Skip to main content

Table 2 Feature definition

From: sEMG feature evaluation for identification of elbow angle resolution in graded arm movement

Features

Equations

Mean Absolute Value

MA V i = 1 N k = 1 N x k

Root Mean Square

RM S i = 1 N k = 1 N x k 2

Waveform Length

W L i = k = 1 N x k x k 1

Willison Amplitude

WAM P i = k = 1 N 1 f x k x k + 1

f x = 1 x > x t h 0 otherwise

Zero Crossings

f k ={ 1 x k x k + 1 < 0 0 otherwise }

Z C i = k = 1 N 1 f k

Autoregressive Model (AR)

y n = k = 1 p a k x n k + w n

In this study, p = 6.

Power Spectral Density

PSD f = 1 N k = 0 N x k e j 2 π f

Power Spectral Density Averages

PSD_A v i = 1 f k f k 1 f k f k 1 P S D f df

Power Spectral Density Moments

PSD_M o i y = 0 w f y PSD f df

In this study, w = 250 Hz and y = 1,2,3