From: EMG-based facial gesture recognition through versatile elliptic basis function neural network
Feature | Equation | Description |
---|---|---|
MAV |
| It adds the absolute value of all the values in a segment divided by the length of the segment. |
MAVS |
| It estimates the difference between the mean absolute values of the adjacent segments k + 1 and k. |
RMS |
| It is modeled as amplitude modulated Gaussian random process whose RMS is related to the constant force and non-fatiguing contraction. |
VAR |
| It is a measure of how far the numbers in each segment lie from the mean. |
WL |
| It is the cumulative length of the waveform over the segment. The resultant values indicate a measure of waveform amplitude, frequency and duration. |
IEMG |
| It calculates the summation of the absolute values of EMG signals (Signal Power estimator). |
SSC | and | 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 |
| It represents the EMG potential from any shift in values of the mean. |
SSI |
| 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. |