Generating approximate region boundaries from heterogeneous spatial information: An evolutionary approach

  • Authors:

  • Steven Schockaert;Philip D. Smart;Florian A. Twaroch

  • Affiliations:

  • Department of Applied Mathematics and Computer Science, Ghent University, Krijgslaan 281 - S9, 9000 Gent, Belgium;School of Computer Science, Cardiff University, 5 The Parade, Roath, Cardiff, UK;School of Computer Science, Cardiff University, 5 The Parade, Roath, Cardiff, UK

  • Venue:
  • Information Sciences: an International Journal
  • Year:
  • 2011

Quantified Score

Hi-index 0.07

Visualization

Abstract

Spatial information takes different forms in different applications, ranging from accurate coordinates in geographic information systems to the qualitative abstractions that are used in artificial intelligence and spatial cognition. As a result, existing spatial information processing techniques tend to be tailored towards one type of spatial information, and cannot readily be extended to cope with the heterogeneity of spatial information that often arises in practice. In applications such as geographic information retrieval, on the other hand, approximate boundaries of spatial regions need to be constructed, using whatever spatial information that can be obtained. Motivated by this observation, we propose a novel methodology for generating spatial scenarios that are compatible with available knowledge. By suitably discretizing space, this task is translated to a combinatorial optimization problem, which is solved using a hybridization of two well-known meta-heuristics: genetic algorithms and ant colony optimization. What results is a flexible method that can cope with both quantitative and qualitative information, and can easily be adapted to the specific needs of specific applications. Experiments with geographic data demonstrate the potential of the approach.