Towards robust HD EMG pattern recognition: Reducing electrode displacement effect using structural similarity

Abstract

Even small changes of electrode recording sites after training a classifier heavily influence robustness and usability of traditional pattern recognition-based myoelectric control schemes. This effect occurs during donning and doffing of the prosthesis or when changing the arm position and generally leads to a significant decrease of classification accuracy. On the other hand, image representations taken from high density electromyographic (EMG) signals offer high spatial resolution and only seem to change slightly during electrode shift, preserving most structural information. In this paper, we present a simple one-against-one nearest neighbor classifier based on the Structural Similarity Index (SSIM). SSIM quantifies visual similarity of two images based on decomposition into three components: luminance, contrast and structure. Our experimental results indicate that an SSIM-based classifier can outperform an LDA-based classifier using structural information taken from high density EMG signals during simulated electrode shift.

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

“…The most commonly reported limb position experimental protocol in the literature is one that uses static limb positions [21,22,94,[113][114][115][116]119,[121][122][123][126][127][128][129][130][131][132][133][134][135][136][137][138]. Among the articles surveyed, these make up 50% of all experiments.…”

Causes of Performance Degradation in Non-invasive Electromyographic Pattern Recognition in Upper Limb Prostheses

“…The most common experimental procedure consists of training the classifiers on features extracted from the original signals and testing the classifier on features from the shifted signals. The maximum electrode displacement distance that is likely to occur in the normal everyday use of the prosthetic hand is noted in different studies as 1 cm (Hargrove et al, 2008 ; Boschmann and Platzner, 2012 , 2014 ; Muceli et al, 2014 ; Pan et al, 2015 ; Stango et al, 2015 ).…”

“…The detection of electrodes shifts from their original positions does not follow a physiological pattern that can be described by ME signal characteristics as in the case of muscle fatigue. Most studies rely on indirectly detecting the electrode shift by monitoring either the classification accuracy or the classification error (Hargrove et al, 2008 ; Tkach et al, 2010 ; Boschmann and Platzner, 2012 , 2014 ; Young et al, 2012 ; Pan et al, 2015 ; Stango et al, 2015 ). A decrease in the former or increase in the latter is associated with some disturbance in the EMG signals, that is not necessarily uniquely associated with electrode shift and could be the result of other disturbances (see following sections).…”

“…Boschmann and Platzner ( 2014 ) utilized high density EMG signals and approached the EMG classification problem in a novel way. They translated the EMG recordings in images and used the luminance, contrast and structure of these images, in order to calculate a Structural Similarity Index (SSIM).…”

A Study on the Effects of Electrode Placement on the Performance of Emg Classification of Hand and Wrist Movements

“…However, increasing the number of electrodes also increases the processing involved, and it has already been shown that the increase in the performance of an EMG classifier isn't significant after four electrodes [4]. Other way to tackle the problem would be using more robust classifiers that can withstand changes in the signal [1 and 5], or even training the classifier with the electrodes slightly shifted [2]. But none of these approaches were consolidated as satisfactory.…”