An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition

Over the last few decades, pattern recognition algorithms have shown promising results in the field of upper limb prostheses myoelectric control and are now gradually being incorporated in commercial devices. A widely used approach is based on a classifier which assigns a specific input value to a s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Veronika Spieker, Amartya Ganguly, Sami Haddadin, Cristina Piazza
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	upper-limb prostheses myoelectric control pattern recognition limb effect linear discriminant analysis multi-modal control Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/c599b68f23bf4c2687c4827922ad7763
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c599b68f23bf4c2687c4827922ad7763
record_format	dspace
spelling	oai:doaj.org-article:c599b68f23bf4c2687c4827922ad77632021-11-11T19:19:34ZAn Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition10.3390/s212174041424-8220https://doaj.org/article/c599b68f23bf4c2687c4827922ad77632021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7404https://doaj.org/toc/1424-8220Over the last few decades, pattern recognition algorithms have shown promising results in the field of upper limb prostheses myoelectric control and are now gradually being incorporated in commercial devices. A widely used approach is based on a classifier which assigns a specific input value to a selected hand motion. While this method guarantees good performance and robustness within each class, it still shows limitations in adapting to different conditions encountered in real-world applications, such as changes in limb position or external loads. This paper proposes an adaptive method based on a pattern recognition classifier that takes advantage of an augmented dataset—i.e., representing variations in limb position or external loads—to selectively adapt to underrepresented variations. The proposed method was evaluated using a series of target achievement control tests with ten able-bodied volunteers. Results indicated a higher median completion rate >3.33% for the adapted algorithm compared to a classical pattern recognition classifier used as a baseline model. Subject-specific performance showed the potential for improved control after adaptation and a ≤13% completion rate; and in many instances, the adapted points were able to provide new information within classes. These preliminary results show the potential of the proposed method and encourage further development.Veronika SpiekerAmartya GangulySami HaddadinCristina PiazzaMDPI AGarticleupper-limb prosthesesmyoelectric controlpattern recognitionlimb effectlinear discriminant analysismulti-modal controlChemical technologyTP1-1185ENSensors, Vol 21, Iss 7404, p 7404 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	upper-limb prostheses myoelectric control pattern recognition limb effect linear discriminant analysis multi-modal control Chemical technology TP1-1185
spellingShingle	upper-limb prostheses myoelectric control pattern recognition limb effect linear discriminant analysis multi-modal control Chemical technology TP1-1185 Veronika Spieker Amartya Ganguly Sami Haddadin Cristina Piazza An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition
description	Over the last few decades, pattern recognition algorithms have shown promising results in the field of upper limb prostheses myoelectric control and are now gradually being incorporated in commercial devices. A widely used approach is based on a classifier which assigns a specific input value to a selected hand motion. While this method guarantees good performance and robustness within each class, it still shows limitations in adapting to different conditions encountered in real-world applications, such as changes in limb position or external loads. This paper proposes an adaptive method based on a pattern recognition classifier that takes advantage of an augmented dataset—i.e., representing variations in limb position or external loads—to selectively adapt to underrepresented variations. The proposed method was evaluated using a series of target achievement control tests with ten able-bodied volunteers. Results indicated a higher median completion rate >3.33% for the adapted algorithm compared to a classical pattern recognition classifier used as a baseline model. Subject-specific performance showed the potential for improved control after adaptation and a ≤13% completion rate; and in many instances, the adapted points were able to provide new information within classes. These preliminary results show the potential of the proposed method and encourage further development.
format	article
author	Veronika Spieker Amartya Ganguly Sami Haddadin Cristina Piazza
author_facet	Veronika Spieker Amartya Ganguly Sami Haddadin Cristina Piazza
author_sort	Veronika Spieker
title	An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition
title_short	An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition
title_full	An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition
title_fullStr	An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition
title_full_unstemmed	An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition
title_sort	adaptive multi-modal control strategy to attenuate the limb position effect in myoelectric pattern recognition
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/c599b68f23bf4c2687c4827922ad7763
work_keys_str_mv	AT veronikaspieker anadaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT amartyaganguly anadaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT samihaddadin anadaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT cristinapiazza anadaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT veronikaspieker adaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT amartyaganguly adaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT samihaddadin adaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition AT cristinapiazza adaptivemultimodalcontrolstrategytoattenuatethelimbpositioneffectinmyoelectricpatternrecognition
_version_	1718431552059211776

An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition

Ejemplares similares