Research Papers
Linear and support vector regressions based on geometrical correlation of data
Authors:
Kaijun Wang ,
School of Computer Science and Engineering, Xidian University, Xian 710071, P. R. China.
Junying Zhang,
School of Computer Science and Engineering, Xidian University, Xian 710071, P. R. China.
Lixin Guo,
Dept of Computer Science, Xian Institute of Post-telecommunications, Xian 710061, P. R. China.
Chongyang Tu
School of Computer Science and Engineering, Xidian University, Xian 710071, P. R. China.
Abstract
Linear regression (LR) and support vector regression (SVR) are widely used in data analysis. Geometrical correlation learning (GcLearn) was proposed recently to improve the predictive ability of LR and SVR through mining and using correlations between data of a variable (inner correlation). This paper theoretically analyzes prediction performance of the GcLearn method and proves that GcLearn LR and SVR will have better prediction performance than traditional LR and SVR for prediction tasks when good inner correlations are obtained and predictions by traditional LR and SVR are far away from their neighbor training data under inner correlation. This gives the applicable condition of GcLearn method.
How to Cite:
Wang, K. et al., (2007). Linear and support vector regressions based on geometrical correlation of data. Data Science Journal. 6, pp.99–106. DOI: http://doi.org/10.2481/dsj.6.99
Published on 05 Oct 2007.
Peer Reviewed
Downloads
