Cluster pca for outliers detection in high-dimensional data

@article{Stefatos2007ClusterPF,
  title={Cluster pca for outliers detection in high-dimensional data},
  author={George Stefatos and A. Ben Hamza},
  journal={2007 IEEE International Conference on Systems, Man and Cybernetics},
  year={2007},
  pages={3961-3966}
}
We introduce a new method to detect multiple outliers in high-dimensional datasets using the concepts of hierarchical clustering and principal component analysis. The proposed algorithm is computationally fast and robust to outliers detection. A comparative study with existing techniques is performed on both low and high dimensional datasets. Our experimental results demonstrate an improved performance of our algorithm in comparison with existing multivariate outlier detection techniques. 

References

Publications referenced by this paper.
Showing 1-10 of 12 references

Outlier detection in multivariate analytical chemical data.

Analytical chemistry • 1998
View 5 Excerpts
Highly Influenced

Distance-based detection and prediction of outliers

IEEE Transactions on Knowledge and Data Engineering • 2006
View 1 Excerpt

Introduction to Statistical Quality Control

D. C. Montgomery
2005
View 1 Excerpt

Robust estimation in multivariate control charts for individual observations

J. A. Vargas
Journal of Quality Technology, vol. 35, no. 4, October 2003. • 2003
View 3 Excerpts

Similar Papers

Loading similar papers…