Attribute Subset Quality Functions over a Universe of Weighted Objects
We consider a rough set inspired approach to deriving meaningful attribute subsets from data organized in a form of a decision system. We focus on quality functions measuring degrees in which particular attribute subsets determine the values of a decision attribute. We follow a well known idea of assigning weights to the training objects in order to reflect their importance in the attribute subset selection and new case classification processes. We discuss an example of an object weighting strategy related to probabilities of decision classes in the training data. We show that two attribute subset quality functions used in our earlier research are the same function computed using two different weighting techniques. We also investigate whether it is worth using the same weights during the processes of attribute selection and new case classification.
KeywordsApproximate decision reducts Attribute subset quality functions Strategies of weighting objects Voting among decision rules
Unable to display preview. Download preview PDF.
- 4.Widz, S., Ślęzak, D.: Rough Set Based Decision Support – Models Easy to Interpret. In: Peters, G., Lingras, P., Ślęzak, D., Yao, Y. (eds.) Rough Sets: Selected Methods and Applications in Management & Engineering. Advanced Information and Knowledge Processing, pp. 95–112. Springer (2012)Google Scholar
- 7.Stawicki, S., Widz, S.: Decision Bireducts and Approximate Decision Reducts: Comparison of Two Approaches to Attribute Subset Ensemble Construction. In: Ganzha, M., Maciaszek, L.A., Paprzycki, M. (eds.) Federated Conference on Computer Science and Information Systems – FedCSIS 2012, Wrocław, Poland, September 9-12, pp. 331–338. IEEE (2012)Google Scholar
- 11.Frank, A., Asuncion, A.: UCI Machine Learning Repository (2010), http://archive.ics.uci.edu/ml
- 12.Brodersen, K.H., Ong, C.S., Stephan, K.E., Buhmann, J.M.: The Balanced Accuracy and Its Posterior Distribution. In: 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, August 23-26, pp. 3121–3124. IEEE (2010)Google Scholar