Cargando…

Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques

Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals colle...

Descripción completa

Detalles Bibliográficos
Autores principales: Little, Kieran, K Pappachan, Bobby, Yang, Sibo, Noronha, Bernardo, Campolo, Domenico, Accoto, Dino
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7827251/
https://www.ncbi.nlm.nih.gov/pubmed/33445601
http://dx.doi.org/10.3390/s21020498
_version_ 1783640716991266816
author Little, Kieran
K Pappachan, Bobby
Yang, Sibo
Noronha, Bernardo
Campolo, Domenico
Accoto, Dino
author_facet Little, Kieran
K Pappachan, Bobby
Yang, Sibo
Noronha, Bernardo
Campolo, Domenico
Accoto, Dino
author_sort Little, Kieran
collection PubMed
description Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals collected from the user (such as kinematic or physiological), the extracted features and the selected algorithm. We explore the use of different features extracted from various signals when used to train multiple algorithms for the prediction of elbow flexion angle trajectories. The accuracy of the prediction was evaluated based on the mean velocity and peak amplitude of the trajectory, which are sufficient to fully define it. Results show that prediction accuracy when using solely physiological signals is low, however, when kinematic signals are included, it is largely improved. This suggests kinematic signals provide a reliable source of information for predicting elbow trajectories. Different models were trained using 10 algorithms. Regularization algorithms performed well in all conditions, whereas neural networks performed better when the most important features are selected. The extensive analysis provided in this study can be consulted to aid in the development of accurate upper limb motion intention detection models.
format Online
Article
Text
id pubmed-7827251
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-78272512021-01-25 Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques Little, Kieran K Pappachan, Bobby Yang, Sibo Noronha, Bernardo Campolo, Domenico Accoto, Dino Sensors (Basel) Article Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals collected from the user (such as kinematic or physiological), the extracted features and the selected algorithm. We explore the use of different features extracted from various signals when used to train multiple algorithms for the prediction of elbow flexion angle trajectories. The accuracy of the prediction was evaluated based on the mean velocity and peak amplitude of the trajectory, which are sufficient to fully define it. Results show that prediction accuracy when using solely physiological signals is low, however, when kinematic signals are included, it is largely improved. This suggests kinematic signals provide a reliable source of information for predicting elbow trajectories. Different models were trained using 10 algorithms. Regularization algorithms performed well in all conditions, whereas neural networks performed better when the most important features are selected. The extensive analysis provided in this study can be consulted to aid in the development of accurate upper limb motion intention detection models. MDPI 2021-01-12 /pmc/articles/PMC7827251/ /pubmed/33445601 http://dx.doi.org/10.3390/s21020498 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Little, Kieran
K Pappachan, Bobby
Yang, Sibo
Noronha, Bernardo
Campolo, Domenico
Accoto, Dino
Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques
title Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques
title_full Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques
title_fullStr Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques
title_full_unstemmed Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques
title_short Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques
title_sort elbow motion trajectory prediction using a multi-modal wearable system: a comparative analysis of machine learning techniques
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7827251/
https://www.ncbi.nlm.nih.gov/pubmed/33445601
http://dx.doi.org/10.3390/s21020498
work_keys_str_mv AT littlekieran elbowmotiontrajectorypredictionusingamultimodalwearablesystemacomparativeanalysisofmachinelearningtechniques
AT kpappachanbobby elbowmotiontrajectorypredictionusingamultimodalwearablesystemacomparativeanalysisofmachinelearningtechniques
AT yangsibo elbowmotiontrajectorypredictionusingamultimodalwearablesystemacomparativeanalysisofmachinelearningtechniques
AT noronhabernardo elbowmotiontrajectorypredictionusingamultimodalwearablesystemacomparativeanalysisofmachinelearningtechniques
AT campolodomenico elbowmotiontrajectorypredictionusingamultimodalwearablesystemacomparativeanalysisofmachinelearningtechniques
AT accotodino elbowmotiontrajectorypredictionusingamultimodalwearablesystemacomparativeanalysisofmachinelearningtechniques