Abstrakt

Study on local graph embedding method with maximal margin criterion

Zhiyong Zhang, Yan Li, Xiaohua Sun

To deal with the efficiency problem of local linear embedding (LLE) method and maximum margin criterion (MMC) method in attribute selection, an effective classification and dimension reduction method, local embedded graph attribute selection algorithm based on maximal region is to generate the inherent graph and penalty graph, with the nearest neighbor premise preservation. With inherent picture, the structured nonlinear can be found on the high-dimensioned space by using local geometry of the restructured linear, which leads to the same instances gathering together as more as possible. Meanwhile, different class instances are as far as possible from each other in penalty picture. In this method, the smallest size instance issue was tackled by the employment of MMC and the neighborhood relationship can be better described by an adequate improvement of the adjacency matrix. The effects of facial recognition tests for Yale, AR and ORL facial data bases show that the effectiveness of the proposed new algorithm performs well in comparison with other related outstanding methods