Title of article :
Fuzzy classification of sites suspected of being contaminated
Author/Authors :
Lehn، نويسنده , , Karsten and Temme، نويسنده , , Karl-Heinz، نويسنده ,
Abstract :
One part of todayʹs environmental pollution problem is referred to by the term contaminated soils. In Germany specialists expect to find approximately 260 000 sites suspected of being contaminated after completion of the registration phase.
arge number, the urgency of carrying out measures to protect the environment and limited personnel and financial resources result in the necessity for a computer support. Detailed considerations of deficiencies of existing computer systems and formal estimation methods lead to a bipartite knowledge-based approach supporting the relative estimation of hazard.
imensional classification, the core of this approach, is mathematically well-founded and serves as an extension of methods already used successfully in practical operation.
suitability of formal risk analysis methods and various sources of incompleteness, uncertainty and vagueness of the whole research field motivate the use of fuzzy methods, and in particular the use of fuzzy classification providing a rough ranking method. Feature generation, the other main part of the approach, allows selecting, valuating and tuning the properties of the sites in such a way to ensure an optimal classification. For maximizing the expressive power of the systemʹs results, the user is enabled to compromise between a detailed survey of a site and an easy to survey representation of a site with resulting loss of information caused by a certain a priori aggregation of properties.
Keywords :
Classification , Cluster analysis , Knowledge-based models , Fuzzy Logic , Pollution , soil
Journal title :
Astroparticle Physics