Classification complexity in myoelectric pattern recognition
Abstract Background Limb prosthetics, exoskeletons, and neurorehabilitation devices can be intuitively controlled using myoelectric pattern recognition (MPR) to decode the subject’s intended movement. In conventional MPR, descriptive electromyography (EMG) features representing the intended movement...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2017-07-01
|
Series: | Journal of NeuroEngineering and Rehabilitation |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12984-017-0283-5 |
id |
doaj-345410f487b340e59573c01ba4716b0b |
---|---|
record_format |
Article |
spelling |
doaj-345410f487b340e59573c01ba4716b0b2020-11-24T20:59:27ZengBMCJournal of NeuroEngineering and Rehabilitation1743-00032017-07-0114111810.1186/s12984-017-0283-5Classification complexity in myoelectric pattern recognitionNiclas Nilsson0Bo Håkansson1Max Ortiz-Catalan2Department of Electrical Engineering, Chalmers University of TechnologyDepartment of Electrical Engineering, Chalmers University of TechnologyDepartment of Electrical Engineering, Chalmers University of TechnologyAbstract Background Limb prosthetics, exoskeletons, and neurorehabilitation devices can be intuitively controlled using myoelectric pattern recognition (MPR) to decode the subject’s intended movement. In conventional MPR, descriptive electromyography (EMG) features representing the intended movement are fed into a classification algorithm. The separability of the different movements in the feature space significantly affects the classification complexity. Classification complexity estimating algorithms (CCEAs) were studied in this work in order to improve feature selection, predict MPR performance, and inform on faulty data acquisition. Methods CCEAs such as nearest neighbor separability (NNS), purity, repeatability index (RI), and separability index (SI) were evaluated based on their correlation with classification accuracy, as well as on their suitability to produce highly performing EMG feature sets. SI was evaluated using Mahalanobis distance, Bhattacharyya distance, Hellinger distance, Kullback–Leibler divergence, and a modified version of Mahalanobis distance. Three commonly used classifiers in MPR were used to compute classification accuracy (linear discriminant analysis (LDA), multi-layer perceptron (MLP), and support vector machine (SVM)). The algorithms and analytic graphical user interfaces produced in this work are freely available in BioPatRec. Results NNS and SI were found to be highly correlated with classification accuracy (correlations up to 0.98 for both algorithms) and capable of yielding highly descriptive feature sets. Additionally, the experiments revealed how the level of correlation between the inputs of the classifiers influences classification accuracy, and emphasizes the classifiers’ sensitivity to such redundancy. Conclusions This study deepens the understanding of the classification complexity in prediction of motor volition based on myoelectric information. It also provides researchers with tools to analyze myoelectric recordings in order to improve classification performance.http://link.springer.com/article/10.1186/s12984-017-0283-5Classification complexityMyoelectric pattern recognitionElectromyographyProsthesis control |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Niclas Nilsson Bo Håkansson Max Ortiz-Catalan |
spellingShingle |
Niclas Nilsson Bo Håkansson Max Ortiz-Catalan Classification complexity in myoelectric pattern recognition Journal of NeuroEngineering and Rehabilitation Classification complexity Myoelectric pattern recognition Electromyography Prosthesis control |
author_facet |
Niclas Nilsson Bo Håkansson Max Ortiz-Catalan |
author_sort |
Niclas Nilsson |
title |
Classification complexity in myoelectric pattern recognition |
title_short |
Classification complexity in myoelectric pattern recognition |
title_full |
Classification complexity in myoelectric pattern recognition |
title_fullStr |
Classification complexity in myoelectric pattern recognition |
title_full_unstemmed |
Classification complexity in myoelectric pattern recognition |
title_sort |
classification complexity in myoelectric pattern recognition |
publisher |
BMC |
series |
Journal of NeuroEngineering and Rehabilitation |
issn |
1743-0003 |
publishDate |
2017-07-01 |
description |
Abstract Background Limb prosthetics, exoskeletons, and neurorehabilitation devices can be intuitively controlled using myoelectric pattern recognition (MPR) to decode the subject’s intended movement. In conventional MPR, descriptive electromyography (EMG) features representing the intended movement are fed into a classification algorithm. The separability of the different movements in the feature space significantly affects the classification complexity. Classification complexity estimating algorithms (CCEAs) were studied in this work in order to improve feature selection, predict MPR performance, and inform on faulty data acquisition. Methods CCEAs such as nearest neighbor separability (NNS), purity, repeatability index (RI), and separability index (SI) were evaluated based on their correlation with classification accuracy, as well as on their suitability to produce highly performing EMG feature sets. SI was evaluated using Mahalanobis distance, Bhattacharyya distance, Hellinger distance, Kullback–Leibler divergence, and a modified version of Mahalanobis distance. Three commonly used classifiers in MPR were used to compute classification accuracy (linear discriminant analysis (LDA), multi-layer perceptron (MLP), and support vector machine (SVM)). The algorithms and analytic graphical user interfaces produced in this work are freely available in BioPatRec. Results NNS and SI were found to be highly correlated with classification accuracy (correlations up to 0.98 for both algorithms) and capable of yielding highly descriptive feature sets. Additionally, the experiments revealed how the level of correlation between the inputs of the classifiers influences classification accuracy, and emphasizes the classifiers’ sensitivity to such redundancy. Conclusions This study deepens the understanding of the classification complexity in prediction of motor volition based on myoelectric information. It also provides researchers with tools to analyze myoelectric recordings in order to improve classification performance. |
topic |
Classification complexity Myoelectric pattern recognition Electromyography Prosthesis control |
url |
http://link.springer.com/article/10.1186/s12984-017-0283-5 |
work_keys_str_mv |
AT niclasnilsson classificationcomplexityinmyoelectricpatternrecognition AT bohakansson classificationcomplexityinmyoelectricpatternrecognition AT maxortizcatalan classificationcomplexityinmyoelectricpatternrecognition |
_version_ |
1716782328988041216 |