Papers by Keyword: Fuzzy Support Vector Machine (FSVM)

Abstract: Concerning the defect of fuzzy membership as a function of distance between the point and its class center in feature space for some current Fuzzy Support Vector Machines (FSVM), a new FSVM based on entropy and Genetic Algorithm (GA) named EGFSVM was proposed in this paper. Making use of evaluation of entropy and intelligence of GA, EGFSVM enhances the classification capability and makes clustering center more suitable and membership more accurate. Experimental results show EGFSVM has better precision and classification performance, especially to multi-class and large scale data.

Abstract: The basic idea of this paper is multiple keywords can be assigned to image through the method of fixed region segmentation. We divide a single image into the 4-level regions. For each of them, the combined feature is extracted and inputted into the trained Fuzzy SVMs to classify, which has been proved better than conventional SVMs in the generalization ability. The values of classification in each category are calculated. Based on these values, the keywords are assigned.

Abstract: By combining fuzzy support vector machine with rough set, we propose a rough margin based fuzzy support vector machine (RFSVM). It inherits the characteristic of the FSVM method and considers position of training samples of the rough margin in order to reduce overfitting due to noises or outliers. The new proposed algorithm finds the optimal separating hyperplane that maximizes the rough margin containing lower margin and upper margin. Meanwhile, the points lied on the lower margin have larger penalty than these in the boundary of the rough margin. Experiments on several benchmark datasets show that the RFSVM algorithm is effective and feasible compared with the existing support vector machines.