Grzegorz Skupinski, Anne Puissant, Christiane Weber et Annabelle Mas (2008),
Constitution d’une base de données spatio-temporelles urbaines : évolution des tissus urbains de Strasbourg Journées Informations Géographiques et Observation de la terre (JIGOT 08), Marseille, France
Julien Lesbegueries, Agnès Braud et Nicolas Lachiche (2009),
« A propositionalisation that Preserves Continuous Attributes »
poster session of the 19th International Conference on Inductive Logic Programming - 2009 .
Abstract : The aim of this paper is to extend local transformation functions for propositionalisation. We follow the works of (Krogel et al., 2001) by adding a transformation function that reverses the thresholding problem. Indeed, we propose an innovative method that manages numeric attributes with the hypothesis that features can be transformed without use of discretisation nor aggregation.
Julien Lesbegueries, Nicolas Lachiche, Agnès Braud, Grzegorz Skupinski, Anne Puissant et Julien Perret (2009),
« A platform for Spatial Data Labeling in an Urban Context » proceedings of the International Opensource Geospatial Research Symposium (OGRS 2009), Nantes, France.
Abstract : This paper presents a platform based on an opensource framework (Geoxygene) adapted to label urban areas from vector based topographic databases. The development of this platform is part of the GeOpenSim project which aims at analysing and simulating urban dynamics The objective is to detect automatically which elementary areas (urban blocks) can potentially evolve. The proposed labelling process is used in order to characterize and identify several evolution processes of different type of urban fabric. This software provides facilities in the domain of urban planning and management to (i) experimentally refine the modelling of their problem, (ii) collect training data, (iii) automate the labelling.
Julien Perret, Annabelle Boffet Mas, Anne Ruas (2009),
« Understanding Urban
Dynamics : the use of vector topographic databases and the creation
of spatio-temporal databases »,
proceedings of the 24th International Cartography Conference (ICC 2009), Santiago, Chile.
Abstract : Understanding urban dynamics is an increasingly important challenge that can be answered in several ways. For many years, an important body of research has been tackling this problem in the literature of regional science, urban and economic geography, geomatics and related fields. But, whatever the field of research, in order to better understand urban dynamics, one needs to study the actual changes geographic objects undergo over time. Studying such changes requires the constitution of spatio-temporal databases containing data for each step of the considered evolutions. Unfortunately, building such spatio-temporal databases from existing topographic databases is a difficult process that requires tracking topographic objects in consecutive databases and creating links between them. The evolution of topographic objects which evolution has been tracked can be studied and then simulated. The observed changes the geographic objects undergo help up understand each topographic object’s dynamics, their particularities on specific geographical areas as well as their evolutions in different time periods. Simulations can then be used to better understand the specific evolutions taking place on a given territory. Eventually, such simulations might be able to help the planning and policy making processes. The methodology presented in this paper includes the construction of spatio-temporal databases, the capture of historical topographic data from existing topographic maps, and a rich hierarchy creation process. Finally, the bases of our vector-based simulation platform are given.
Florence Curie, Julien Perret, Anne Ruas (2010),
« Simulation of urban blocks densification »,
proceedings of the 13th AGILE International Conference on Geographic Information Science, Guimarães, Portugal.
Abstract : This paper addresses urban block densification in a simulation context. The simulation of such a process requires several spatial analysis tools and specific knowledge on the types of objects accounting for the increased urban density. In this paper, only buildings creation is considered. The method proposed hereby takes into account the existing spatial organisation of an urban block in order to respect it while creating new buildings.
Julien Perret, Florence Curie, Julien Gaffuri, Anne Ruas (2010),
« A Multi-Agent System for the simulation of urban dynamics »,
in proceeding of the 10th European Conference on Complex Systems (ECCS 2010), Lisbon, Portugal.
Abstract : Simulating the evolution of cities suggests the ability to understand and model the laws governing urban dynamics. The approach presented in this paper uses a multi-agent system to model the self-organising properties of urban systems. The proposed multi-agent system is a hierarchy of topographic agents (e.g. buildings, roads, rivers or urban blocks) that are built, modified, merged, split, restructured and destroyed over time. Each agent’s behaviour is controlled by a set of constraints and associated actions. In the proposed system, only topographic objects are taken into account, assuming a certain independence between society and the urban form (morphology) as well as a delay between the action of the society on the urban form and the feedback of the latter to the former.
Anne Puissant, Nicolas Lachiche, Agnès Braud, Grzegorz Skupinski, et Julien Perret (2010),
« Classification des tissus urbains à partir de données vectorielles - application à Strasbourg »
proceedings of the
Colloque International de Géomatique et d’Analyse Spatiale SAGEO’10, page 198—211, Toulouse, France.
Résumé : L’analyse morphologique des tissus urbains est un préalable important afin de mieux comprendre les dynamiques urbaines et afin de les simuler. Dans ce contexte, l’objectif de cet article est de tester un algorithme d’apprentissage supervisé symbolique (TILDE) permettant d’obtenir un modèle de classification représenté sous forme de règles de décision. L’objectif est d’automatiser le processus d’identification des tissus urbains à partir de bases de données vectorielles et d’extraire des connaissances morphologiques sur les tissus urbains. Différents tests, appliqués à l’agglomération de Strasbourg, sur des données historiques reconstruites sur une période de 50 ans, met en évidence l’intérêt de ce type d’algorithme pour classer les tissus urbains. Toutefois, l’identification automatique de règles caractérisant la morphologie des tissus urbains de manière univoque n’est pas satisfaisante.
Abstract : Morphological analysis of urban fabric is a relevant step in order to perform the analysis of urban dynamics and to simulate their evolutions. In this context, the objective of this paper is to test a classification method based on a supervised and symbolic algorithm (tilde) to label urban blocks and to produce rules on their morphology. The objective is to automate the identification of urban fabrics from vector and historical database and to extract knowledge on urban morphology. Several tests applied on the Strasbourg area on historical database, are encouraging but rules are not relevant to extract urban blocks.