PCA Supervised and Unsupervised Classifiers in Signal Processing

Catalina Cocianu, Luminita State, Panayiotis Vlamos, Constantin Doru, Corina Sararu

2009

Abstract

The aims of the research reported in this paper are to investigate the potential of principal directions-based approach in supervised and unsupervised frameworks. The structure of a class is represented in terms of the estimates of its principal directions computed from data, the overall dissimilarity of a particular object with a given class being given by the “disturbance” of the structure, when the object is identified as a member of this class. In case of unsupervised framework, the clusters are computed using the estimates of the principal directions. Our attempt uses arguments based on the principal components to refine the basic idea of k-means aiming to assure soundness and homogeneity to the resulted clusters. Each cluster is represented in terms of its skeleton given by a set of orthogonal and unit eigen vectors (principal directions) of sample covariance matrix, a set of principal directions corresponding to the maximum variability of the “cloud” from metric point of view. A series of conclusions experimentally established are exposed in the final section of the paper.

References

  1. Chatterjee, C., Roychowdhury, V.P., Chong, E.K.P.: On Relative Convergence Properties of PCA Algorithms, IEEE Trans. on Neural Networks, vol.9,no.2 (1998).
  2. Cocianu, C., State, L., Rosca, I., Vlamos, P: A New Adaptive Classification Scheme Based on Skeleton Information, Proceedings of SIGMAP 2007 (2007).
  3. Diamantaras, K.I., Kung, S.Y.: Principal Component Neural Networks: theory and applications, John Wiley &Sons, (1996).
  4. Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood Component Analysis, Proceedings of the Conference on Advances in Neural Information Processing Systems (2004).
  5. Gordon, A.D.: Classification, Chapman&Hall/CRC, 2nd Edition (1999).
  6. Haykin, S., Neural Networks A Comprehensive Foundation, Prentice Hall,Inc. (1999).
  7. Hastie, T., Tibshirani, R., Friedman,J.: The Elements of Statistical Learning Data Mining, Inference, and Prediction, Springer (2001).
  8. Hyvarinen, A., Karhunen, J., Oja, E. Independent Component Analysis, John Wiley &Sons (2001).
  9. Larose, D.T. Data Mining. Methods and Models, Wiley-Interscience, A John Wiley and Sons, Inc Publication, Hoboken, New Jersey (2006).
  10. Liu, J., and Chen, S. Discriminant common vectors versus neighborhood components analysis and Laplacianfaces: A comparative study in small sample size problem. Image and Vision Computing 24 (2006).
  11. State, L., Cocianu, C., Vlamos, P, Stefanescu, V. PCA-Based Data Mining Probabilistic and Fuzzy Approaches with Applications in Pattern Recognition, Proceedings of ICSOFT 2006 (2006).
  12. State, L., Cocianu, C., Rosca, I., Vlamos, P: A New Learning Algorithm for Classification in the Reduced Space, Proceedings of ICEIS 2008 (2008).
Download


Paper Citation


in Harvard Style

Cocianu C., State L., Vlamos P., Doru C. and Sararu C. (2009). PCA Supervised and Unsupervised Classifiers in Signal Processing . In Proceedings of the 9th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2009) ISBN 978-989-8111-89-0, pages 61-70. DOI: 10.5220/0002195000610070


in Bibtex Style

@conference{pris09,
author={Catalina Cocianu and Luminita State and Panayiotis Vlamos and Constantin Doru and Corina Sararu},
title={PCA Supervised and Unsupervised Classifiers in Signal Processing},
booktitle={Proceedings of the 9th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2009)},
year={2009},
pages={61-70},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002195000610070},
isbn={978-989-8111-89-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2009)
TI - PCA Supervised and Unsupervised Classifiers in Signal Processing
SN - 978-989-8111-89-0
AU - Cocianu C.
AU - State L.
AU - Vlamos P.
AU - Doru C.
AU - Sararu C.
PY - 2009
SP - 61
EP - 70
DO - 10.5220/0002195000610070