Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Calgary

$15,000.00

Incorporating domain knowledge in spatial clustering

FY 2011-12

Summary
Spatial clustering is an important topic in knowledge discovery research. It is to partition similar data objects into the same group (called cluster) based on their distance, density and reachability in space. It can be used to find natural clusters, to identify hot spots, and to partition an area based on utility. Ignoring domain knowledge and users' requirements during the spatial clustering can lead to useless and distorted clustering results. However, most existing clustering methods do not consider them during the clustering process, which prevents users from precisely describing their goals and understanding the results. Although some methods consider constraints, they only consider sharply limited knowledge concerning the domain and the users. The objective of this study is to propose new knowledge-driven clustering methods and clustering process. Domain knowledge will be mainly organized as ontologies. Users will be guided to select suitable clustering methods and datasets, customize distance functions on non-spatial attributes, and visualize the clustering results with explanation data. To achieve the objective, the first task is to build spatial clustering ontologies. Next, new clustering methods will be proposed, implemented and tested. Then, interactive software prototypes will be developed for guiding users to specifying their goals and supporting reasoning on the ontologies. Last, the framework will be applied on real applications in remote sensing and geospatial sensor network. The proposed research will make original and significant contributions in spatial data mining research. New clustering methods and clustering process produced from the research will generate more meaningful and useful clustering results. The research will also have wide range of real world applications, including environment modeling (e.g., animal habitat monitoring, agriculture and forest management, air quality monitoring), city planning (e.g., intelligent transportation systems), remote sensing (e.g., photogrammetric calibration), and other applications (e.g., oil and gas pipeline management). The whole framework can also be extended to find clusters in a variety of semantic web environments in future.
Program
Discovery Grants Program - Individual
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
355996-2008
Name nom
Wang, Xin
Department département
Geomatics Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2008
Award amount
15000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
330
Committee name en
Computing and Information Sciences - A
Committee name fr
Informatique - A
Area of application code
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Partie
4
Nb partie
5
Application title
Incorporating domain knowledge in spatial clustering
Keyword
NSERC
Application summary
Spatial clustering is an important topic in knowledge discovery research. It is to partition similar data objects into the same group (called cluster) based on their distance, density and reachability in space. It can be used to find natural clusters, to identify hot spots, and to partition an area based on utility. Ignoring domain knowledge and users' requirements during the spatial clustering can lead to useless and distorted clustering results. However, most existing clustering methods do not consider them during the clustering process, which prevents users from precisely describing their goals and understanding the results. Although some methods consider constraints, they only consider sharply limited knowledge concerning the domain and the users. The objective of this study is to propose new knowledge-driven clustering methods and clustering process. Domain knowledge will be mainly organized as ontologies. Users will be guided to select suitable clustering methods and datasets, customize distance functions on non-spatial attributes, and visualize the clustering results with explanation data. To achieve the objective, the first task is to build spatial clustering ontologies. Next, new clustering methods will be proposed, implemented and tested. Then, interactive software prototypes will be developed for guiding users to specifying their goals and supporting reasoning on the ontologies. Last, the framework will be applied on real applications in remote sensing and geospatial sensor network. The proposed research will make original and significant contributions in spatial data mining research. New clustering methods and clustering process produced from the research will generate more meaningful and useful clustering results. The research will also have wide range of real world applications, including environment modeling (e.g., animal habitat monitoring, agriculture and forest management, air quality monitoring), city planning (e.g., intelligent transportation systems), remote sensing (e.g., photogrammetric calibration), and other applications (e.g., oil and gas pipeline management). The whole framework can also be extended to find clusters in a variety of semantic web environments in future.