As a new version of support vector machine(SVM),twin support vector machine(TWSVM) was proposed recently. TWSVM is not only faster than a conventional SVM, but shows good generalization for pattern classification. But the different effects of the different training samples on the classification hyperplanes are ignored in TWSVM, and the limitation is existed for some actual applications. Therefore, a twin support vector machine based on fuzzy membership was presented. A fuzzy membership function based on distance was designed, and TWSVM was modified by applying the fuzzy membership to every training sample, finally two optimal nonparallel hyperplanes were builded to achieve classification. The experiment results indicate that the classification performance of the algorithm is more superiorer than a traditional TWSVM.

Twin support vector machine ,  Fuzzy membership ,  , Pattern classification