Evaluation of Methods for Estimating Fractal Dimension in Motor Imagery-Based Brain Computer Interface

Table 1

Maximum classification accuracies (percentage of correctly classified testing samples) obtained by the combination of fractal dimension estimation methods and classifiers with the two and three electrode configurations (and the parameters (k and k _max) used to obtain these values).

	Classification accuracy (%)
	Katz’s method		Higuchi’s method		R/S method		Renyi’s entropy
	C3, C4	C3, Cz, C4	C3, C4	C3, Cz, C4	C3, C4	C3, Cz, C4	C3, C4	C3, Cz, C4
FKNN	83; (𝑘=9)	85; (𝑘=9)	77; (𝑘=7, 𝑘max=18)	79; (𝑘=5, 𝑘max=18)	71; (𝑘=9)	69; (𝑘=9)	66; (𝑘=9, 𝑞=4)	65; (𝑘=9, 𝑞=5)
SVM	77	79	78; (𝑘max=13)	81; (𝑘max=13)	71	70	59; (𝑞=2)	55; (𝑞=4)
LDA	78	81	78; (𝑘max=13)	79; (𝑘max=13)	71	70	59; (𝑞=3)	57; (𝑞=18)