Clustering the Feature Space

@inproceedings{Ienco2008ClusteringTF,
  title={Clustering the Feature Space},
  author={Dino Ienco and Rosa Meo},
  booktitle={SEBD},
  year={2008}
}
In this paper we propose and test the use of hierarchical clustering for feature selection in databases. The clustering method is Ward’s with a distance measure based on Goodman-Kruskal τ . We motivate the choice of this measure and compare it with other ones. Our hierarchical clustering is applied to over 40 data-sets from UCI archive. The proposed approach is interesting from many viewpoints. First, it produces the feature subsets dendrogram which serves as a valuable tool to study relevance… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 14 REFERENCES

Efficient Feature Selection via Analysis of Relevance and Redundancy

  • J. Mach. Learn. Res.
  • 2004
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

On feature selection through clustering

  • Fifth IEEE International Conference on Data Mining (ICDM'05)
  • 2005
VIEW 2 EXCERPTS

John . Wrappers for feature subset selection

Ron Kohavi, H. George
  • Artificial Intelligence
  • 2003

Kruskal . Measures of association for cross classifications

Leo A. Goodman, H. William
  • Journal American Statistical Association
  • 1998