PMID- 34674720
OWN - NLM
STAT- MEDLINE
DCOM- 20211125
LR  - 20240403
IS  - 1743-0003 (Electronic)
IS  - 1743-0003 (Linking)
VI  - 18
IP  - 1
DP  - 2021 Oct 21
TI  - Long short-term memory (LSTM) recurrent neural network for muscle activity 
      detection.
PG  - 153
LID - 10.1186/s12984-021-00945-w [doi]
LID - 153
AB  - BACKGROUND: The accurate temporal analysis of muscle activation is of great 
      interest in many research areas, spanning from neurorobotic systems to the 
      assessment of altered locomotion patterns in orthopedic and neurological patients 
      and the monitoring of their motor rehabilitation. The performance of the existing 
      muscle activity detectors is strongly affected by both the SNR of the surface 
      electromyography (sEMG) signals and the set of features used to detect the 
      activation intervals. This work aims at introducing and validating a powerful 
      approach to detect muscle activation intervals from sEMG signals, based on long 
      short-term memory (LSTM) recurrent neural networks. METHODS: First, the 
      applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is 
      studied through simulated sEMG signals, comparing the LSTM-MAD performance 
      against other two widely used approaches, i.e., the standard approach based on 
      Teager-Kaiser Energy Operator (TKEO) and the traditional approach, used in 
      clinical gait analysis, based on a double-threshold statistical detector (Stat). 
      Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the 
      LSTM-MAD is assessed considering simulated signals with nine different SNR 
      values. Finally, the newly introduced approach is validated on real sEMG signals, 
      acquired during both physiological and pathological gait. Electromyography 
      recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic 
      patients, and 6 neurological patients) were included in the analysis. RESULTS: 
      The proposed algorithm overcomes the main limitations of the other tested 
      approaches and it works directly on sEMG signals, without the need for 
      background-noise and SNR estimation (as in Stat). Results demonstrate that 
      LSTM-MAD outperforms the other approaches, revealing higher values of F1-score 
      (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values 
      of onset/offset bias (average absolute bias < 6 ms), both on simulated and real 
      sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are 
      particularly evident for signals featuring a low to medium SNR. CONCLUSIONS: The 
      presented approach LSTM-MAD revealed excellent performances against TKEO and 
      Stat. The validation carried out both on simulated and real signals, considering 
      normal as well as pathological motor function during locomotion, demonstrated 
      that it can be considered a powerful tool in the accurate and effective 
      recognition/distinction of muscle activity from background noise in sEMG signals.
CI  - (c) 2021. The Author(s).
FAU - Ghislieri, Marco
AU  - Ghislieri M
AUID- ORCID: 0000-0001-7626-1563
AD  - Department of Electronics and Telecommunications, Politecnico Di Torino, 10129, 
      Turin, Italy. marco.ghislieri@polito.it.
AD  - PoliToBIOMed Lab, Politecnico di Torino, 10129, Turin, Italy. 
      marco.ghislieri@polito.it.
FAU - Cerone, Giacinto Luigi
AU  - Cerone GL
AD  - PoliToBIOMed Lab, Politecnico di Torino, 10129, Turin, Italy.
AD  - Laboratory for Engineering of the Neuromuscular System (LISiN), Departement of 
      Electronics and Telecommunications, Politecnico di Torino, 10129, Turin, Italy.
FAU - Knaflitz, Marco
AU  - Knaflitz M
AD  - Department of Electronics and Telecommunications, Politecnico Di Torino, 10129, 
      Turin, Italy.
AD  - PoliToBIOMed Lab, Politecnico di Torino, 10129, Turin, Italy.
FAU - Agostini, Valentina
AU  - Agostini V
AD  - Department of Electronics and Telecommunications, Politecnico Di Torino, 10129, 
      Turin, Italy.
AD  - PoliToBIOMed Lab, Politecnico di Torino, 10129, Turin, Italy.
LA  - eng
PT  - Journal Article
DEP - 20211021
PL  - England
TA  - J Neuroeng Rehabil
JT  - Journal of neuroengineering and rehabilitation
JID - 101232233
SB  - IM
MH  - Algorithms
MH  - Electromyography
MH  - Humans
MH  - *Memory, Short-Term
MH  - *Muscle, Skeletal
MH  - Neural Networks, Computer
PMC - PMC8532313
OTO - NOTNLM
OT  - Deep learning
OT  - EMG
OT  - EMG-based interfaces
OT  - Gait analysis
OT  - Muscle activation intervals
OT  - Muscle activity
OT  - Onset-offset detection
OT  - RNN
OT  - Surface electromyography
COIS- The authors declare that thay have no competing interests.
EDAT- 2021/10/23 06:00
MHDA- 2021/11/26 06:00
PMCR- 2021/10/21
CRDT- 2021/10/22 05:34
PHST- 2021/06/23 00:00 [received]
PHST- 2021/10/13 00:00 [accepted]
PHST- 2021/10/22 05:34 [entrez]
PHST- 2021/10/23 06:00 [pubmed]
PHST- 2021/11/26 06:00 [medline]
PHST- 2021/10/21 00:00 [pmc-release]
AID - 10.1186/s12984-021-00945-w [pii]
AID - 945 [pii]
AID - 10.1186/s12984-021-00945-w [doi]
PST - epublish
SO  - J Neuroeng Rehabil. 2021 Oct 21;18(1):153. doi: 10.1186/s12984-021-00945-w.