EMG Based Gesture Recognition Using Noise Removal

We propose a feature calibration method for the electromyography (EMG) based gesture recognition to be robust to noise. The proposed method is to subtract the feature of noise calculated in resting period from the signal feature. For the performance evaluation, we compare the recognition accuracy of the feature calibration applied with that of the feature calibration not applied. As noise level increases, the result of the proposed feature calibration method applied shows clear improvement in accuracy. When SNR is 0dB, the recognition result of the proposed method applied shows about 20% improvement in average accuracy compared to that of the proposed method not applied.

[1]  Arto Visala,et al.  urrent state of digital signal processing in myoelectric interfaces and elated applications , 2015 .

[2]  Beth Jelfs,et al.  Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network , 2017, Front. Neurosci..

[3]  Pornchai Phukpattaranont,et al.  WAVELET-BASED DENOISING ALGORITHM FOR ROBUST EMG PATTERN RECOGNITION , 2011 .

[4]  Xun Chen,et al.  Pattern recognition of number gestures based on a wireless surface EMG system , 2013, Biomed. Signal Process. Control..

[5]  Qiang Li,et al.  A Hand Gesture Recognition Framework and Wearable Gesture-Based Interaction Prototype for Mobile Devices , 2014, IEEE Transactions on Human-Machine Systems.

[6]  Hyun-Chool Shin,et al.  Electromyogram-based hand gesture recognition robust to various arm postures , 2018, Int. J. Distributed Sens. Networks.

[7]  Xiaowei Yang,et al.  A Kernel Fuzzy c-Means Clustering-Based Fuzzy Support Vector Machine Algorithm for Classification Problems With Outliers or Noises , 2011, IEEE Transactions on Fuzzy Systems.

[8]  K. Englehart,et al.  Classification of the myoelectric signal using time-frequency based representations. , 1999, Medical engineering & physics.

[9]  Ganesh R. Naik,et al.  Nonnegative Matrix Factorization for the Identification of EMG Finger Movements: Evaluation Using Matrix Analysis , 2015, IEEE Journal of Biomedical and Health Informatics.

[10]  Todd A. Kuiken,et al.  Improving Myoelectric Pattern Recognition Robustness to Electrode Shift by Changing Interelectrode Distance and Electrode Configuration , 2012, IEEE Transactions on Biomedical Engineering.