Multi-classification method based on fuzzy support vector machine

Abstract

The invention discloses a multi-classification method based on a fuzzy support vector machine. The basic idea of fuzzy support vector machines (FSVMs) comprises the steps that the fuzzy technology is applied to a support vector machine, different punishment weight coefficients are adopted on different samples, when objective functions are established, different samples have different contributions, smaller weight is given to the samples containing noise or outliers, and therefore the purpose of eliminating the influences of the noise and the outliers is achieved. Inseparable areas exist on the fuzzy support vector machine in multi-class classification problems, namely, regarding to trained classification functions, classification cannot be carried out on data to be classified. In order to prevent the inseparable areas from being generated, a fuzzy membership degree function is introduced, and the problem of the inseparable areas is eliminated to a large extent. In addition, correction is carried out through fuzzy support, and consistency of classification results of all classifiers is further guaranteed.

Description

technical field [0001] The invention relates to a classification method, in particular to a multi-classification method based on a fuzzy support vector machine. Background technique [0002] As early as the 1970s, a group of scholars headed by V.N.Vapnik began to study the theory of machine learning under the condition of limited samples. It was not until the mid-1990s that the theory of machine learning under limited samples gradually developed and matured, thus Formed a relatively complete theoretical system - Statistical Learning Theory (Statistical Learning Theory). At the same time, some popular methods in the field of machine learning encountered some problems, such as in the neural network, the determination of the network model structure, the "over-learning" problem, and the local minimum point problem, etc., which to a certain extent This provides an opportunity for statistical learning theory to gain attention in the field of machine learning. Around 1995, Vapnik...

AI Technical Summary

Problems solved by technology

Solve the problem that there is an inseparable area in the multi-class classification problem, that is, for the trained classification function, it may not be possible to classify a data to be divided

Images