A Self-Representation-Based Fuzzy SVM Model for Predicting Vascular Calcification of Hemodialysis Patients

Table 4

Comparison on existing models via 10-fold crossvalidation (under 3 classes).

Model	Whole ACC (%)	ACC^1 (%)	ACC^2 (%)	ACC^3 (%)
Logistic regression
BP neural network
RBF neural network
TSK-FS
SVM
FSVM-SR (our method)

ACC¹: the accuracy of class 1; ACC²: the accuracy of class 2; ACC³: the accuracy of class 3.