Brain-Computer Interface for Control of Wheelchair Using Fuzzy Neural Networks

Table 2

Comparison of classification results.

Method	Correctly classified instances	Incorrectly classified instances	Mean absolute error	Root mean squared error
Linear logistic regression model	96%	4%	0.0214	0.1265
SVM (polynomial kernel)	100%	0	0.24	0.3162
SVM (RBF kernel)	74%	26%	0.2568	0.3404
SVM (PUK kernel)	96%	4%	0.2424	0.32
MLP (NN) (5 hidden neurons)	88%	12%	0.0724	0.1586
MLP (NN) (6 hidden neurons)	100%	0	0.048	0.0958
Naïve Bayesian	94%	6%	0.024	0.1549
Random Tree	74%	26%	0.104	0.3225
Random Forest	98%	2%	0.1215	0.179
FNN (6 hidden neurons)	100%	0	1.823	0.257986