Skip to main content

Table 1 Non-exhaustive compilation of myoelectric signal features employed in pattern recognition for prosthetic control

From: BioPatRec: A modular research platform for the control of artificial limbs based on pattern recognition algorithms

  Publication references
  [6, 14, 1725] [26] [27] [7] [5, 28] [29] [30] [31] [32] [33] [34, 35] [36] [37] [38] BioPatRec*
Mean absolute value x x x x x x x x x x x     x
Zero crossing x x x x x x x         x
Slope sign changes x x   x x x x         x
Waveform length x x x x x x x x   x      x
Mean abs. value slope   x x             x
Root-mean square     x x x   x x    x    x
Variance     x     x        x
William amplitude     x            
Wavelet transf.    x             
Wavelet packet transf.    x             
Fourier transf.    x             x
Autoregression coeff.      x   x         
Integral abs. value       x          
Sample skewness       x          
Fractal dimension         x        x
Max. fractal length         x        x
Quadratic polynomials              x   
Rough Entropy               x x
  1. * Non-exhaustive list of features included in the “ETT” release. See the online project for all features [15].