A new multi-class classification method based on minimum enclosing balls

다국어 초록 (Multilingual Abstract)

With respect to classification problems, the Minimum enclosing ball (MEB) method was recently studied by some scholars as a newsupport vector machine. As a nascent technology, however, MEB reports poor adaptability for different types of samples, especiallymulti-class samples. In this paper, we propose a new multi-class classification method based on MEB. This method is derived from eachclass sample center and radius with the Gaussian kernel width factor parameter σ, which is labelled as σ-MEB. σ is a variable parameteraccording to the different sample characteristics. When this parameter is considered, the multi-class classifier is easy to adapt and is robustin diverse datasets. The quadratic programming problem was transformed into its dual form with Lagrange multipliers using thismethod. Finally, we applied sequential minimal optimization method and Karush—Kuhn—Tucker conditions to accelerate the trainingprocess. Numerical experiment results indicate that given different types of samples, the proposed method is more accurate than themethods with which it is compared. Moreover, the proposed method reports values in the upper quantile with respect to adaptation performance.

참고문헌 (Reference)

1 W. F. Cheng, "Wavelet correlation feature scale entropy and fuzzy support vector machine approach for aeroengine whole-body vibration fault diagnosis" 20 : 341-349, 2013

2 N. Bassam, "Utilizing wavelet transform and support vector machine for detection of the paradoxical splitting in the second heart sound" 48 : 177-184, 2010

3 E. Frandi, "Training support vector machines using Frank-Wolfe optimization methods" 27 (27): 1360003-1360001, 2013

4 L. L. Diao, "Training SVM email classifiers using very large imbalanced dataset" 24 (24): 193-210, 2012

5 Y. Li, "Thirty cases analysis of MATLAB neural network" Beijing University of Aeronautics and Astronautics Press 2010

6 P. S. Kang, "Support vector class description (SVCD): Classification in kernel space" 16 : 351-364, 2012

7 L. P. Jing, "Sparse label-indicator optimization methods for image classification" 23 (23): 1002-1014, 2014

8 E. Welzl, "Smallest enclosing disks (balls and ellipsoids)" 555 : 359-370, 1991

9 T. Le, "Proximity multi-sphere support vector clustering" 22 : 1309-1319, 2013

10 J. L. Balcázar, "Provably fast training algorithms for support vector machines" 42 : 568-595, 2008

11 J. Mashford, "Prediction of sewer condition grade using support vector machines" 25 (25): 283-290, 2011

12 X. L. Tang, "Multi-fault pattern recognition based on support vector machine trained by chaos particle swarm optimization" 23 : 486-490, 2010

13 N. Collier, "Learning to recognize phenotype candidates in the auto-immune literature using SVM re-ranking" 8 (8): 1-15, 2013

14 F. F. Li, "Group enclosing queries" 23 (23): 1526-1540, 2011

15 Y. Mao, "Gene selection using Gaussian kernel support vector machine based recursive feature elimination with adaptive kernel width strategy" 4062 : 799-806, 2006

16 B. Zaman, "Fusion of remotely sensed data for soil moisture estimation using relevance vector and support vector machines" 33 (33): 6516-6552, 2012

17 F. L. Chung, "From minimum enclosing ball to fast fuzzy inference system training on large datasets" 17 (17): 173-184, 2009

18 ShengFa Yuan, "Fault diagnosis using binary tree and sphere-structured support vector machines" 대한기계학회 26 (26): 1431-1438, 2012

19 Ouahab Kadri, "Fault diagnosis of rotary kiln using SVM and binary ACO" 대한기계학회 26 (26): 601-608, 2012

20 R. C. Conceição, "Evaluation of features and classifiers for classification of early-stage breast cancer" 25 : 1-14, 2011

21 T. Nakagawa, "Defect classification of electronic board using multiple classifiers and grid search of SVM parameters" 493 : 115-127, 2013

22 I. Tsang, "Core vector machines:fast SVM training on very large data sets," 6 : 363-392, 2005

23 J. Amores, "Context-based objectclass recognition and retrieval by generalized correlograms" 29 : 1818-1833, 2007

24 A. K. Verma, "Comparative study of cognitive systems for ground vibration measurements" 22 : S341-S350, 2013

25 M. Jian, "Class-discriminative kernel sparse representation-based classification using multi-objective optimization" 61 (61): 4416-4427, 2013

26 J. G. Wang, "Bayes classification based on minimum bounding spheres" 70 : 801-808, 2007

27 M. Mohammadi, "Application of multi-class support vector machines for power system online static security assessment using DT-based feature and data selection algorithms" 20 : 133-146, 2009

28 X. W. Liu, "An efficient approach to integrating radius information into multiple kernel learning" 43 (43): 757-569, 2013

29 J. C. B. Christopher, "A tutorial on support vector machines for pattern recognition" 2 : 121-167, 1998

30 P. Y. Hao, "A new maximalmargin spherical-structured multi-class support vector machine" 30 : 98-111, 2009

31 W. T. Mao, "A new SVM regression approach for mechanical load identification" 33 : 1001-1008, 2010

32 T. Kamali, "A multi-classifier approach to MUAP classification for diagnosis of neuromuscular disorders" 22 (22): 191-200, 2014