ANALYSIS OF TRACE ELEMENTS IN CLINKER BASED ON SUPERVISED CLUSTERING AND FUZZY DECISION TREE INDUCTION
-
Published:2005
Ferenc D Tamás, Ferenc Péter Pach, János Abonyi, Ana Maria Esteves, 2005. "ANALYSIS OF TRACE ELEMENTS IN CLINKER BASED ON SUPERVISED CLUSTERING AND FUZZY DECISION TREE INDUCTION", Cement Combinations for Durable Concrete: Proceedings of the International Conference held at the University of Dundee, Scotland, UK on 5–7 July 2005, Ravindra K. Dhir, Thomas A. Harrison, Moray D. Newlands
Download citation file:
The qualitative identification to determine the origin (i.e. manufacturing factory) of Portuguese clinkers is described. The classification of clinkers produced in different factories can be based on their trace element content. Approximately 24 clinker sorts were analysed, collected from all Portuguese cement factories to determine their Mg, Sr, Ba, Mn, Ti, Zr, Zn and V content. An expert system can be formulated by crisp or fuzzy decision tree designed based on the collected data. The performance of the obtained classifiers was measured by ten-fold cross validation. The results show that the proposed methods are useful to identify easy-to-use expert systems that are able to determine the origin of the clinker based on its trace element content.
INTRODUCTION
DECISION TREES
SUPERVISED CLUSTERING AND FUZZY DECISION TREE INDUCTION
APPLICATION
CONCLUSIONS
REFERENCES
