CLASSIFICATION USING HIGH ORDER DISSIMILARITIES IN NON-EUCLIDEAN SPACES

Helena Aidos, Ana Fred, Robert P. W. Duin

2012

Abstract

This paper introduces a novel classification algorithm named MAP-DID. This algorithm combines a maximum a posteriori (MAP) approach using the well-known Gaussian Mixture Model (GMM) method with a term that forces the various Gaussian components within each class to have a common structure. That structure is based on higher-order statistics of the data, through the use of the dissimilarity increments distribution (DID), which contains information regarding the triplets of neighbor points in the data, as opposed to typical pairwise measures, such as the Euclidean distance. We study the performance ofMAP-DID on several synthetic and real datasets and on various non-Euclidean spaces. The results show that MAP-DID outperforms other classifiers and is therefore appropriate for classification of data on such spaces.

References

  1. Aidos, H. and Fred, A. (2011). On the distribution of dissimilarity increments. In IbPRIA, pages 192-199.
  2. Duda, R. O., Hart, P. E., and Stork, D. G. (2001). Pattern Classification. John Wiley & Sons Inc., 2nd edition.
  3. Duin, R., Pekalska, E., Harol, A., Lee, W.-J., and Bunke, H. (2008). On euclidean corrections for non-euclidean dissimilarities. In SSPR/SPR, pages 551-561.
  4. Duin, R. P. and Pekalska, E. (2008). On refining dissimilarity matrices for an improved nn learning. In ICPR.
  5. Figueiredo, M. and Jain, A. (2002). Unsupervised learning of finite mixture models. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(3):381-396.
  6. Fred, A. and Leita˜o, J. (2003). A new cluster isolation criterion based on dissimilarity increments. IEEE Trans. on Pattern Analysis and Machine Intelligence, 25(8):944-958.
  7. Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, 2nd edition.
  8. Pekalska, E. (2005). Dissimilarity Representations in Pattern Recognition: Concepts, Theory and Applications. PhD thesis, Delft University of Technology, Delft, Netherland.
  9. Su, T. and Dy, J. G. (2007). In search of deterministic methods for initializing k-means and gaussian mixture clustering. Intelligent Data Analysis, 11(4):319-338.
Download


Paper Citation


in Harvard Style

Aidos H., Fred A. and P. W. Duin R. (2012). CLASSIFICATION USING HIGH ORDER DISSIMILARITIES IN NON-EUCLIDEAN SPACES . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8425-98-0, pages 306-309. DOI: 10.5220/0003779503060309


in Bibtex Style

@conference{icpram12,
author={Helena Aidos and Ana Fred and Robert P. W. Duin},
title={CLASSIFICATION USING HIGH ORDER DISSIMILARITIES IN NON-EUCLIDEAN SPACES},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2012},
pages={306-309},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003779503060309},
isbn={978-989-8425-98-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - CLASSIFICATION USING HIGH ORDER DISSIMILARITIES IN NON-EUCLIDEAN SPACES
SN - 978-989-8425-98-0
AU - Aidos H.
AU - Fred A.
AU - P. W. Duin R.
PY - 2012
SP - 306
EP - 309
DO - 10.5220/0003779503060309