Novel algorithm for constructing support vector machine regression ensemble

doi:10.1016/S1004-4132(06)60093-5

Journal of Systems Engineering and Electronics ›› 2006, Vol. 17 ›› Issue (3): 541-545.doi: 10.1016/S1004-4132(06)60093-5

出版日期:2006-09-25 发布日期:2006-09-25

Novel algorithm for constructing support vector machine regression ensemble

Li Bo , Li Xinjun & Ζhao Zhiyan

School of Management, Tianjin Univ., Tianjin 300072, P. R China

Online:2006-09-25 Published:2006-09-25

摘要/Abstract

关键词:

Abstract:

A novel algorithm for constructing support vector machine regression ensemble is proposed. As to regression prediction, support vector machine regression (SVMR) ensemble is proposed by resampling from given training data sets repeatedly and aggregating several independent SVMRs, each of which is trained to use a replicated training set. After training, several independently trained SVMRs need to be aggregated in an appropriate combination manner. Generally, the linear weighting is usually used like expert weighting score in Boosting Regression and it is without optimization capacity. Three combination techniques are proposed, including simple arithmetic mean, linear least square error weighting and nonlinear hierarchical combining that uses another upper-layer SVMR to

combine several lower-layer SVMRs. Finally, simulation experiments demonstrate the accuracy and validity of the presented algorithm.

Key words:

color:#000000, font-family:", sans serif", ,tahoma,verdana,helvetica, font-size:12px, font-style:normal, font-weight:400, text-decoration:none, ">SVMR ensemble, boosting regression, combination optimization strategy

. [J]. Journal of Systems Engineering and Electronics, 2006, 17(3): 541-545.

Li Bo , Li Xinjun & Ζhao Zhiyan.

Novel algorithm for constructing support vector machine regression ensemble

[J]. Journal of Systems Engineering and Electronics, 2006, 17(3): 541-545.

Novel algorithm for constructing support vector machine regression ensemble

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价