The Research on the Algorithm of Approximately Linearly Dividable Support Vector Classification Machine Based on Fuzzy Theory

Data mining is a new filed in data processing research. Support vector machine (SVM) is a useful method adopted in data mining. However, when the training set of the SVM contains information of uncertainty, the SVM can do nothing about it. In order to solve the problem presented above, this article discusses an algorithm of approximately linearly dividable support vector classification machine based on fuzzy theory. With the restriction of the confidence lambda(0<lambdales), we can using the classification method in fuzzy theory to solve the problem of constraining programming of uncertain chance. By establishing a chain like this: constraining programming of uncertain chance rarr clearly equivalent programming rarr programming of antithesis, the universal algorithm of linearly dividable support vector classification machine based on fuzzy theory can be deduced.