A dual ensemble classifier used to recognise contaminated multi-channel EMG and MMG signals in the control of upper limb bioprosthesis

Pawel Trajdos, Marek Kurzynski
Proceedings of The Workshop on Classifier Learning from Difficult Data, PMLR 263:1-8, 2024.

Abstract

Myopotential pattern recognition to decode the intent of the user is the most advanced approach to controlling a powered bioprosthesis. Unfortunately, many factors make this a difficult problem and achieving acceptable recognition quality in real-word conditions is a serious challenge. The aim of the paper is to develop a recognition system that will mitigate factors related to multimodality and multichannel recording of biosignals and their high susceptibility to contamination. The proposed method involves the use of two co-operating multiclassifier systems. The first system is composed of one-class classifiers related to individual electromyographic (EMG) and mechanomyographic (MMG) biosignal recording channels, and its task is to recognise contaminated channels. The role of the second system is to recognise the class of movement resulting from the patient’s intention. The ensemble system consists of base classifiers using the representation (extracted features) of biosignals from different channels. The system uses a dynamic selection mechanism, eliminating those base classifiers that are associated with biosignal channels that are recognised by the one-class ensemble system as being contaminated. Experimental studies were conducted using signals from an able-bodied person with simulation of amputation. The results obtained confirm the hypothesis that the use of a dual ensemble classifier leads to improved classification quality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v263-trajdos24a, title = {A dual ensemble classifier used to recognise contaminated multi-channel EMG and MMG signals in the control of upper limb bioprosthesis}, author = {Trajdos, Pawel and Kurzynski, Marek}, booktitle = {Proceedings of The Workshop on Classifier Learning from Difficult Data}, pages = {1--8}, year = {2024}, editor = {Zyblewski, Pawel and Grana, Manuel and Pawel, Ksieniewicz and Minku, Leandro}, volume = {263}, series = {Proceedings of Machine Learning Research}, month = {19--20 Oct}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v263/main/assets/trajdos24a/trajdos24a.pdf}, url = {https://proceedings.mlr.press/v263/trajdos24a.html}, abstract = {Myopotential pattern recognition to decode the intent of the user is the most advanced approach to controlling a powered bioprosthesis. Unfortunately, many factors make this a difficult problem and achieving acceptable recognition quality in real-word conditions is a serious challenge. The aim of the paper is to develop a recognition system that will mitigate factors related to multimodality and multichannel recording of biosignals and their high susceptibility to contamination. The proposed method involves the use of two co-operating multiclassifier systems. The first system is composed of one-class classifiers related to individual electromyographic (EMG) and mechanomyographic (MMG) biosignal recording channels, and its task is to recognise contaminated channels. The role of the second system is to recognise the class of movement resulting from the patient’s intention. The ensemble system consists of base classifiers using the representation (extracted features) of biosignals from different channels. The system uses a dynamic selection mechanism, eliminating those base classifiers that are associated with biosignal channels that are recognised by the one-class ensemble system as being contaminated. Experimental studies were conducted using signals from an able-bodied person with simulation of amputation. The results obtained confirm the hypothesis that the use of a dual ensemble classifier leads to improved classification quality.} }
Endnote
%0 Conference Paper %T A dual ensemble classifier used to recognise contaminated multi-channel EMG and MMG signals in the control of upper limb bioprosthesis %A Pawel Trajdos %A Marek Kurzynski %B Proceedings of The Workshop on Classifier Learning from Difficult Data %C Proceedings of Machine Learning Research %D 2024 %E Pawel Zyblewski %E Manuel Grana %E Ksieniewicz Pawel %E Leandro Minku %F pmlr-v263-trajdos24a %I PMLR %P 1--8 %U https://proceedings.mlr.press/v263/trajdos24a.html %V 263 %X Myopotential pattern recognition to decode the intent of the user is the most advanced approach to controlling a powered bioprosthesis. Unfortunately, many factors make this a difficult problem and achieving acceptable recognition quality in real-word conditions is a serious challenge. The aim of the paper is to develop a recognition system that will mitigate factors related to multimodality and multichannel recording of biosignals and their high susceptibility to contamination. The proposed method involves the use of two co-operating multiclassifier systems. The first system is composed of one-class classifiers related to individual electromyographic (EMG) and mechanomyographic (MMG) biosignal recording channels, and its task is to recognise contaminated channels. The role of the second system is to recognise the class of movement resulting from the patient’s intention. The ensemble system consists of base classifiers using the representation (extracted features) of biosignals from different channels. The system uses a dynamic selection mechanism, eliminating those base classifiers that are associated with biosignal channels that are recognised by the one-class ensemble system as being contaminated. Experimental studies were conducted using signals from an able-bodied person with simulation of amputation. The results obtained confirm the hypothesis that the use of a dual ensemble classifier leads to improved classification quality.
APA
Trajdos, P. & Kurzynski, M.. (2024). A dual ensemble classifier used to recognise contaminated multi-channel EMG and MMG signals in the control of upper limb bioprosthesis. Proceedings of The Workshop on Classifier Learning from Difficult Data, in Proceedings of Machine Learning Research 263:1-8 Available from https://proceedings.mlr.press/v263/trajdos24a.html.

Related Material