Evaluation of EMG Signal Time Domain Features for Hand Gesture Distinction

This paper illustrates a collection of wide used time domain features of EMG signal, investigates their ability to distinguish hand gestures from one subject performing six different gestures with two sensor channels. The extracted set of features is presented as a fusion between the two sensor channels and a visual evaluation of their usability for performed hand gesture distinction is described. Results have shown that extracting Integrated EMG, Variance, Mean absolute values type one and type two, Average amplitude change and zero crossing time domain features are more significant for hand gesture recognition based on surface EMG signal analysis then extracting temporal moments coefficients, Wilson amplitude and myopulse percentage rate. However, the necessity of a feature selection step to eliminate information redundancy before hand gesture classification is concluded.

[1]  Pornchai Phukpattaranont,et al.  Feature reduction and selection for EMG signal classification , 2012, Expert Syst. Appl..

[2]  Sabri Koçer,et al.  Classifying neuromuscular diseases using artificial neural networks with applied Autoregressive and Cepstral analysis , 2016, Neural Computing and Applications.

[3]  Feng Duan,et al.  Comparison of sEMG-based feature extraction and hand motion classification methods , 2015, 2015 11th International Conference on Natural Computation (ICNC).

[4]  Roliana Ibrahim,et al.  Feature Reduction Using Standard Deviation with Different Subsets Selection in Sentiment Analysis , 2014, ACIIDS.

[5]  Liqiong Tang,et al.  Surface EMG Signal Amplification and Filtering , 2013 .

[6]  Wahyu Caesarendra,et al.  A Review of Feature Extraction Methods in Vibration-Based Condition Monitoring and Its Application for Degradation Trend Estimation of Low-Speed Slew Bearing , 2017 .

[7]  Sridhar Krishnan,et al.  Trends in biomedical signal feature extraction , 2018, Biomed. Signal Process. Control..

[8]  Han-Pang Huang,et al.  Automatic EMG feature evaluation for controlling a prosthetic hand using supervised feature mining method: an intelligent approach , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[9]  Anthony Tzes,et al.  Improving EMG based classification of basic hand movements using EMD , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[10]  Mary Walowe Mwadulo,et al.  A Review on Feature Selection Methods For Classification Tasks , 2016 .

[11]  Jianhua Wang,et al.  A portable artificial robotic hand controlled by EMG signal using ANN classifier , 2015, 2015 IEEE International Conference on Information and Automation.

[12]  Tomasz Grzejszczak,et al.  Applications of hand feature points detection and localization algorithms , 2016 .

[13]  Tanu Sharma,et al.  A novel feature extraction for robust EMG pattern recognition , 2016, Journal of medical engineering & technology.