A dissimilarity function for clustering geospatial polygons

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

The traditional point-based clustering algorithms when applied to geospatial polygons may produce clusters that are spatially disjoint due to their inability to consider various types of spatial relationships between polygons. In this paper, we propose to represent geospatial polygons as sets of spatial and non-spatial attributes. By representing a polygon as a set of spatial and non-spatial attributes we are able to take into account all the properties of a polygon (such as structural, topological and directional) that were ignored while using point-based representation of polygons, and that aid in the formation of high quality clusters. Based on this framework we propose a dissimilarity function that can be plugged into common state-of-the-art spatial clustering algorithms. The result is clusters of polygons that are more compact in terms of cluster validity and spatial contiguity. We show the effectiveness and robustness of our approach by applying our dissimilarity function on the traditional k-means clustering algorithm and testing it on a watershed dataset.

Original languageEnglish (US)
Title of host publication17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009
Pages384-387
Number of pages4
DOIs
StatePublished - Dec 1 2009
Event17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009 - Seattle, WA, United States
Duration: Nov 4 2009Nov 6 2009

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Conference

Conference17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009
CountryUnited States
CitySeattle, WA
Period11/4/0911/6/09

Fingerprint

Dissimilarity
polygon
Clustering algorithms
Polygon
Clustering
Clustering Algorithm
Watersheds
Attribute
Cluster Validity
Contiguity
Spatial Clustering
Testing
K-means Algorithm
K-means Clustering
aid
Disjoint
watershed
Robustness

Keywords

  • Clustering
  • Polygons
  • Regionalization
  • Spatial data mining

ASJC Scopus subject areas

  • Earth-Surface Processes
  • Computer Science Applications
  • Modeling and Simulation
  • Computer Graphics and Computer-Aided Design
  • Information Systems

Cite this

Joshi, D., Samal, A. K., & Soh, L-K. (2009). A dissimilarity function for clustering geospatial polygons. In 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009 (pp. 384-387). (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems). https://doi.org/10.1145/1653771.1653825

A dissimilarity function for clustering geospatial polygons. / Joshi, Deepti; Samal, Ashok K; Soh, Leen-Kiat.

17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009. 2009. p. 384-387 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Joshi, D, Samal, AK & Soh, L-K 2009, A dissimilarity function for clustering geospatial polygons. in 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009. GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems, pp. 384-387, 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009, Seattle, WA, United States, 11/4/09. https://doi.org/10.1145/1653771.1653825
Joshi D, Samal AK, Soh L-K. A dissimilarity function for clustering geospatial polygons. In 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009. 2009. p. 384-387. (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems). https://doi.org/10.1145/1653771.1653825
Joshi, Deepti ; Samal, Ashok K ; Soh, Leen-Kiat. / A dissimilarity function for clustering geospatial polygons. 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009. 2009. pp. 384-387 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems).
@inproceedings{7610d5a366bc41978b4061b187c9a632,
title = "A dissimilarity function for clustering geospatial polygons",
abstract = "The traditional point-based clustering algorithms when applied to geospatial polygons may produce clusters that are spatially disjoint due to their inability to consider various types of spatial relationships between polygons. In this paper, we propose to represent geospatial polygons as sets of spatial and non-spatial attributes. By representing a polygon as a set of spatial and non-spatial attributes we are able to take into account all the properties of a polygon (such as structural, topological and directional) that were ignored while using point-based representation of polygons, and that aid in the formation of high quality clusters. Based on this framework we propose a dissimilarity function that can be plugged into common state-of-the-art spatial clustering algorithms. The result is clusters of polygons that are more compact in terms of cluster validity and spatial contiguity. We show the effectiveness and robustness of our approach by applying our dissimilarity function on the traditional k-means clustering algorithm and testing it on a watershed dataset.",
keywords = "Clustering, Polygons, Regionalization, Spatial data mining",
author = "Deepti Joshi and Samal, {Ashok K} and Leen-Kiat Soh",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1653771.1653825",
language = "English (US)",
isbn = "9781605586496",
series = "GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems",
pages = "384--387",
booktitle = "17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009",

}

TY - GEN

T1 - A dissimilarity function for clustering geospatial polygons

AU - Joshi, Deepti

AU - Samal, Ashok K

AU - Soh, Leen-Kiat

PY - 2009/12/1

Y1 - 2009/12/1

N2 - The traditional point-based clustering algorithms when applied to geospatial polygons may produce clusters that are spatially disjoint due to their inability to consider various types of spatial relationships between polygons. In this paper, we propose to represent geospatial polygons as sets of spatial and non-spatial attributes. By representing a polygon as a set of spatial and non-spatial attributes we are able to take into account all the properties of a polygon (such as structural, topological and directional) that were ignored while using point-based representation of polygons, and that aid in the formation of high quality clusters. Based on this framework we propose a dissimilarity function that can be plugged into common state-of-the-art spatial clustering algorithms. The result is clusters of polygons that are more compact in terms of cluster validity and spatial contiguity. We show the effectiveness and robustness of our approach by applying our dissimilarity function on the traditional k-means clustering algorithm and testing it on a watershed dataset.

AB - The traditional point-based clustering algorithms when applied to geospatial polygons may produce clusters that are spatially disjoint due to their inability to consider various types of spatial relationships between polygons. In this paper, we propose to represent geospatial polygons as sets of spatial and non-spatial attributes. By representing a polygon as a set of spatial and non-spatial attributes we are able to take into account all the properties of a polygon (such as structural, topological and directional) that were ignored while using point-based representation of polygons, and that aid in the formation of high quality clusters. Based on this framework we propose a dissimilarity function that can be plugged into common state-of-the-art spatial clustering algorithms. The result is clusters of polygons that are more compact in terms of cluster validity and spatial contiguity. We show the effectiveness and robustness of our approach by applying our dissimilarity function on the traditional k-means clustering algorithm and testing it on a watershed dataset.

KW - Clustering

KW - Polygons

KW - Regionalization

KW - Spatial data mining

UR - http://www.scopus.com/inward/record.url?scp=74049135603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74049135603&partnerID=8YFLogxK

U2 - 10.1145/1653771.1653825

DO - 10.1145/1653771.1653825

M3 - Conference contribution

AN - SCOPUS:74049135603

SN - 9781605586496

T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

SP - 384

EP - 387

BT - 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009

ER -