Entropy-Based Pattern Learning Based on Singular Spectrum Analysis Components for Assessment of Physiological Signals

Table 10

Comparison results of the identification accuracies for entropy-based pattern learning to identify specific biosignal patterns from EEG, EMG, and RR-interval signals with and without SSA components representation. For pattern learning task #1, #2, and #3, FuzzyEn is used as the entropy features for experimental analysis, the SVM is used as pattern classifier and LOOCV is used as the cross-validation strategy. DimIF, dimension of input features.

Pattern learning task	Main method	DimIF	Accuracy
#1	FuzzyEn extracting from the SSA components of EEG signals	8	96.50%
	FuzzyEn extracting from EEG signals	1	71.50%
#2	FuzzyEn extracting from the SSA components of EMG signals	20	87.50%
	FuzzyEn extracting from EMG signals	1	80.00%
#3	FuzzyEn extracting from the SSA components of RR-intervals signals	4	83.13%
	FuzzyEn extracting from RR-intervals	1	65.06%