Table 2. Data processing.

Order	Processing	Additional Details
	preprocessing
1	20-Hz Butterworth high-pass filter
2	Adaptive non-linear noise cancellation
3	Segmentation and feature extraction: from 1000-Hz signals to 1 Hz signals with root mean square (RMS) and waveform length (WL) transformation	$RMS=\sqrt{\frac{1}{N}{\sum }_{i=1}^N{\left(x_i\right)}^2}WL={\sum }_{i=1}^{N-1}|x_{i+1}-x_i|$
	preprocessing
4	Hampel filtering	The Hampel filter (K = 3, t = 3) [34], where K is the half-window and the outlier threshold is t standard deviations
5	Z-score standardization on test level	$z=\frac{(x-\mu )}{\sigma }$, where μ is the mean, and σ is the standard deviation