A Hybrid Approach for MS Diagnosis Through Nonlinear EEG Descriptors and Metaheuristic Optimized Classification Learning

Table 1

Assessments of accuracy in different data dividing situations and with/without feature selection strategy and change in the type of features. The bold values are the best measures achieved.

Data dividing	Type of features	Without feature selection			With feature selection
		Best value	Mean value	Worst value	Best value	Mean value	Worst value
10-fold (1)	Statistical	0.93 ± (0.05)	0.90 ± (0.06)	0.88 ± (0.09)	0.96 ± (0.03)	0.94 ± (0.05)	0.93 ± (0.06)
	Fractals	0.91 ± (0.05)	0.90 ± (0.06)	0.88 ± (0.09)	0.97 ± (0.03)	0.94 ± (0.05)	0.93 ± (0.05)
	Hybrid	0.93 ± (0.04)	0.91 ± (0.05)	0.89 ± (0.08)	0.98 ± (0.02)	0.95 ± (0.03)	0.94 ± (0.05)
10-fold (2)	Statistical	0.93 ± (0.04)	0.92 ± (0.07)	0.88 ± (0.08)	0.96 ± (0.02)	0.95 ± (0.04)	0.94 ± (0.05)
	Fractals	0.93 ± (0.04)	0.91 ± (0.07)	0.88 ± (0.09)	0.98 ± (0.02)	0.95 ± (0.04)	0.94 ± (0.05)
	Hybrid	0.93 ± (0.05)	0.91 ± (0.06)	0.89 ± (0.08)	0.98 ± (0.01)	0.96 ± (0.02)	0.94 ± (0.04)
10-fold (3)	Statistical	0.92 ± (0.05)	0.90 ± (0.05)	0.87 ± (0.08)	0.95 ± (0.02)	0.94 ± (0.05)	0.93 ± (0.05)
	Fractals	0.92 ± (0.05)	0.91 ± (0.05)	0.88 ± (0.09)	0.97 ± (0.02)	0.95 ± (0.04)	0.94 ± (0.04)
	Hybrid	0.92 ± (0.05)	0.91 ± (0.04)	0.88 ± (0.08)	0.98 ± (0.01)	0.97 ± (0.02)	0.94 ± (0.05)
10-fold (4)	Statistical	0.93 ± (0.06)	0.91 ± (0.06)	0.88 ± (0.08)	0.96 ± (0.03)	0.95 ± (0.05)	0.94 ± (0.03)
	Fractals	0.92 ± (0.04)	0.90 ± (0.06)	0.89 ± (0.08)	0.97 ± (0.03)	0.95 ± (0.05)	0.93 ± (0.05)
	Hybrid	0.93 ± (0.05)	0.92 ± (0.06)	0.89 ± (0.07)	0.98 ± (0.02)	0.97 ± (0.03)	0.94 ± (0.04)
10-fold (5)	Statistical	0.92 ± (0.04)	0.91 ± (0.07)	0.87 ± (0.08)	0.96 ± (0.03)	0.94 ± (0.05)	0.93 ± (0.05)
	Fractals	0.93 ± (0.04)	0.90 ± (0.08)	0.88 ± (0.07)	0.97 ± (0.03)	0.96 ± (0.04)	0.94 ± (0.05)
	Hybrid	0.93 ± (0.03)	0.92 ± (0.07)	0.88 ± (0.07)	0.98 ± (0.02)	0.97 ± (0.02)	0.95 ± (0.03)