A fuzzy support vector machine based on geometric model

Fuzzy support vector machine is a learning algorithm used to solve the classification problems based on statistical learning theory and fuzzy properties of training points. To determine the fuzzy membership of the training points, the guard vector method and the circle method are proposed using the fuzzy membership function and the geometrical properties of the distribution of the training points in space. Numerical experiments indicate that the two methods improve the accuracy of classification and takes a shorter training time.