Functional electrical stimulation controlled by artificial neural networks: Pilot experiments with simple movements are promising for rehabilitation applications

Simona Ferrante, Alessandra Pedrocchi, Marco Iannò, Elena De Momi, Maurizio Ferrarin, Giancarlo Ferrigno

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This study falls within the ambit of research on functional electrical stimulation for the design of rehabilitation training for spinal cord injured patients. In this context, a crucial issue is the control of the stimulation parameters in order to optimize the patterns of muscle activation and to increase the duration of the exercises. An adaptive control system (NEURADAPT) based on artificial neural networks (ANNs) was developed to control the knee joint in accordance with desired trajectories by stimulating quadriceps muscles. This strategy includes an inverse neural model of the stimulated limb in the feedforward line and a neural network trained on-line in the feedback loop. NEURADAPT was compared with a linear closed-loop proportional integrative derivative (PID) controller and with a model-based neural controller (NEUROPID). Experiments on two subjects (one healthy and one paraplegic) show the good performance of NEURADAPT, which is able to reduce the time lag introduced by the PID controller. In addition, control systems based on ANN techniques do not require complicated calibration procedures at the beginning of each experimental session. After the initial learning phase, the ANN, thanks to its generalization capacity, is able to cope with a certain range of variability of skeletal muscle properties.

Original languageEnglish
Pages (from-to)243-252
Number of pages10
JournalFunctional Neurology
Volume19
Issue number4
Publication statusPublished - Oct 2004

Fingerprint

Quadriceps Muscle
Knee Joint
Calibration
Electric Stimulation
Spinal Cord
Healthy Volunteers
Skeletal Muscle
Rehabilitation
Extremities
Learning
Exercise
Muscles
Research

Keywords

  • Artificial neural networks
  • Functional electrical stimulation
  • Non-linear adaptive control systems
  • Rehabilitation engineering

ASJC Scopus subject areas

  • Clinical Neurology
  • Neuroscience(all)

Cite this

Functional electrical stimulation controlled by artificial neural networks : Pilot experiments with simple movements are promising for rehabilitation applications. / Ferrante, Simona; Pedrocchi, Alessandra; Iannò, Marco; De Momi, Elena; Ferrarin, Maurizio; Ferrigno, Giancarlo.

In: Functional Neurology, Vol. 19, No. 4, 10.2004, p. 243-252.

Research output: Contribution to journalArticle

Ferrante, Simona ; Pedrocchi, Alessandra ; Iannò, Marco ; De Momi, Elena ; Ferrarin, Maurizio ; Ferrigno, Giancarlo. / Functional electrical stimulation controlled by artificial neural networks : Pilot experiments with simple movements are promising for rehabilitation applications. In: Functional Neurology. 2004 ; Vol. 19, No. 4. pp. 243-252.
@article{74a9829637f248e5bb88aff10e5fe76d,
title = "Functional electrical stimulation controlled by artificial neural networks: Pilot experiments with simple movements are promising for rehabilitation applications",
abstract = "This study falls within the ambit of research on functional electrical stimulation for the design of rehabilitation training for spinal cord injured patients. In this context, a crucial issue is the control of the stimulation parameters in order to optimize the patterns of muscle activation and to increase the duration of the exercises. An adaptive control system (NEURADAPT) based on artificial neural networks (ANNs) was developed to control the knee joint in accordance with desired trajectories by stimulating quadriceps muscles. This strategy includes an inverse neural model of the stimulated limb in the feedforward line and a neural network trained on-line in the feedback loop. NEURADAPT was compared with a linear closed-loop proportional integrative derivative (PID) controller and with a model-based neural controller (NEUROPID). Experiments on two subjects (one healthy and one paraplegic) show the good performance of NEURADAPT, which is able to reduce the time lag introduced by the PID controller. In addition, control systems based on ANN techniques do not require complicated calibration procedures at the beginning of each experimental session. After the initial learning phase, the ANN, thanks to its generalization capacity, is able to cope with a certain range of variability of skeletal muscle properties.",
keywords = "Artificial neural networks, Functional electrical stimulation, Non-linear adaptive control systems, Rehabilitation engineering",
author = "Simona Ferrante and Alessandra Pedrocchi and Marco Iann{\`o} and {De Momi}, Elena and Maurizio Ferrarin and Giancarlo Ferrigno",
year = "2004",
month = "10",
language = "English",
volume = "19",
pages = "243--252",
journal = "Functional Neurology",
issn = "0393-5264",
publisher = "CIC Edizioni Internazionali s.r.l.",
number = "4",

}

TY - JOUR

T1 - Functional electrical stimulation controlled by artificial neural networks

T2 - Pilot experiments with simple movements are promising for rehabilitation applications

AU - Ferrante, Simona

AU - Pedrocchi, Alessandra

AU - Iannò, Marco

AU - De Momi, Elena

AU - Ferrarin, Maurizio

AU - Ferrigno, Giancarlo

PY - 2004/10

Y1 - 2004/10

N2 - This study falls within the ambit of research on functional electrical stimulation for the design of rehabilitation training for spinal cord injured patients. In this context, a crucial issue is the control of the stimulation parameters in order to optimize the patterns of muscle activation and to increase the duration of the exercises. An adaptive control system (NEURADAPT) based on artificial neural networks (ANNs) was developed to control the knee joint in accordance with desired trajectories by stimulating quadriceps muscles. This strategy includes an inverse neural model of the stimulated limb in the feedforward line and a neural network trained on-line in the feedback loop. NEURADAPT was compared with a linear closed-loop proportional integrative derivative (PID) controller and with a model-based neural controller (NEUROPID). Experiments on two subjects (one healthy and one paraplegic) show the good performance of NEURADAPT, which is able to reduce the time lag introduced by the PID controller. In addition, control systems based on ANN techniques do not require complicated calibration procedures at the beginning of each experimental session. After the initial learning phase, the ANN, thanks to its generalization capacity, is able to cope with a certain range of variability of skeletal muscle properties.

AB - This study falls within the ambit of research on functional electrical stimulation for the design of rehabilitation training for spinal cord injured patients. In this context, a crucial issue is the control of the stimulation parameters in order to optimize the patterns of muscle activation and to increase the duration of the exercises. An adaptive control system (NEURADAPT) based on artificial neural networks (ANNs) was developed to control the knee joint in accordance with desired trajectories by stimulating quadriceps muscles. This strategy includes an inverse neural model of the stimulated limb in the feedforward line and a neural network trained on-line in the feedback loop. NEURADAPT was compared with a linear closed-loop proportional integrative derivative (PID) controller and with a model-based neural controller (NEUROPID). Experiments on two subjects (one healthy and one paraplegic) show the good performance of NEURADAPT, which is able to reduce the time lag introduced by the PID controller. In addition, control systems based on ANN techniques do not require complicated calibration procedures at the beginning of each experimental session. After the initial learning phase, the ANN, thanks to its generalization capacity, is able to cope with a certain range of variability of skeletal muscle properties.

KW - Artificial neural networks

KW - Functional electrical stimulation

KW - Non-linear adaptive control systems

KW - Rehabilitation engineering

UR - http://www.scopus.com/inward/record.url?scp=16344370636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=16344370636&partnerID=8YFLogxK

M3 - Article

C2 - 15776793

AN - SCOPUS:16344370636

VL - 19

SP - 243

EP - 252

JO - Functional Neurology

JF - Functional Neurology

SN - 0393-5264

IS - 4

ER -