Real-time pinch force estimation by surface electromyography using an artificial neural network

Changmok Choi, Suncheol Kwon, Wonil Park, Hae Dong Lee, Jung Kim

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

The palmar pinch force estimation is highly relevant not only in biomechanical studies, the analysis of sports activities, and ergonomic design analyses but also in clinical applications such as rehabilitation, in which information about muscle forces influences the physician's decisions on diagnosis and treatment. Force transducers have been used for such purposes, but they are restricted to grasping points and inevitably interfere with the human haptic sense because fingers cannot directly touch the environmental surface. We propose an estimation method of the palmar pinch force using surface electromyography (SEMG). Three myoelectric sites on the skin were selected on the basis of anatomical considerations and a Fisher discriminant analysis (FDA), and SEMG at these sites yields suitable information for pinch force estimation. An artificial neural network (ANN) was implemented to map the SEMG to the force, and its structure was optimized to avoid both under- and over-fitting problems. The resulting network was tested using SEMG signals recorded from the selected myoelectric sites of ten subjects in real time. The training time for each subject was short (approximately 96. s), and the estimation results were promising, with a normalized root mean squared error (NRMSE) of 0.081 ± 0.023 and a correlation (CORR) of 0.968 ± 0.017.

Original languageEnglish
Pages (from-to)429-436
Number of pages8
JournalMedical Engineering and Physics
Volume32
Issue number5
DOIs
Publication statusPublished - 2010 Jun 1

Fingerprint

Electromyography
Neural networks
Human Engineering
Touch
Discriminant Analysis
Transducers
Fingers
Sports
Discriminant analysis
Ergonomics
Rehabilitation
Patient rehabilitation
Muscle
Physicians
Skin
Muscles
Therapeutics

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Biomedical Engineering

Cite this

Choi, Changmok ; Kwon, Suncheol ; Park, Wonil ; Lee, Hae Dong ; Kim, Jung. / Real-time pinch force estimation by surface electromyography using an artificial neural network. In: Medical Engineering and Physics. 2010 ; Vol. 32, No. 5. pp. 429-436.
@article{d0019f01319f4bf2b7adc2a7857dda99,
title = "Real-time pinch force estimation by surface electromyography using an artificial neural network",
abstract = "The palmar pinch force estimation is highly relevant not only in biomechanical studies, the analysis of sports activities, and ergonomic design analyses but also in clinical applications such as rehabilitation, in which information about muscle forces influences the physician's decisions on diagnosis and treatment. Force transducers have been used for such purposes, but they are restricted to grasping points and inevitably interfere with the human haptic sense because fingers cannot directly touch the environmental surface. We propose an estimation method of the palmar pinch force using surface electromyography (SEMG). Three myoelectric sites on the skin were selected on the basis of anatomical considerations and a Fisher discriminant analysis (FDA), and SEMG at these sites yields suitable information for pinch force estimation. An artificial neural network (ANN) was implemented to map the SEMG to the force, and its structure was optimized to avoid both under- and over-fitting problems. The resulting network was tested using SEMG signals recorded from the selected myoelectric sites of ten subjects in real time. The training time for each subject was short (approximately 96. s), and the estimation results were promising, with a normalized root mean squared error (NRMSE) of 0.081 ± 0.023 and a correlation (CORR) of 0.968 ± 0.017.",
author = "Changmok Choi and Suncheol Kwon and Wonil Park and Lee, {Hae Dong} and Jung Kim",
year = "2010",
month = "6",
day = "1",
doi = "10.1016/j.medengphy.2010.04.004",
language = "English",
volume = "32",
pages = "429--436",
journal = "Medical Engineering and Physics",
issn = "1350-4533",
publisher = "Elsevier BV",
number = "5",

}

Real-time pinch force estimation by surface electromyography using an artificial neural network. / Choi, Changmok; Kwon, Suncheol; Park, Wonil; Lee, Hae Dong; Kim, Jung.

In: Medical Engineering and Physics, Vol. 32, No. 5, 01.06.2010, p. 429-436.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time pinch force estimation by surface electromyography using an artificial neural network

AU - Choi, Changmok

AU - Kwon, Suncheol

AU - Park, Wonil

AU - Lee, Hae Dong

AU - Kim, Jung

PY - 2010/6/1

Y1 - 2010/6/1

N2 - The palmar pinch force estimation is highly relevant not only in biomechanical studies, the analysis of sports activities, and ergonomic design analyses but also in clinical applications such as rehabilitation, in which information about muscle forces influences the physician's decisions on diagnosis and treatment. Force transducers have been used for such purposes, but they are restricted to grasping points and inevitably interfere with the human haptic sense because fingers cannot directly touch the environmental surface. We propose an estimation method of the palmar pinch force using surface electromyography (SEMG). Three myoelectric sites on the skin were selected on the basis of anatomical considerations and a Fisher discriminant analysis (FDA), and SEMG at these sites yields suitable information for pinch force estimation. An artificial neural network (ANN) was implemented to map the SEMG to the force, and its structure was optimized to avoid both under- and over-fitting problems. The resulting network was tested using SEMG signals recorded from the selected myoelectric sites of ten subjects in real time. The training time for each subject was short (approximately 96. s), and the estimation results were promising, with a normalized root mean squared error (NRMSE) of 0.081 ± 0.023 and a correlation (CORR) of 0.968 ± 0.017.

AB - The palmar pinch force estimation is highly relevant not only in biomechanical studies, the analysis of sports activities, and ergonomic design analyses but also in clinical applications such as rehabilitation, in which information about muscle forces influences the physician's decisions on diagnosis and treatment. Force transducers have been used for such purposes, but they are restricted to grasping points and inevitably interfere with the human haptic sense because fingers cannot directly touch the environmental surface. We propose an estimation method of the palmar pinch force using surface electromyography (SEMG). Three myoelectric sites on the skin were selected on the basis of anatomical considerations and a Fisher discriminant analysis (FDA), and SEMG at these sites yields suitable information for pinch force estimation. An artificial neural network (ANN) was implemented to map the SEMG to the force, and its structure was optimized to avoid both under- and over-fitting problems. The resulting network was tested using SEMG signals recorded from the selected myoelectric sites of ten subjects in real time. The training time for each subject was short (approximately 96. s), and the estimation results were promising, with a normalized root mean squared error (NRMSE) of 0.081 ± 0.023 and a correlation (CORR) of 0.968 ± 0.017.

UR - http://www.scopus.com/inward/record.url?scp=77952878508&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952878508&partnerID=8YFLogxK

U2 - 10.1016/j.medengphy.2010.04.004

DO - 10.1016/j.medengphy.2010.04.004

M3 - Article

VL - 32

SP - 429

EP - 436

JO - Medical Engineering and Physics

JF - Medical Engineering and Physics

SN - 1350-4533

IS - 5

ER -