; Olteanu et al 2019).…”

“…For a more interpretable version of the Distortion coefficient and transverse comparison considerations, Olteanu et al (2019) suggest a normalized adaptation. They normalize the coefficient computed in any area by the Distortion calculated for the most isolated unit of the most segregated configuration possible, given the global figures of the city.…”

“…The property of the profile‐based Distortion Index captures this relative “distance” as an additional form of segregation. This particular is discussed in (Olteanu et al 2019) through simulations of various extreme configurations.…”

Optimized Query Algorithms for Top- K Group Skyline

“…The Skyline has been differently extended in recent years and becomes an emphasis for research in the database domain. At present, there are still many researches on single point query based on the traditional Skyline, such as the Skyline query on the data stream [3] and on the subspace [4][5][6][7][8]. In the skyline query on the data stream, with the dynamic change of data stream tuples, for a given constraint query, find the nodes that fall into the valid area or affect the result tuple set.…”

Segregation through the multiscalar lens

“…segregation | spatial statistics | multiscalar analysis I ndices of spatial dissimilarities continue to be at the center of studies of ethnic (and other forms of) segregation in large cities (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13). However, single-number indices as well as singlescale indices cannot capture the complexity of spatial patterns that arise in actual cities.…”