Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Exploiting the Intertemporal Structure of the Upper-Limb sEMG: Comparisons between an LSTM Network and Cross-Sectional Myoelectric Pattern Recognition Methods

Olsson, Alexander LU ; Malesevic, Nebojsa LU ; Björkman, Anders LU and Antfolk, Christian LU (2019) 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Abstract
The use of natural myoelectric interfaces promises great value for a variety of potential applications, clinical and otherwise, provided a computational mapping between measured neuromuscular activity and executed motion can be approximated to a satisfactory degree. However, prevalent methods intended for such decoding of movement intent from the surface electromyogram (sEMG) based on pattern recognition typically do not capitalize on the inherently time series-like nature of the acquired signals. In this paper, we present the results from a comparative study in which the performances of traditional cross-sectional pattern recognition methods were compared with that of a classifier built on the natural assumption of temporal ordering by... (More)
The use of natural myoelectric interfaces promises great value for a variety of potential applications, clinical and otherwise, provided a computational mapping between measured neuromuscular activity and executed motion can be approximated to a satisfactory degree. However, prevalent methods intended for such decoding of movement intent from the surface electromyogram (sEMG) based on pattern recognition typically do not capitalize on the inherently time series-like nature of the acquired signals. In this paper, we present the results from a comparative study in which the performances of traditional cross-sectional pattern recognition methods were compared with that of a classifier built on the natural assumption of temporal ordering by utilizing a long short-term memory (LSTM) neural network. The resulting evaluation indicate that the LSTM approach outperforms traditional gesture recognition techniques which are based on cross-sectional inference. These findings held both when the LSTM classifier operated on conventional features and on raw sEMG and for both healthy subjects and transradial amputees. (Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
conference location
Berlin, Germany
conference dates
2019-07-23 - 2019-07-27
external identifiers
  • scopus:85077861105
  • pmid:31947357
ISBN
978-1-5386-1312-2
978-1-5386-1312-2
DOI
10.1109/EMBC.2019.8856648
language
Swedish
LU publication?
yes
id
85463de0-65c9-4b2f-8876-82c12420bea0
date added to LUP
2019-10-08 10:28:34
date last changed
2023-04-10 01:12:38
@inproceedings{85463de0-65c9-4b2f-8876-82c12420bea0,
  abstract     = {{The use of natural myoelectric interfaces promises great value for a variety of potential applications, clinical and otherwise, provided a computational mapping between measured neuromuscular activity and executed motion can be approximated to a satisfactory degree. However, prevalent methods intended for such decoding of movement intent from the surface electromyogram (sEMG) based on pattern recognition typically do not capitalize on the inherently time series-like nature of the acquired signals. In this paper, we present the results from a comparative study in which the performances of traditional cross-sectional pattern recognition methods were compared with that of a classifier built on the natural assumption of temporal ordering by utilizing a long short-term memory (LSTM) neural network. The resulting evaluation indicate that the LSTM approach outperforms traditional gesture recognition techniques which are based on cross-sectional inference. These findings held both when the LSTM classifier operated on conventional features and on raw sEMG and for both healthy subjects and transradial amputees.}},
  author       = {{Olsson, Alexander and Malesevic, Nebojsa and Björkman, Anders and Antfolk, Christian}},
  booktitle    = {{2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)}},
  isbn         = {{978-1-5386-1312-2}},
  language     = {{swe}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Exploiting the Intertemporal Structure of the Upper-Limb sEMG: Comparisons between an LSTM Network and Cross-Sectional Myoelectric Pattern Recognition Methods}},
  url          = {{http://dx.doi.org/10.1109/EMBC.2019.8856648}},
  doi          = {{10.1109/EMBC.2019.8856648}},
  year         = {{2019}},
}