RETRACTED: Incorporating discriminative neighborhood preserving constraints for improved support vector classification (Retracted Article)

In this paper a new SVM-based classification model is proposed by adding discriminative neighborhood preserving constraints. It obtains separating hyperplane from the combination of the support vector of the traditional SVM as well as the geometric and discriminant structure arise from the within-class and between-class neighborhood preserving matrices. These matrices characterize the two kinds of neighborhood geometric structures of data manifolds that are more helpful for obtaining consistent separating hyperplane than the isolated support vectors. The proposed model can be deduced to the generalized framework of SVM with some extra preprocessing for efficient and uniform computation, which makes it more attractive for real world applications. Experimental results on public data sets show that the proposed method has comparable or better generalization ability compared to some related SVMs algorithms. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Organizers of 2011 International Conference on Energy and Environmental Science.