An Improved Fuzzy Support Vector Machine

Most fuzzy support machines (FSVM) canpsilat effectively distinguish between valid samples and outliers or noises. A fuzzy support vector machine based on the fuzzy connectedness is improved in this paper. The fuzzy connectedness proposed for the measurement of the inaccuracy of samples effectively distinguishes between valid samples and outliers or noises. In the FSVM method, a membership function is defined according to not only the relation between a sample and its class center, but also those among samples, which is described by the fuzzy connectedness among samples. Experimental results show that this improved method is more robust than the traditional SVM, and other FSVM methods.