Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques

Pattern recognition of electromyography (EMG) signals can potentially improve the performance of myoelectric control for upper limb prostheses with respect to current clinical approaches based on direct control. However, the choice of features for classification is challenging and impacts long-term...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Vol. 18; no. 8; p. 2497
Main Authors: Zia ur Rehman, Muhammad, Waris, Asim, Gilani, Syed Omer, Jochumsen, Mads, Niazi, Imran Khan, Jamil, Mohsin, Farina, Dario, Kamavuako, Ernest Nlandu
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 01.08.2018
MDPI
Subjects:
Adult
Artificial Limbs
autoencoders
Classification
convolutional neural networks
Deep Learning
Discriminant analysis
Electromyography
Electromyography - methods
Female
Hand - physiology
Humans
Male
multiday classification
MYO band
myocontrol
Neural networks
pattern recognition
Young Adult
autoencoders
MYO band
electromyography
convolutional neural networks
multiday classification
myocontrol
pattern recognition
ISSN:1424-8220, 1424-8220
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Pattern recognition of electromyography (EMG) signals can potentially improve the performance of myoelectric control for upper limb prostheses with respect to current clinical approaches based on direct control. However, the choice of features for classification is challenging and impacts long-term performance. Here, we propose the use of EMG raw signals as direct inputs to deep networks with intrinsic feature extraction capabilities recorded over multiple days. Seven able-bodied subjects performed six active motions (plus rest), and EMG signals were recorded for 15 consecutive days with two sessions per day using the MYO armband (MYB, a wearable EMG sensor). The classification was performed by a convolutional neural network (CNN) with raw bipolar EMG samples as the inputs, and the performance was compared with linear discriminant analysis (LDA) and stacked sparse autoencoders with features (SSAE-f) and raw samples (SSAE-r) as inputs. CNN outperformed (lower classification error) both LDA and SSAE-r in the within-session, between sessions on same day, between the pair of days, and leave-out one-day evaluation (p < 0.001) analyses. However, no significant difference was found between CNN and SSAE-f. These results demonstrated that CNN significantly improved performance and increased robustness over time compared with standard LDA with associated handcrafted features. This data-driven features extraction approach may overcome the problem of the feature calibration and selection in myoelectric control.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s18082497