Skip to Main Content
In this paper, we study two measures of classification complexity based on feature space partitioning: purity and neighborhood separability. The new measures of complexity are compared with probabilistic distance measures and a number of other nonparametric estimates of classification complexity on a total of 10 databases from the University of California, Irvine, (UCI) repository.
Pattern Analysis and Machine Intelligence, IEEE Transactions on (Volume:25 , Issue: 12 )
Date of Publication: Dec. 2003