Abstract
Confronting with plenty of information from multiple targets and multiple sources, it is core and important to learn and decide for the bionic brain or robot within limited capacity in the bionic-technology field. Several multiclass multiple kernel learning algorithms are proposed instead of a single one, which can not only combine multiple kernels corresponding to different notions of similarity or information from multiple feature subsets, but also avoid kernel parameters selecting and fuse distinctions of multiple kernels. The core of these algorithms is the small sphere and large margin approach with hypersphere boundary, which takes the advantages of support vector machine (SVM) and support vector data description (SVDD), making the volume of sphere as small as well and the margin as large as possible, in other words, minimizing the within-class divergence like SVDD and maximizing the between-class margin like SVM. Meanwhile, The one-class essence of SSLM can relieve problem of the data imbalance. Besides, the one-against-all strategy is adopted for multiclass recognition. Hence, there will be a remarkable improvement of recognition accuracy. Numerical experiments based on three publicly UCI datasets demonstrate that using multiple kernels instead of a single one is useful and promising. These MMKL algorithms are ideal for classification and recognition of multiple targets and sources in artificial intelligence field.
Similar content being viewed by others
References
Jessica S, Janaina M, Christophe P, Josef P (2016) Decoding intracranial EEG data with multiple kernel learning method. J Neurosci Meth 261:19–28
Zhang X, Hu L (2016) A nonlinear subspace multiple kernel learning for financial distress prediction of Chinese listed companies. Neurocomputing 177:636–642
Bucak SS, Jin R, Jain AK (2014) Multiple kernel learning for visual object recognition: a review. IEEE Trans Pattern Anal 36:1354–1369
Wang Q, Gu Y, Tuia D (2016) Discriminative multiple kernel learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 54:3912–3927
Diosan L, Rogozan A, Pecuchet J (2012) Improving classification performance of Support Vector Machine by genetically optimising kernel shape and hyper-parameters. Appl Intell 36:280–294
Maldonado S, Lopez J (2017) Robust kernel-based multiclass support vector machines via second-order cone programming. Appl Intell 46(4):983–992
Kim M (2013) Accelerated max-margin multiple kernel learning. Appl Intell 38:45–57
Gonen M, Alpaydm E (2011) Multiple kernel learning algorithms. J Mach Learn Res 12:2211–2268
Peng Z, Gurram P, Kwon H, Yin W (2015) Sparse kernel learning-based feature selection for anomaly detection. IEEE Trans Aero Elec Sys 51:1698–1716
Huang H, Chuang Y, Chen C (2012) Multiple kernel fuzzy clustering. IEEE Trans Fuzzy Syst 20:120–134
Liu X, Wang L, Huang G, Zhang J, Yin J (2015) Multiple kernel extreme learning machine. Neurocomputing 149:253–264
Hao P, Chiang J, Lin Y (2009) A new maximal-margin spherical-structured multi-class support vector machine. Appl Intell 30:98–111
Wu M, Ye J (2009) A small sphere and large margin approach for novelty detection using training data with outliers. IEEE Trans Pattern Anal 31:2088–2092
Rakotomamonjy A, Bach FR, Canu S, Grandvalet Y (2008) SimpleMKL. J Mach Learn Res 9:2491–2521
Lopez J, Maldonado S, Carrasco M (2016) A novel multi-class SVM model using second-order cone constraints. Appl Intell 44:457–469
Nello C, John S (2000) An introduction to support vector maahines and other kernel-based learning methods. Cambridge University Press, Cambridge
Nello C, John S, Andre E, Jaz K (2010) On kernel-target alignment. Adv Neur Inf Proces Syst 179:367–373
Qiu S, Lane T (2009) A framework for multiple kernel support vector regression and its applications to siRNA efficacy prediction. IEEE ACM Trans Comput Bi 6:190–199
Gert RGL, Nello C, Peter B, Laurent EG, Michael IJ (2004) Learning the kernel matrix with semidefinite programming. J Mach Learn Res 5:27–72
Cortes C, Mohri M, Rostamizadeh A (2012) Algorithms for learning kernels based on centered alignment. J Mach Learn Res 13:795–828
Mu T, Nandi AK (2009) Multiclass classification based on extended support vector data description. IEEE Trans Syst Man Cy B 39:1206–1216
Acknowledgements
The authors gratefully acknowledge the helpful comments and suggestions of reviewers. This work was supported by National Natural Science Foundation of China (No.61372159).
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
1.1 Proof of (17)
Proof
The solution of coefficients can be rewritten as \({{\eta }^{*}}=\underset {{{\left \| \eta \right \|}_{2}}= 1}{\mathop {\arg \max }}\,\frac {{{\left ({{\eta }^{T}}a \right )}^{2}}}{{{\eta }^{T}}M\eta }\).
Let u = M 1/2 η,u ∗ = M 1/2 η ∗,then
Rewrite (35) as:
Hence, u ∗∈ V e c(M − 1/2 a),with ∥M − 1/2 u ∗∥2 = 1, whichleads to \({{\eta }^{*}}=\frac {{{M}^{{-1}/{2}\;}}a}{\left \| {{M}^{{-1}/{2}\;}}a \right \|}\).□
Rights and permissions
About this article
Cite this article
Guo, Y., Xiao, H. Multiclass multiple kernel learning using hypersphere for pattern recognition. Appl Intell 48, 2746–2754 (2018). https://doi.org/10.1007/s10489-017-1111-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-017-1111-0