Skip to main content

Table 2 Time-Domain features considered in this study

From: EMG-based facial gesture recognition through versatile elliptic basis function neural network

Feature

Equation

Description

MAV

MA V k = 1 N ∑ i = 1 N x i

It adds the absolute value of all the values in a segment divided by the length of the segment.

MAVS

MAV S k = MA V k + 1 − MA V k

It estimates the difference between the mean absolute values of the adjacent segments k + 1 and k.

RMS

RM S k = 1 N ∑ i = 1 N x i 2

It is modeled as amplitude modulated Gaussian random process whose RMS is related to the constant force and non-fatiguing contraction.

VAR

VA R k = 1 N ∑ i = 1 N x i − x ¯ 2

It is a measure of how far the numbers in each segment lie from the mean.

WL

W L k = ∑ i = 1 N − 1 x i + 1 − x i

It is the cumulative length of the waveform over the segment. The resultant values indicate a measure of waveform amplitude, frequency and duration.

IEMG

IEM G k = ∑ i = 1 N x i

It calculates the summation of the absolute values of EMG signals (Signal Power estimator).

SSC

x i > x i − 1 & x i > x i + 1 and x i − x i + 1 ≥ ϵ

Given three consecutive samples xi-1, xi and xi+1, the slope sign change is incremented if the equation is satisfied. A Threshold ϵ = 0.02

MV

x ¯ = 1 N ∑ i = 1 N x i

It represents the EMG potential from any shift in values of the mean.

SSI

SS I k = ∑ i = 1 N x i 2

It determines the energy of EMGs in each segment.

MPV

x k = max |x i |

It is used to find the maximum absolute peak value of EMGs.