Paper Info
Title
Knowledge acquisition in the STREAMES project: the key process in the Environmental Decision Support System development
Abstract
Nowadays, bad river water quality has become a serious problem, especially in developed regions, due to the high nutrient loads from anthropogenic sources dumped into the rivers. Pollution sources can have different origins: point or non-point sources. As point sources can be well identified, these can be controlled, but the identification and control of non-point sources is not an easy task. Moreover, the natural responses of polluted streams in front of these external aggressions are still quite unknown. The decision-making processes involved in stream reach management require extensive human expertise (from water managers), empirical knowledge from scientific research and elaborated calculation over large amounts of numerical and symbolic data. In this sense, the STREAMES project appears as an attempt to develop and implement a knowledge-based decision support system to help water managers in taking decisions. The knowledge acquisition process is the most important step to build a complete knowledge base. After acquiring the knowledge, the efforts will concentrate on structuring and representing the knowledge in a decision tree fashion as a previous step to build the knowledge base. Each decision tree developed refers to a specific river problem: eutrophication, excess of ammonia, organic matter pollution … This paper presents the STREAMES project, with major emphasis on the knowledge acquisition step.
Year
Venue
Keywords
2003
AI Commun.
decision support system,knowledge acquisition process,knowledge-based,knowledge management,non-point source,bad river water quality,streames project,river water quality.,stream management,knowledge base,key process,water manager,knowledge acquisition step,decision tree,knowledge acquisition,complete knowledge base,empirical knowledge,environmental decision support system,scientific research,decision making process,non point source,point source,organic matter
Field
DocType
Volume
Decision tree,Empirical evidence,Computer science,Knowledge management,Risk analysis (engineering),Artificial intelligence,Knowledge base,Structuring,Decision support system,River water,Knowledge acquisition,Machine learning,Scientific method
Journal
16
Issue
ISSN
Citations 
4
0921-7126
4
PageRank 
References 
Authors
0.47
6
7
Name
Order
Citations
PageRank
J. Comas1262.76
E. Llorens240.80
E. Martí340.47
M. A. Puig440.47
J. L. Riera540.47
F. Sabater670.91
M. Poch78011.71