An MR Brain Images Classifier System via Particle Swarm Optimization and Kernel Support Vector Machine

Table 2

Methods of comparison between BP-NN, RBF-NN, and PSO-KSVM.

Method	Confusion matrix	Success Cases	Sensitivity	Specificity	Classification accuracy
BP-NN	37411; 5114	388	88.0%	56%	86.22%
RBF-NN	3937; 3218	411	92.47%	72%	91.33%
PSO-KSVM	4172; 823	440	98.12%	92%	97.78%