Share This Article:

Finding the Asymptotically Optimal Baire Distance for Multi-Channel Data

Abstract Full-Text HTML XML Download Download as PDF (Size:823KB) PP. 484-495
DOI: 10.4236/am.2015.63046    3,429 Downloads   3,832 Views   Citations


A novel permutation-dependent Baire distance is introduced for multi-channel data. The optimal permutation is given by minimizing the sum of these pairwise distances. It is shown that for most practical cases the minimum is attained by a new gradient descent algorithm introduced in this article. It is of biquadratic time complexity: Both quadratic in number of channels and in size of data. The optimal permutation allows us to introduce a novel Baire-distance kernel Support Vector Machine (SVM). Applied to benchmark hyperspectral remote sensing data, this new SVM produces results which are comparable with the classical linear SVM, but with higher kernel target alignment.

Conflicts of Interest

The authors declare no conflicts of interest.

Cite this paper

Bradley, P. and Braun, A. (2015) Finding the Asymptotically Optimal Baire Distance for Multi-Channel Data. Applied Mathematics, 6, 484-495. doi: 10.4236/am.2015.63046.


[1] Contreras, P. and Murtagh, F. (2010) Fast Hierarchical Clustering from the Baire Distance. In: Locarek-Junge, H. and Weighs, C., Eds., Classification as a Tool for Research, Springer Berlin Heidelberg, Germany, 235-243.
[2] Cristianini, N., Shawe-Taylor, J., Elisseeff, A. and Kandola, J. (2006) On Kernel Alignment. In: Holmes, D.E., Ed., Innovations in Machine Learning, Springer Berlin Heidelberg, Germany, 205-256.
[3] Murtagh, F. (2004) On Ultrametricity, Data Coding, and Computation. Journal of Classification, 21, 167-184.
[4] Benois-Pineau, J., Khrennikov, A.Y. and Kotovich, N.V. (2001) Segmentation of Images in p-Adic and Euclidean Metrics. Doklady Mathematic, 64, 450-455.
[5] Bradley, P.E. (2010) Mumford Dendrograms. The Computer Journal, 53, 393-404.
[6] Bradley, P.E. (2008) Degenerating Families of Dendrograms. Journal of Classification, 25, 27-42.
[7] Bradley, P.E. (2009) On p-Adic Classification. p-Adic Numbers, Ultrametric Analysis, and Applications, 1, 271-285.
[8] Cortes, C. and Vapnik, V. (1995) Support-Vector Networks. Machine Learning, 20, 273-297.
[9] Braun, A.C. (2010) Evaluation of One-Class SVM for Pixe-Based and Segment-Based Classification in Remote Sensing. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 38, 160-165.
[10] Braun, A.C., Weidner, U., Jutzi, B. and Hinz, S. (2011) Integrating External Knowledge into SVM Classification—Fusing Hyperspectral and Laserscanning Data by Kernel Composition. In: Heipke, C., Jacobsen, K., Rottensteiner, F., Müller, S. and Sörgel, U., Eds., High-Resolution Earth Imaging for Geospatial Information, International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 38, Part 4/W19 (on CD).
[11] Amari, S. and Wu, S. (1999) Improving Support Vector Machine Classifiers by Modifying Kernel Functions. Neural Networks, 12, 783-789.
[12] Braun, A.C., Weidner, U., Jutzi, B. and Hinz, S. (2012) Kernel Composition with the One-against-One Cascade for Integrating External Knowledge into SVM Classification. Photogrammetrie-Fernerkundung-Geoinformation, 2012, 371-384.
[13] Sonnenburg, S., Rätsch, G., Schäfer, C. and Schölkopf, B. (2006) Large Scale Multiple Kernel Learning. The Journal of Machine Learning Research, 7, 1531-1565.
[14] Braun, A.C., Weidner, U. and Hinz, S. (2010) Support Vector Machines for Vegetation Classification? A Revision. Photo-grammetrie-Fernerkundung-Geoinformation, 2010, 273-281.

comments powered by Disqus

Copyright © 2019 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.