Skip to Main content Skip to Navigation
Theses

Fusion de connaissances imparfaites pour l'appariement de données géographiques : proposition d'une approche s'appuyant sur la théorie des fonctions de croyance

Ana-Maria Olteanu 1
1 COGIT - Cartographie et Géomatique
LaSTIG - Laboratoire des Sciences et Technologies de l'Information Géographique
Abstract : Nowadays, there are many geographic databases, (GDB), covering the same reality. The geographical data are represented differently (for example a river can be represented by a line or a polygon), they are used in different applications (visualisation, analysis) and they are created using various modes of acquisition (sources, processes). All these factors create independence between GDB, which causes problems for both producers and users. Thus, a solution is to clarify the relationships between various database objects, i.e. to match homologous objects, which represent the same reality. This process is known as spatial data matching. Because of the complexity of the matching process, the existing approaches depend on the types of data (points, lines or polygons) and the level of detail of the GDB. We realised, that most of the approaches are based on the geometry and the topology of the geographical objects, and very few approaches take into account the descriptive information of geographical objects. Besides, for most approaches, the criteria are applied one after the other and knowledge is contained within the process. Following this analysis, we proposed a matching approach that is guided by knowledge and takes into account all criteria at the same time exploiting the geometry, descriptive information and relations between geographical objects. In order to formalise knowledge and model their imperfections (imprecision, uncertainty and incompleteness), we used the Belief Theory [Shafer, 1976]. Our approach of the data matching is composed of five steps. After a selection of candidates, the masses of beliefs are initialised by analysing each candidate separately from the others using different knowledge expressed by various matching criteria. Then, the matching criteria and candidates are fusioned. Finally, a decision is taken. Our approach has been tested on real data having different levels of detail and representing relief (data points) and road networks (linear data)
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-00469407
Contributor : Abes Star :  Contact
Submitted on : Thursday, April 1, 2010 - 1:36:14 PM
Last modification on : Tuesday, May 12, 2020 - 8:28:22 AM
Long-term archiving on: : Wednesday, September 8, 2010 - 4:57:04 PM

File

2008PEST0252_0_0.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-00469407, version 1

Collections

Citation

Ana-Maria Olteanu. Fusion de connaissances imparfaites pour l'appariement de données géographiques : proposition d'une approche s'appuyant sur la théorie des fonctions de croyance. Autre [cs.OH]. Université Paris-Est, 2008. Français. ⟨NNT : 2008PEST0252⟩. ⟨tel-00469407⟩

Share

Metrics

Record views

726

Files downloads

1412