Table 1.

Features of classifiers.

Model and extraction methods		Descriptions
Support vector machine
	Wavelet transform 5/3, 9/7, and Daubechies	The maximum, minimum, mean, and variance using each wavelet transform. The number of features extracted by the three wavelet transforms is 12.
	Peak-segment features	Local maximums of RR interval widths/R-wave peak amplitudes in different scales Local minimums of RR interval widths/R-wave peak amplitudes in different scales Local means of RR interval widths/R-wave peak amplitudes in different scales Local variances of RR interval widths in different scales The number of local maximums between two R-wave peaks The rate of the case where the P peak does not exist Local mean of PR-segment lengths Local mean of QT-segment lengths Local mean of ST-segment lengths Local mean of P-wave widths Local mean of T-wave widths Local mean of QRS-complex width Local mean of P-wave amplitudes Local mean of T-wave amplitudes
Rule based
	Amplitude and time analysis	The amplitude of the R-wave peak The amplitude of the S peak The amplitude ratio of the R-wave peak and the maximal amplitude of the S peak and the Q peak The distance between the Q and S peaks in a QRS complex The distance between the R and S peaks in a QRS complex The distance between the Q- and R-wave peaks in a QRS complex The ratio of the current RR interval to the local average RR interval