Jx-EMGT : Electromyography ( EMG ) Feature Extraction Toolbox

"Toward Talent Scientist: Sharing and Learning Together" --- Jingwei Too

Introduction

• This toolbox offers 40 types of EMG features
• The A_Main file demos how the feature extraction methods can be applied using generated sample signal.

Input

• X : signal ( 1 x samples )
• opts : parameter settings ( some methods have parameters: refer here )

Output

• feat : feature vector ( you may use other name like f1 or etc. )

Usage

The main function jfemg is adopted to perform feature extraction. You may switch the method by changing the 'mav' to other abbreviations

• If you wish to extract mean absolute value ( MAV ) then you may write

feat = jfemg('mav', X);

• If you want to extract enhanced wavelenght ( EWL ) then you may write

feat = jfemg('ewl', X);

Example 1 : Extract 5 normal features ( without parameter )

% Generate a sample random signal X
fs = 1000;            % Sampling frequency 
Ts = 1 / fs;          % Period
t  = 0 : Ts : 0.25; 
X  = 0.01 * (cos(2 * pi * fs * t) + randn(1, length(t)));

% Plot sample signal
plot(t,X);  grid on
xlabel('Number of samples');
ylabel('Amplitude');

% Enhanced Mean Absolute Value
f1 = jfemg('emav', X); 
% Average Amplitude Change
f2 = jfemg('aac', X); 
% Waveform Length
f3 = jfemg('wl', X); 
% Maximum Fractal Length 
f4 = jfemg('mfl', X); 
% Root Mean Square
f5 = jfemg('rms', X); 

% Feature vector
feat = [f1, f2, f3, f4, f5];

% Display features
disp(feat)

Example 2 : Extract 3 features with parameter

% Generate a sample random signal X
fs = 1000;            % Sampling frequency 
Ts = 1 / fs;          % Period
t  = 0 : Ts : 0.25; 
X  = 0.01 * (cos(2 * pi * fs * t) + randn(1, length(t)));

% Zeros Crossing
opts.thres = 0.01;
f1 = jfemg('zc', X, opts); 
% Slope Sign Change
opts.thres = 0.01;
f2 = jfemg('ssc', X, opts);
% Temporal Moment
opts.order = 3;
f3 = jfemg('tm', X, opts);

% Feature vector
feat = [f1, f2, f3];

% Display features
disp(feat)

List of available feature extraction methods

• Some methods contain parameter to be adjusted. If you do not set the parameter then the feature will be extracted using default setting
• For convenience, you may extract the feature with parameter using default setting as following. That is, you don't have to set the opts

feat = jfemg('zc', X);

• You can use opts to set the parameter
  • thres : threshold
  • order : the number of orders

Cite As

@article{too2019classification,
  title={Classification of hand movements based on discrete wavelet transform and enhanced feature extraction},
  author={Too, Jingwei and Abdullah, Abdul Rahim and Saad, Norhashimah Mohd},
  journal={International Journal of Advanced Computer Science and Applications},
  volume={10},
  number={6},
  pages={83--89},
  year={2019}
}


@article{too2019emg,
  title={EMG feature selection and classification using a Pbest-guide binary particle swarm optimization},
  author={Too, Jingwei and Abdullah, Abdul Rahim and Mohd Saad, Norhashimah and Tee, Weihown},
  journal={Computation},
  volume={7},
  number={1},
  pages={12},
  year={2019},
  publisher={Multidisciplinary Digital Publishing Institute}
}