Istituto di Scienza e Tecnologie dell'Informazione     
Furletti B., Turini F., Baglioni M., Rinzivillo S. Examples of integration of induction and deduction in knowledge discovery. vol. 4155 Oliviero Stock, Marco Schaerf (eds.). (Lecture Notes in Artificial Intelligence, vol. 4155). Berlin: Springer, 2006.
The use of classification trees in two quite different application areas -business documents on one side and geographic information systems on the other- is presented. What is in common between such so different applications of the classification techniques based on trees is the need of complementing the straightforward use of induction with the exploitation of some form of deductive, or better to say expert, knowledge. When working on business documents, the expert knowledge, in the form of rules elicited from human experts, is used to improve the construction of the classification tree by complementing the inductive knowledge coming from the examples in the choice of the next node to add to the tree. When working on geographic information systems, the expert knowledge, in the form of specifying which are the spatial relationships among the geographic objects, is used to extract the information from the GIS in a form that can be then processed in an inductive style.
URL: http://link.springer.com/chapter/10.1007%2F11829263_17
DOI: 10.1007/11829263_17
Subject Knowledge discovery
68U99 None of the above, but in this section

Icona documento 1) Download Document PDF

Icona documento Open access Icona documento Restricted Icona documento Private


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional