Facing High EEG Signals Variability during Classification Using Fractal Dimension and Different Cutoff Frequencies

Table 1

Average accuracy for Condition A using the classical filter configuration (1–100 Hz).

Subject	Higuchi	Katz	AR
A1	0.65 ± 0.04	0.58 ± 0.03	0.61 ± 0.04
A2	0.49 ± 0.05	0.51 ± 0.02	0.52 ± 0.03
A3	0.78 ± 0.03	0.51 ± 0.05	0.65 ± 0.04
A4	0.45 ± 0.04	0.47 ± 0.03	0.48 ± 0.04
A5	0.54 ± 0.05	0.51 ± 0.03	0.51 ± 0.03
A6	0.54 ± 0.04	0.55 ± 0.03	0.53 ± 0.05
A7	0.53 ± 0.04	0.55 ± 0.04	0.55 ± 0.04
A8	0.85 ± 0.03	0.66 ± 0.04	0.78 ± 0.04
A9	0.65 ± 0.05	0.78 ± 0.07	0.69 ± 0.06
Average	0.61 ± 0.04	0.57 ± 0.04	0.59 ± 0.04

Accuracies that are significantly different compared with the best result. Values in bold indicate the best average accuracy achieved from the different feature extraction techniques.