Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study

One major challenge limiting the use of dexterous robotic hand prostheses controlled via electromyography and pattern recognition relates to the important efforts required to train complex models from scratch. To overcome this problem, several studies in recent years proposed to use transfer learnin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Giulio Marano, Cristina Brambilla, Robert Mihai Mira, Alessandro Scano, Henning Müller, Manfredo Atzori
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	machine learning EMG biofeedback transfer learning random forest classifier Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/391934e93c1140679dfb0f541308f874
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:391934e93c1140679dfb0f541308f874
record_format	dspace
spelling	oai:doaj.org-article:391934e93c1140679dfb0f541308f8742021-11-25T18:56:55ZQuestioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study10.3390/s212275001424-8220https://doaj.org/article/391934e93c1140679dfb0f541308f8742021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7500https://doaj.org/toc/1424-8220One major challenge limiting the use of dexterous robotic hand prostheses controlled via electromyography and pattern recognition relates to the important efforts required to train complex models from scratch. To overcome this problem, several studies in recent years proposed to use transfer learning, combining pre-trained models (obtained from prior subjects) with training sessions performed on a specific user. Although a few promising results were reported in the past, it was recently shown that the use of conventional transfer learning algorithms does not increase performance if proper hyperparameter optimization is performed on the standard approach that does not exploit transfer learning. The objective of this paper is to introduce novel analyses on this topic by using a random forest classifier without hyperparameter optimization and to extend them with experiments performed on data recorded from the same patient, but in different data acquisition sessions. Two domain adaptation techniques were tested on the random forest classifier, allowing us to conduct experiments on healthy subjects and amputees. Differently from several previous papers, our results show that there are no appreciable improvements in terms of accuracy, regardless of the transfer learning techniques tested. The lack of adaptive learning is also demonstrated for the first time in an intra-subject experimental setting when using as a source ten data acquisitions recorded from the same subject but on five different days.Giulio MaranoCristina BrambillaRobert Mihai MiraAlessandro ScanoHenning MüllerManfredo AtzoriMDPI AGarticlemachine learningEMGbiofeedbacktransfer learningrandom forest classifierChemical technologyTP1-1185ENSensors, Vol 21, Iss 7500, p 7500 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning EMG biofeedback transfer learning random forest classifier Chemical technology TP1-1185
spellingShingle	machine learning EMG biofeedback transfer learning random forest classifier Chemical technology TP1-1185 Giulio Marano Cristina Brambilla Robert Mihai Mira Alessandro Scano Henning Müller Manfredo Atzori Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study
description	One major challenge limiting the use of dexterous robotic hand prostheses controlled via electromyography and pattern recognition relates to the important efforts required to train complex models from scratch. To overcome this problem, several studies in recent years proposed to use transfer learning, combining pre-trained models (obtained from prior subjects) with training sessions performed on a specific user. Although a few promising results were reported in the past, it was recently shown that the use of conventional transfer learning algorithms does not increase performance if proper hyperparameter optimization is performed on the standard approach that does not exploit transfer learning. The objective of this paper is to introduce novel analyses on this topic by using a random forest classifier without hyperparameter optimization and to extend them with experiments performed on data recorded from the same patient, but in different data acquisition sessions. Two domain adaptation techniques were tested on the random forest classifier, allowing us to conduct experiments on healthy subjects and amputees. Differently from several previous papers, our results show that there are no appreciable improvements in terms of accuracy, regardless of the transfer learning techniques tested. The lack of adaptive learning is also demonstrated for the first time in an intra-subject experimental setting when using as a source ten data acquisitions recorded from the same subject but on five different days.
format	article
author	Giulio Marano Cristina Brambilla Robert Mihai Mira Alessandro Scano Henning Müller Manfredo Atzori
author_facet	Giulio Marano Cristina Brambilla Robert Mihai Mira Alessandro Scano Henning Müller Manfredo Atzori
author_sort	Giulio Marano
title	Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study
title_short	Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study
title_full	Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study
title_fullStr	Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study
title_full_unstemmed	Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study
title_sort	questioning domain adaptation in myoelectric hand prostheses control: an inter- and intra-subject study
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/391934e93c1140679dfb0f541308f874
work_keys_str_mv	AT giuliomarano questioningdomainadaptationinmyoelectrichandprosthesescontrolaninterandintrasubjectstudy AT cristinabrambilla questioningdomainadaptationinmyoelectrichandprosthesescontrolaninterandintrasubjectstudy AT robertmihaimira questioningdomainadaptationinmyoelectrichandprosthesescontrolaninterandintrasubjectstudy AT alessandroscano questioningdomainadaptationinmyoelectrichandprosthesescontrolaninterandintrasubjectstudy AT henningmuller questioningdomainadaptationinmyoelectrichandprosthesescontrolaninterandintrasubjectstudy AT manfredoatzori questioningdomainadaptationinmyoelectrichandprosthesescontrolaninterandintrasubjectstudy
_version_	1718410517065760768

Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study

Ejemplares similares