DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

The movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification

Gijsberts, Arjan and Atzori, Manfredo and Castellini, Claudio and Müller, Henning and Caputo, Barbara (2014) The movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 22 (4), pp. 735-744. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/TNSRE.2014.2303394. ISSN 1534-4320.

[img] PDF


There has been increasing interest in applying learning algorithms to improve the dexterity of myoelectric prostheses. In this work, we present a large-scale benchmark evaluation on the second iteration of the publicly released NinaPro database, which contains surface electromyography data for 6 DOF force activations as well as for 40 discrete hand movements. The evaluation involves a modern kernel method and compares performance of three feature representations and three kernel functions. Both the force regression and movement classification problems can be learned successfully when using a nonlinear kernel function, while the exp- kernel outperforms the more popular radial basis function kernel in all cases. Furthermore, combining surface electromyography and accelerometry in a multimodal classifier results in significant increases in accuracy as compared to when either modality is used individually. Since window-based classification accuracy should not be considered in isolation to estimate prosthetic controllability, we also provide results in terms of classification mistakes and prediction delay. To this extent, we propose the movement error rate as an alternative to the standard window-based accuracy. This error rate is insensitive to prediction delays and it allows us therefore to quantify mistakes and delays as independent performance characteristics. This type of analysis confirms that the inclusion of accelerometry is superior, as it results in fewer mistakes while at the same time reducing prediction delay.

Item URL in elib:https://elib.dlr.de/89781/
Document Type:Article
Title:The movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Gijsberts, ArjanIDIAP, SwitzerlandUNSPECIFIED
Atzori, ManfredoHES-SO, SwitzerlandUNSPECIFIED
Castellini, Claudioclaudio.castellini (at) dlr.deUNSPECIFIED
Müller, HenningHES-SO, SwitzerlandUNSPECIFIED
Caputo, BarbaraIDIAP, SwitzerlandUNSPECIFIED
Journal or Publication Title:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
DOI :10.1109/TNSRE.2014.2303394
Page Range:pp. 735-744
Publisher:IEEE - Institute of Electrical and Electronics Engineers
Keywords:Electromyography, machine learning, prosthetics.
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Castellini, Dr. Claudio
Deposited On:17 Oct 2014 15:10
Last Modified:31 Jul 2019 19:47

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.