Research on Multiple Sub-Hyper-Sphere Support Vector Machine

This paper put forward a multiple sub-hyper-sphere support vector machine.New algorithm computed hyper-spheres for all classes first,and then obtained position relationships between hyper-spheres and saved them in the corresponding data set.For hyper-spheres in the intersection set,it computed overlap coefficient based on map of key value index,and partitioned the hyper-sphere with maximized difference degree into sub-hyper-spheres.Number of sub-hyper-spheres is based on the overlap coefficient.With experimental results compared to other hyper-sphere support vector machines,new proposed algorithm improves the performance of the resulting classifier and decreases computation complexity for decision.