Analyzing Knowledge Exchanges in Hybrid MAS GIS Decision Support Systems, Toward a New DSS Architecture
In this paper we present the strong points and the weakness of GIS used as decision support systems. We expose the advantages of adding MAS to GIS. We present the common critters used to characterize the MAS-GIS links, and introduce a new point of view ab
- PDF / 414,910 Bytes
- 10 Pages / 430 x 660 pts Page_size
- 109 Downloads / 178 Views
bstract. In this paper we present the strong points and the weakness of GIS used as decision support systems. We expose the advantages of adding MAS to GIS. We present the common critters used to characterize the MAS-GIS links, and introduce a new point of view about these relations studying the nature of the knowledge used to help decision makers. We explicit the nature and the purpose of these knowledge, and we study the knowledge exchanges between MAS, GIS, experts and decision makers. Then, we propose a new architecture, SMAG, for hybrid MAS-GIS decision support systems development platforms. We implement this architecture and build a decision support system dedicated to the fresh water problem. Thus we illustrate the relevance of our operational decision making solution that is of one the first to make possible to take into account together individual and social behaviors, spatial component and specificities of target sites. Keywords: multi-agent systems, geographic information systems, decision support systems, knowledge management, model, water, corsica.
1 Introduction In this paper we present the decision support systems focusing on those based on geographic information systems (GIS). We highlight the strengths and the weak points of this approach and we propose solutions to reduce its main insufficiencies. To overcome the limits due to the intrinsic static property of GIS representations, we study the opportunity to couple a GIS with an individual based model of the system built following the multi-agents systems (MAS) paradigm. First, we present our work about coupling MAS and GIS, and then we introduce and explain together the nature, the purposes, and the management of the knowledge required to support decision makers. Using this analysis, we propose a framework for hybrid MAS-GIS decision support systems. Following our ideas about knowledge and decision making process, we present our SMAG platform architecture, dedicated to the development of hybrid MAS-GIS decision support systems (DSS). Finally we present CORMGIS, the first SMAG compliant platform dedicated to DSS development, and its first application: HydroValleA, a decision support system used to solve the fresh water problem in Mediterranean islands. N.T. Nguyen et al. (Eds.): KES-AMSTA 2008, LNAI 4953, pp. 323–332, 2008. © Springer-Verlag Berlin Heidelberg 2008
324
D. Urbani and M. Delhom
2 DSS Based on GIS Due to their capabilities GIS are used by decision makers in geo marketing, navigation, agriculture, advertising, infrastructure maintenance and many other fields [1]. Use GIS is a fruitful approach for choice's problems with strong spatial component. But this approach is limited by the intrinsic static nature of GIS representations witch makes impossible to take into account the systems ' dynamics [2]. To reduce this weakness, GIS are commonly coupled with generic dynamic models of the systems. The advantages of using such a way are obvious to most users: integrate the spatial dimension and take into account the system's process. In the a
Data Loading...
