Construction method and device, classification method and device of support vector machine

Abstract

The invention provides a construction method and device, a classification method and device of support vector machine. The construction method and device, the classification method and device of support vector machine comprises: make sure non-linear weighted kernel function of a single variable; make sure nonconvex Lpfraction norm penalty object function on the base of the weighted kernel function of a single variable; make use of nonconvex Lpfraction norm penalty object function to construct support vector machine. Compared with the technical proposal which needs to traverse all characteristic combination of dimension to look for the desired characteristics when high-dimensional data of small sample is classified in the existing technology, the invention constructs the support vector machine and the support vector machine is used to classify the high-dimensional data of small sample so as to produce more sparse model, to achieve feature selection of any structure more accurately, to obtain better prediction accuracy, to reduce computation complexity largely and to avoid data disaster.

Description

technical field [0001] The present invention relates to the technical field of intelligent information processing, in particular to a construction method and device of a Support Vector Machine (SVM for short) classifier, and a classification method and device. technical background [0002] In the fields of computer vision, such as three-dimensional brain magnetic resonance imaging, bioinformatics, cancer microarray gene diagnosis, and customer relationship analysis on commercial websites, there are a large number of high-dimensional small-sample data, which is characterized by high-dimensional and small-sample data. Dimensional data, the sample dimension is as high as several thousand to tens of thousands of dimensions. It is difficult to obtain the class labels of high-dimensional small-sample data samples. If manual labeling is used, the cost is relatively high, resulting in fewer samples with class labels, and the number of sample-class label pairs is also relatively smal...

AI Technical Summary

Problems solved by technology

The usual L2 norm regularized SVM needs to traverse all combinations of feature dimensions to find the required features, resulting in high computational complexity and easy to cause data disasters

Images