Abstract
A new model parameter selection method for support vector machine based on adaptive fusion of multiple kernel functions is proposed in this paper. Characteristics of local kernels, global kernels, mixtures of kernels and multiple kernels were analyzed. Fusion coefficients of the multiple kernel function, kernel function parameters and regression parameters are combined to form the parameters of the state vector. Thus, the model selection problem is transformed into a nonlinear system state estimation problem. Then, we use a fifth-degree cubature Kalman filter to estimate the parameters. In this way, we realize adaptive selection of the multiple kernel function weighted coefficient, the kernel parameters and the regression parameters. A simulation experiment was performed to interpret the PE process for fault diagnosis.
Similar content being viewed by others
References
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Wu J (2014) Efficient HIK SVM learning for image classification. IEEE Trans Image Process 21(10):4442–4453
Liu XL, Ding SF, Zhu H (2010) Appropriateness in applying SVMs to text classification. Comput Eng Sci 32(6):106–108
Xie SQ, Sheng FM, Qiu XN (2009) Face recognition method based on support vector machine. Comput Eng 35(16):186–188
Xiao HJ, Wang XF, Hong F (2016) Attribute selection-based and support vector machine for anomaly detection. J Huazhong Univ Sci Technol (Nat Sci Ed) 36(3):99–102
Dileep AD, Sekhar CC (2009) Representation and feature selection using multiple kernel learning. In: Proceedings of international joint conference on neural networks, Atlanta, 14–19 June
Lin YY, Liu TL, Fuh CS (2014) Local ensemble kernel learning for object category recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, Washington D. C. IEEE, pp 1–8
Mak B, Kwok JT, Ho S (2014) A study of various composite kernels for kernel eigenvoice speaker adaptation. In: Proceedings of the IEEE international conference on acoustics, speech, and signal processing, Montreal. IEEE, pp 325–328
Zhang N, Xia ZQ, Jiang H (2010) Prediction of runoff based on the multiple quantity index of SVM. J Hydraul Eng 40(11):1318–1324
Mu T, Nandi AK (2013) Automatic tuning of L2-SVM parameters employing the extended Kalman filter. Expert Syst 26(2):160–175
Rakotomamonjy A, Bach FR, Canu S, Grandvalet Y (2015) Simple MKL. J Mach Learn Res 9(11):2491–2521
Bach FR (2008) Consistency of the group Lasso and multiple kernel learning. J Mach Learn Res 9(6):1179–1225
Ong CS, Smola AJ, Williamson RC (2015) Learning the kernel with hyperkernels. J Mach Learn Res 6(7):1043–1071
Jia B, Xin M, Cheng Y (2015) High-degree cubature Kalman filter. Automatica 49(2):510–518
Xu Z, Jin R, Yang H et al (2015) Simple and efficient multiple kernel learning by group lasso. In: Proc. of the 27th international conference on machine learning, Haifa, pp 1175–1182
Lee WJ, Verzakov S, Duin RPW (2013) Kernel combination versus classifier combination. In: Proceedings of the multiple classifier systems. Springer, Berlin, pp 22–31
Bach FR, Lanckriet GRG, Jordon MI (2004) Multiple kernel learning, conic duality, and the SMO algorithm. In: Proc of the 21st international conference on machine learning, Banff, pp 41–48
Sonnenburg S, Ratsch G, Schafer C et al (2006) Large scale multiple kernel learning. J Mach Learn Res 7(1):1531–1565
Rakotomamonjy A, Bach F, Canu S et al (2008) Simple MKL. J Mach Learn Res 9:2491–2521
Kloft M, Brefeld U, Laskov P et al (2008) Non-sparse multiple kernel learning. In: Proc of the NIPS workshop on kernel learning: automatic selection of optimal kernels
Kloft M, Brefeld U, Sonnenburg S et al (2009) Efficient and accurate L p-norm multiple kernel learning. In: Advance in neural information processing systems vol 22, pp 997–1005
Nath JS, Dinesh G, Raman S et al (2009) On the algorithmics and applications of a mixed-norm based kernel learning formulation. In: Advances in neural information processing systems vol 22, pp 844–852
Cortes C, Mohri M, Rostamizadeh A (2014) Learning non-linear combinations of kernels. In: Advances in neural information processing systems vol 22, pp 396–404
Mu S, Tian S, Yin C (2015) Multiple kernel learning based on cooperative clustering. J Beijing Jiaotong Univ 32(2):10–13
Wang HQ, Sun FC, Cai YN et al (2016) On multiple kernel learning methods. Acta Automatica Sinica 36(8):1037–1050
Qiu SB, Lane T (2012) Multiple kernel support vector regression for RNA efficacy prediction. In: Proceedings of the 4th international conference on bioinformatics research and applications, Atlanta. Springer, pp 367–378
Bosch A, Zisserman A, Munoz X (2014) Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM international conference on image and video retrieval, Amsterdam. ACM, pp 401–408
Liu Y (2015) Study on kernel function of support vector machine. Ph.D. dissertation, Xidian University, China
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27
Acknowledgements
This work was supported by the Natural Science Foundation of China (61403229, 61503213) and Zhejiang Provincial Natural Science Foundation of China (LY13F030011, LQ17F030005).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, H., Xu, D. & Martinez, A. Parameter selection method for support vector machine based on adaptive fusion of multiple kernel functions and its application in fault diagnosis. Neural Comput & Applic 32, 183–193 (2020). https://doi.org/10.1007/s00521-018-3792-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3792-7