非线性回归支持向量机的SMO算法改进

赵长春; 姜晓爱; 金英汉

非线性回归支持向量机的SMO算法改进

1.
北京航空航天大学航空科学与工程学院, 北京 100191
2. 西北工业大学航天学院, 西安 710072

详细信息

中图分类号: TP301.6
计量
- 文章访问数: 2021
- HTML全文浏览量: 255
- PDF下载量: 585
- 被引次数: 0
出版历程
- 收稿日期: 2013-01-28
- 网络出版日期: 2014-01-20

Improved SMO algorithm of nonlinear regression support vector machine

1.
School of Aeronautic Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
2. School of Astronautics, Northwestern Polytechnical University, Xi'an 710072, China

摘要

摘要: 为了解决非线性数据和非线性函数的回归问题，采用了支持向量机序列最小优化算法.原始序列最小优化（SMO，Sequential Minimal Optimization）算法存在训练速度慢和训练结果不稳定的缺点，为了能加快SMO算法的训练速度和提高训练结果稳定性，通过改进优化乘子更新方法、采用双阈值法、预存核函数、增加停机准则等方法对SMO算法做了改进.仿真实验表明，改进的算法能很好地对非线性数据和非线性函数进行回归，具有比原始SMO算法更快的训练速度和稳定的训练结果.
- 支持向量机 /
- 回归;非线性数据;非线性函数;序列最小优化算法
Abstract: In order to solve the regression problems of nonlinear data and nonlinear function, the support vector machine (SVM) sequential minimal optimization (SMO) algorithm was adopted. The original SMO algorithm has deficiencies such as low training speed and instability training results. To accelerate the training process of SMO algorithm and promote training stability of the solution, the SMO algorithm was improved by updating the optimization multipliers method, using double threshold values, caching kernel function outputs, adding stop criterion. Simulation results show that the improved algorithm performs well for regression of nonlinear data and nonlinear function, and it has faster training speed and better training result stability than original SMO algorithm.
- support vector machine /
- regression

HTML全文

参考文献(10)

[1]	Platt J C.Fast training of support vector machines using sequential minimal optimization[R].MSR-TR-98-14, 1998
[2]	Smola A J, Scholkopf B.A tutorial on support vector regression[R].NC2-TR-1998-030, 1998
[3]	Shevade S K, Keerthi S S, Bhattacharyya C, et al.Improvements to SMO algorithm for SVM regression[J].IEEE Transactions on Neural Networks, 2000, 11(5):1188-1193
[4]	Flake G W, Lawrence S．Efficient SVM regression training with SMO[J].Machine Learning, 2002, 46(1-3):271-290
[5]	张浩然, 韩正之.回归支持向量机的改进序列最小优化学习算法[J].软件学报, 2003, 14(12):2006-2013 Zhang Haoran, Han Zhengzhi.An improved sequential minimal optimization learning algorithm for regression support vector machine[J].Journal of Software, 2003, 14(12):2006-2013 (in Chinese)
[6]	刘胜, 李妍妍.自适应GA-SVM参数选择算法研究[J].哈尔滨工程大学学报, 2007, 28(4):398-402 Liu Sheng, Li Yanyan.Parameter selection algorithm for support Vector machines based on adaptive genetic algorithm[J].Journal of Harbin Engineering University, 2007, 28(4):398-402 (in Chinese)
[7]	闫国华, 朱永生.支持向量机回归的参数选择方法[J].计算机工程, 2009, 35(14):218-220 Yan Guohua, Zhu Yongsheng.Parameters selection method for support vector machine regression[J].Computer Engineering, 2009, 35(14):218-220 (in Chinese)
[8]	董磊, 任章, 李清东.基于SMO-SVR的飞机舵面损伤故障趋势预测[J].北京航空航天大学学报, 2012, 38(10): 1300-1305 Dong Lei, Ren Zhang, Li Qingdong.Fault prediction for aircraft control surface damage based on SMO-SVR[J].Journal of Beijing University of Aeronautics and Astronautics, 2012, 38(10):1300-1305 (in Chinese)
[9]	王书舟, 伞冶, 张允昌.基于支持向量机改进 SMO 算法的直升机旋翼自转着陆过程建模[J].航空学报, 2009, 30(1): 46-51 Wang Shuzhou, San Ye, Zhang Yunchang.Modeling for landing process of helicopter with rotator self-rotating based on modified SMO algorithm of support vector machine[J].Acta Aeronautica et Astronautica Sinica, 2009, 30(1):46-51(in Chinese)
[10]	王定成.支持向量机建模预测与控制[M].北京:气象出版社, 2009:48-49 Wang Dingcheng.Prediction and control based on support vector machine modelling[M].Beijing:Meteorological Press, 2009:48-49(in Chinese)