超平面支持向量机简化性能分析

doi:10.11959/j.issn.1000-0801.2015161

Abstract

Abstract:

Comparing with traditional support vector machine，hyperplane support vector machine （HPSVM）and hyperplane support vector machine for regression（HPSVMR）not only reduce the number of support vectors and calculation time but also have comparable accuracy.However，they have different simplification effect on different problems.The reasons for this phenomenon were analyzed，the conclusion that the lower the percentage of non-bound support vectors is，the more obvious the effect of simplification was pointed out.

Key words: pattern recognition, hyperplane support vector machine, reduced support vector machine, performance analysis

Hui Cheng,Jinglong Fang,Daquan Wang,Xingqi Wang. Performance Analysis of Simplification of Hyperplane Support Vector Machine[J]. Telecommunications Science, 2015, 31(8): 78-83.

Figures/Tables 4

References 12

1	Burges C J C . Simplified support vector decision rule. Proceedings of the 13th International Conference on Machine Learning， San Mateo，CA，USA， 1996： 71～77
2	Lin M K ， Lin J C . A study on reduced support vector machines. IEEE Transactions on Neural Networks， 2003，14（6）： 1449～1459
3	Shieh L H ， Kuo C C . A reduced data set method for support vector regression. Expert Systems with Applications， 2010，37（12）： 7781～7787
4	Lin H J ， Yeh J P . Optimal reduction of solutions for support vector machines. Applied Mathematics and Computation， 2009，214（2）： 329～335
5	Geebelen D ， Suykens J A K ， Vandewalle J . Reducing the number of support vectors of SVM classifiers using the smoothed separable case approximation. IEEE Transactions on Neural Networks and Learning Systems， 2012，23（4）： 682～688
6	Liang X ， Ma Y ， He Y ，et al. Fast pruning superfluous support vectors in SVMs. Pattern Recognition Letters， 2013，34（10）： 1203～1209
7	Severyn A ， Moschitti A . Fast support vector machines for convolution tree kernels. Data Mining and Knowledge Discovery， 2012，25（2）： 325～357
8	方景龙，陈铄，潘志庚等. 复杂分类问题支持向量机的简化. 电子学报， 2007，35（5）： 858～861 Fang J L ， Chen S ， Pan Z G ，et al. A simplification to support vector machine for complicated recognition problem. Acta Electronica Sinica， 2007，35（5）： 858～861
9	Fang J L ， Chen S ， Liang X W ，et al. An improved model of support vector machine for high noise data regression problem. Proceedings of the IET China Ireland International Conference on Information and Communications Technologies， Dublin，Ireland， 2007
10	Sch02lkopf B ， Burges C J C ， Smola A J . Advances in Kernel Methods：Support Vector Learning. Cambridge： MIT Press, 1998
11	Lee M ， Keerthi S ， Ong C ，et al. An efficient method for computing leave-one-out error in support vector machines with Gaussian kernels. IEEE Transactions on Neural Networks， 2004，15（3）： 750～757
12	全勇，杨杰，姚莉秀等. 基于连续过松弛方法的支持向量回归算法. 软件学报， 2004，15（2）： 200～206 Quan Y ， Yang J ， Yao X L ，et al. Successive over relaxation for support vector regression. Journal of Software， 2004，15（2）： 200～206

Metrics

Recommended 0

No Suggested Reading articles found!

数据集	支持向量个数				计算时间/ms		计算精度
数据集	0＜α＜C	α=C	SVM	HPSVM1	SVM	HPSVM1	SVM	HPSVM1
A1a	27	758	785	63	13 688	1 844	82.67%	82.65%
A2a	23	1 082	1 105	72	18 937	1 954	83.46%	83.405%
A3a	39	1 412	1 451	87	3 734	1 000	83.55%	83.52%
A4a	40	2 051	2 091	97	7 390	1 141	83.74%	83.86%
A5a	52	2 662	2 714	111	28 234	1 891	84.06%	84.10%
A6a	55	4 422	4 477	156	24 297	1 719	84.06%	84.10%
A7a	68	6 251	6 319	184	39 703	1 782	84.43%	84.48%
A8a	59	8 668	8 727	225	3 657	500	84.87%	84.87%
A9a	83	12 082	12 165	265	18 141	1 375	84.89%	84.80%

数据集	支持向量个数				计算精度
数据集	0＜α＜C	α=C	SVM	HPSVM1	SVM	HPSVM1
Breast Cancer	9	35	44	10	82.67%	82.65%
Heart	23	46	69	25	83.46%	83.40%
German	213	161	374	215	75.94%	75.94%
Splice	565	0	565	565	78.71%	79.81%

数据集	ε	支持向量个数				均方误差
数据集	ε	0＜α＜C	α=C	SVM	HPSVMR1	SVM	HPSVMR1
Abalone	4	63	242	305	61	5.52%	5.33%
	3	71	486	557	70	4.56%	4.68%
	2	82	952	103 4	93	4.18%	4.27%
	1.5	92	138 3	147 5	97	4.17%	4.26%
	1	104	201 1	211 5	101	4.21%	4.30%

[1]	Zhenlei DAN,Xuewen WU,Jian OUYANG,Xiaoxiao WANG,Chenwei GU. Outage performance analysis for multi-UAV relay systems with threshold-based DF protocol [J]. Telecommunications Science, 2020, 36(8): 103-111.
[2]	Yingzhao ZHU,Man LI. Current situation and development trend of gait recognition [J]. Telecommunications Science, 2020, 36(8): 130-138.
[3]	Chaolun BU,Yang XIAO,Tong YE,Peng WU,Xiaojian ZHANG,Junmin WU. Performance analysis of random access network with post-backoff [J]. Telecommunications Science, 2016, 32(2): 34-40.
[4]	Li Taoshen,Zhang Hongyu,Ye Jin and Ge Zhihui. Analysis Model of Gateway in Wireless Mesh Network Based on M/M/1 Queuing Model [J]. Telecommunications Science, 2015, 31(1): 2015044-.
[5]	Taoshen Li,Hongyu Zhang,Jin Ye,Zhihui Ge. Analysis Model of Gateway in Wireless Mesh Network Based on M/M/1 Queuing Model [J]. Telecommunications Science, 2015, 31(1): 58-64.
[6]	Gen Yuan,Tong Liu,Zhaoyang Shi. A Method of Abnormal Cell Analysis for Customer Experience Active Optimization [J]. Telecommunications Science, 2014, 30(8): 159-165.
[7]	Chenjie Huo,Shuxin Chen,Hengyang Zhang. A Performance Research on the Threshold-Based Decoding Algorithm in Cooperative Communications [J]. Telecommunications Science, 2013, 29(1): 97-102.

Performance Analysis of Simplification of Hyperplane Support Vector Machine

RichHTML

PDF下载

Knowledge

Cited

Abstract

Cite this article

share this article

Figures/Tables 4

References 12

Related Articles 7

Metrics

Recommended 0