A Prototype Generalisation System Based on the Multi-Agent System Paradigm

Ruas, Anne; Duchêne, Cécile

doi:10.1016/b978-008045374-3/50016-8

Cited by 52 publications

(45 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a step preceding the generalisation buildings touching each other were merged into one building. Such a merge could be done as well with the agent approach, but then we would need to introduce so-called meso agents that control several single building agents together (see Ruas and Duchêne 2007). This would add an additional level of complexity and make the experimental setup and evaluation more difficult than necessary.…”

Section: Test Data Generalisation System and Learning Frameworkmentioning

confidence: 99%

“…All three parameters are usually pre-defined by an expert but may also be set dynamically at runtime (Ruas 1999). For a more detailed introduction of multi-agent models in cartographic generalisation we refer to the review by Ruas and Duchêne (2007). In the previous section we have introduced an approach for the generalisation of buildings that is based on constraint modelling and the use of a multi-agent system to control the generalisation process.…”

Section: Controlling Generalisation With An Agent Modelmentioning

confidence: 99%

“…A review of relevant techniques can be found in Harrie and Weibel (2007). The currently most promising techniques to solve this optimisation problem appear to be simulated annealing (Ware et al 2003a), genetic algorithms (Ware et al 2003b), and multi-agent systems (Ruas 1999, Barrault et al 2001, Ruas and Duchêne 2007.…”

Section: Controlling Generalisation With An Agent Modelmentioning

confidence: 99%

See 2 more Smart Citations

Utilising urban context recognition and machine learning to improve the generalisation of buildings

Steiniger

Taillandier

Weibel

2010

International Journal of Geographical Information Science

View full text Add to dashboard Cite

The introduction of automated generalisation procedures in map production systems requires that generalisation systems are capable of processing large amounts of map data in acceptable time and that cartographic quality is similar to traditional map products. With respect to these requirements, we examine two complementary approaches that should improve generalisation systems currently in use by national topographic mapping agencies. Our focus is particularly on self-evaluating systems, taking as an example those systems that build on the multi-agent paradigm. The first approach aims to improve the cartographic quality by utilising cartographic expert knowledge relating to spatial context. More specifically, we introduce expert rules for the selection of generalisation operations based on a classification of buildings into five urban structure types, including inner city, urban, suburban, rural, and industrial and commercial areas. The second approach aims to utilise machine learning techniques to extract heuristics that allow us to reduce the search space and hence the time in which a good cartographical solution is reached. Both approaches are tested individually and in combination for the generalisation of buildings from map scale 1:5000 to the target map scale of 1:25 000. Our experiments show improvements in terms of efficiency and effectiveness. We provide evidence that both approaches complement each other and that a combination of expert and machine learnt rules give better results than the individual approaches. Both approaches are sufficiently general to be applicable to other forms of self-evaluating, constraint-based systems than multi-agent systems, and to other feature classes than buildings. Problems have been identified resulting from difficulties to formalise cartographic quality by means of constraints for the control of the generalisation process. The introduction of automated generalisation procedures in map production systems requires that generalisation systems are capable of processing large amounts of map data in acceptable time and that cartographic quality is similar to traditional map products. With respect to these requirements we examine two complementary approaches that should improve generalisation systems currently in use by national topographic mapping agencies. Our focus is particularly on self-evaluating systems, taking as an example those systems that build on the multi-agent paradigm. The first approach aims to improve the cartographic quality by utilising cartographic expert knowledge relating to spatial context. More specifically we introduce expert rules for the selection of generalisation operations based on a classification of buildings into five urban structure types, including inner city, urban, suburban, rural, and industrial and commercial areas. The second approach aims to utilise machine learning techniques to extract heuristics that allow to reduce the search space and hence the time in which a good cartographical solution is reached. Both approaches are t...

show abstract

Section: Test Data Generalisation System and Learning Frameworkmentioning

confidence: 99%

Section: Controlling Generalisation With An Agent Modelmentioning

confidence: 99%

Section: Controlling Generalisation With An Agent Modelmentioning

confidence: 99%

See 1 more Smart Citation

Utilising urban context recognition and machine learning to improve the generalisation of buildings

Steiniger

Taillandier

Weibel

2010

International Journal of Geographical Information Science

View full text Add to dashboard Cite

show abstract

“…The constrained based methods can be further subdivided into complex techniques which perform different operations simultaneously, as opposed to methods that use constraints to chain specific algorithms that perform one operation at a time [23]. Examples of the first category are for instance least squares adjustment [15], [33], energy minimization [7], [2] or simulated annealing [40], whereas the AGENT approach [27], [31], [32] belongs to the second one. The AGENT approach tries to minimize the constraint violations for map features represented by autonomous software agents.…”

Section: Automating the Generalization Processmentioning

confidence: 99%

“…Constraints received special importance in cartography through the application of intelligent agents in the area of automated generalization 0. Following the results from AGENT project [4], [32] constraints define a final product specification on a certain property of an object that should be respected by an appropriate generalization. While measures only characterize objects or situations [30], without considering cartographic objectives, constraints evaluate situations with respect to the formalized cartographic objectives.…”

Section: Cartographic Constraintsmentioning

confidence: 99%

Automated processing for map generalization using web services

2008

View full text Add to dashboard Cite

In map generalization various operators are applied to the features of a map in order to maintain and improve the legibility of the map after the scale has been changed. These operators must be applied in the proper sequence and the quality of the results must be continuously evaluated. Cartographic constraints can be used to define the conditions that have to be met in order to make a map legible and compliant to the user needs. The combinatorial optimization approaches shown in this paper use cartographic constraints to control and restrict the selection and application of a variety of different independent generalization operators into an optimal sequence. Different optimization techniques including hill climbing, simulated annealing and genetic deep search are presented and evaluated experimentally by the example of the generalization of buildings in blocks. All algorithms used in this paper have been implemented in a web services framework. This allows the use of distributed and parallel processing in order to speed up the search for optimized generalization operator sequences.

show abstract

Map Generalization

Mackaness

Burghardt

Duchêne

2017

International Encyclopedia of Geography

View full text Add to dashboard Cite

Map generalization is concerned with the optimal display of geographic information in map form. It involves the careful selection of data and the use of a range of abstraction techniques that seek to give emphasis to what is important, while still including sufficient contextualizing information. If geographic phenomena are stored at fine levels of detail, the goal of automated map generalization is to derive maps at coarser (smaller) scales. Traditionally, the focus has been on paper maps, but increasingly map generalization services are available via the web, and accessible to users with relatively little cartographic knowledge who wish to integrate data from multiple sources (including their own). These high levels of automation require us to make explicit the relationships and behaviors among geographic phenomena, in order that we can reason about the complex decision‐making process that is cartographic design.

show abstract

A Prototype Generalisation System Based on the Multi-Agent System Paradigm

Cited by 52 publications

References 0 publications

Utilising urban context recognition and machine learning to improve the generalisation of buildings

Utilising urban context recognition and machine learning to improve the generalisation of buildings

Automated processing for map generalization using web services

Map Generalization

Contact Info

Product

Resources

About