摘要:

Increasing interest in configuration similarity is currently developing in the context of Digital Libraries, Spatial Databases and Geographical Information Systems. The corresponding queries retrieve all database configurations that match an input description (e.g. 'find all configurations where an object x0 is about 5 km north-east of another x1, which, in turn, is inside object x2'). This paper introduces a framework for configuration similarity that takes into account all major types of spatial constraints (topology, direction, and distance). We define appropriate fuzzy similarity measures for each type of constraint to provide flexibility and allow the system to capture real-life needs. Then we apply preprocessing techniques to explicate constraints in the query, and present algorithms that effectively solve the problem. Extensive experimental results demonstrate the applicability of our approach to images and queries of considerable size.

ISSN:1365-8816    

DOI:10.1080/136588199241373

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This paper presents an iterative, structured knowledge-acquisition process for extracting human understanding of relationships between a natural resource and its environment. This understanding can then be used to map natural resources as spatial continua. The knowledge acquisition process is based on personal construct theory and consists of several iterations. Each iteration has five structured interview sessions: preparation, key development, description, comparison, and quantification. The knowledge derived from each iteration is represented as a set of membership functions that describes the degree to which a given environmental condition impacts the status of the given resource. The final set of membership functions, which is the final version of knowledge, is derived through the comparison and 'fusion' of the membership functions from each iteration. The comparison of the membership functions among different iterations is also used to measure the consistency (integrity) of an expert's understanding of the relationships. In a soil mapping case study, knowledge on soil-environment relationships was acquired from a local soil scientist using the knowledge acquisition process. The case study shows that knowledge sets extracted a year apart were consistent with each other. The study also shows that the soil expert was more familiar with the relationships between soils and some environmental variables than with other environmental variables. The expert's understanding about soil-environmental relationships also differed among soil series. Although it was designed to extract expert knowledge for mapping natural resources as spatial continua under a GIS environment, this knowledge elicitation process can be easily adapted to extract expert knowledge for other knowledge-based applications.

ISSN:1365-8816    

DOI:10.1080/136588199241382

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This paper is concerned with the problems and solutions to reliable analysis of arbitrary datasets. Our approach is to describe components of a system called the GARP Modelling System (GMS) which we have developed for automating predictive spatial modelling of the distribution of species of plants and animals. The essence of the system is an underlying generic spatial modelling method which filters out potential sources of errors. The approach is generally applicable however, as the statistical problems arising in arbitrary spatial data analysis potentially apply to any domain. For ease of development, GMS is integrated with the facilities of existing database and visualization tools, and Internet browsers. The GMS is an example of a class of application which has been very successful for providing spatial data analysis in a simple to use way via the Internet.

ISSN:1365-8816    

DOI:10.1080/136588199241391

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

摘要:

This paper reports some of the findings from a two-year study into crime and disadvantage on Merseyside in north-west England. Particular attention is paid to how a GIS has been used in conjunction with crime pattern analysis software to explore relations between crime and the distribution of different types of disadvantaged, middle income and affluent residential neighbourhood. The GIS has also been used to examine crime incidents in relation to the distribution of residential properties, community facilities, administrative boundaries and the street network. Discussion is focused on the utility of combining disaggregate information with aggregate statistics in crime pattern analysis.

ISSN:1365-8816    

DOI:10.1080/136588199241409

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor

ISSN:1365-8816    

DOI:10.1080/136588199241418

出版商:Taylor & Francis Group    

年代:1999

数据来源: Taylor