Isaac Scientific Publishing

Frontiers in Signal Processing

Application of a Sparse Least Squares Support Vector Machine Algorithm in Radar Target Recognition

Download PDF (999.1 KB) PP. 31 - 46 Pub. Date: April 1, 2018

DOI: 10.22606/fsp.2018.22001

Author(s)

  • Zhao Dongbo*
    School of Electronic Engineering, Xi'an Aeronautical University, Xi’an,710077,China
  • Li Hui
    School of Electronic Information, Northwestern Polytechnical University, Xi’an,710129,China

Abstract

Least squares support vector machine (LS-SVM) has a large amount of computation and sparsity. Aiming at this problem, a fast sparse approximation least squares support vector machine (FSALS-SVM) algorithm is proposed. The algorithm uses an iterative algorithm of complexity to ac-celerate the calculation of the inverse of the kernel matrix and the sparse processing of the support vector machine through the pruning algorithm, thus reducing the computational complexity. The classification and recognition experiments of one dimension range profile of one dimensional radar target show that the FSALS-SVM is more sparsely under the same generalization performance.

Keywords

Least Squares Support Vector Machine (LS-SVM); Fast Sparse Approximation Least Squares Support Vector Machine (FSALS-SVM); pruning algorithm; Kernel Principal Component Analysis (KPCA); Central moment; Radar Target Recognition

References

[1] Ebuchi F, Kitamura T. Fast Sparse Least Squares Support Vector Machines by Block Addition[C]. International Symposium on Neural Networks. Springer, Cham, 2017:60-70.

[2] Shao Y H, Li C N, Liu M Z, et al. Sparse L q -norm least squares support vector machine with feature selection[J]. Pattern Recognition, 2018, 78:167-181.

[3] Ma W, Liu H. Sparse least square support vector machines based on random entropy[C].Control Conference. IEEE, 2017:333-337.

[4] Zhang C H, Chen Y, Cao S H, et al. A Sparse Algorithm Based on Tsallis Entropy for Least Squares Support Vector Machine[J]. Fire Control & Command Control, 2017.

[5] Yang Z, Zhou Z, Jiang Y. Least squares support vector machine with parametric margin for binary classification1[J]. Journal of Intelligent & Fuzzy Systems, 2016, 30(5):2897-2904.

[6] Liu D, Shi Y, Tian Y, et al. Ramp loss least squares support vector machine[J]. Journal of Computational Science, 2016, 14:61-68.

[7] Si G, Shi J, Zhang G, et al. Density clustering pruning method based on reconstructed support vectors for sparse LSSVM[C].Control and Decision Conference. IEEE, 2016:3582-3587.

[8] Peng J X, Rafferty K, Ferguson S. A fast algorithm for sparse support vector machines for mobile computing applications[J]. Neurocomputing, 2016, 230.

[9] Nan S, Sun L, Chen B, et al. Density-Dependent Quantized Least Squares Support Vector Machine for Large Data Sets.[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 28(1):94-106.

[10] Shi J, Si G, Guo Z, et al. A pruning strategy based on confidence interval for sparse LS-SVM[C].World Congress on Intelligent Control and Automation. 2016:577-582.

[11] Wong P K, Hang C W, Chi M V, et al. Online wavelet least-squares support vector machine fuzzy predictive control for engine lambda regulation[J]. International Journal of Engine Research, 2016, 17(8).

[12] Mageswari A U, Vinodha R. Engine knock detection based on wavelet packet transform and sparse fuzzy least squares support vector machines (SFLS-SVM)[J]. Iioab Journal, 2016, 7(11):194-199.

[13] Yang Z, Zhou Z, Jiang Y. Least squares support vector machine with parametric margin for binary classifica-tion1[J]. Journal of Intelligent & Fuzzy Systems, 2016, 30(5):2897-2904.