Estimation of manual wheelchair-based activities in the free-living environment using a neural network model with inertial body-worn sensors

Emma Fortune, Beth A. Cloud-Biebl, Stefan I. Madansingh, Che Ngufor, Meegan G. Van Straaten, Brianna M. Goodwin, Dennis H. Murphree, Kristin D Zhao, Melissa (Missy) M. Morrow

Research output: Contribution to journalArticle

Abstract

Shoulder pain is common in manual wheelchair (MWC) users. Overuse is thought to be a major cause, but little is known about exposure to activities of daily living (ADLs). The study goal was to develop a method to estimate three conditions in the field: (1) non-propulsion activity, (2) MWC propulsion, and (3) static time using an inertial measurement unit (IMU). Upper arm IMU data were collected as ten MWC users performed lab-based MWC-related ADLs. A neural network model was developed to classify data as non-propulsion activity, propulsion, or static, and validated for the lab-based data collection by video comparison. Six of the participants’ free-living IMU data were collected and the lab-based model was applied to estimate daily non-propulsion activity, propulsion, and static time. The neural network model yielded lab-based validity measures ≥0.87 for differentiating non-propulsion activity, propulsion, and static time. A quasi-validation of one participant's field-based data yielded validity measures ≥0.66 for identifying propulsion. Participants’ estimated mean daily non-propulsion activity, propulsion, and static time ranged from 158 to 409, 13 to 25, and 367 to 609 min, respectively. The preliminary results suggest the model may be able to accurately identify MWC users’ field-based activities. The inclusion of field-based IMU data in the model could further improve field-based classification.

Original languageEnglish (US)
JournalJournal of Electromyography and Kinesiology
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Wheelchairs
Neural Networks (Computer)
Activities of Daily Living
Shoulder Pain
Arm

Keywords

  • Activity classification
  • Body-worn sensors
  • Inertial measurement units
  • Shoulder overuse
  • Spinal cord injury
  • Wheelchair propulsion

ASJC Scopus subject areas

  • Neuroscience (miscellaneous)
  • Biophysics
  • Clinical Neurology

Cite this

Estimation of manual wheelchair-based activities in the free-living environment using a neural network model with inertial body-worn sensors. / Fortune, Emma; Cloud-Biebl, Beth A.; Madansingh, Stefan I.; Ngufor, Che; Van Straaten, Meegan G.; Goodwin, Brianna M.; Murphree, Dennis H.; Zhao, Kristin D; Morrow, Melissa (Missy) M.

In: Journal of Electromyography and Kinesiology, 01.01.2019.

Research output: Contribution to journalArticle

@article{2f298142f8ed4ee598770a43f65545fb,
title = "Estimation of manual wheelchair-based activities in the free-living environment using a neural network model with inertial body-worn sensors",
abstract = "Shoulder pain is common in manual wheelchair (MWC) users. Overuse is thought to be a major cause, but little is known about exposure to activities of daily living (ADLs). The study goal was to develop a method to estimate three conditions in the field: (1) non-propulsion activity, (2) MWC propulsion, and (3) static time using an inertial measurement unit (IMU). Upper arm IMU data were collected as ten MWC users performed lab-based MWC-related ADLs. A neural network model was developed to classify data as non-propulsion activity, propulsion, or static, and validated for the lab-based data collection by video comparison. Six of the participants’ free-living IMU data were collected and the lab-based model was applied to estimate daily non-propulsion activity, propulsion, and static time. The neural network model yielded lab-based validity measures ≥0.87 for differentiating non-propulsion activity, propulsion, and static time. A quasi-validation of one participant's field-based data yielded validity measures ≥0.66 for identifying propulsion. Participants’ estimated mean daily non-propulsion activity, propulsion, and static time ranged from 158 to 409, 13 to 25, and 367 to 609 min, respectively. The preliminary results suggest the model may be able to accurately identify MWC users’ field-based activities. The inclusion of field-based IMU data in the model could further improve field-based classification.",
keywords = "Activity classification, Body-worn sensors, Inertial measurement units, Shoulder overuse, Spinal cord injury, Wheelchair propulsion",
author = "Emma Fortune and Cloud-Biebl, {Beth A.} and Madansingh, {Stefan I.} and Che Ngufor and {Van Straaten}, {Meegan G.} and Goodwin, {Brianna M.} and Murphree, {Dennis H.} and Zhao, {Kristin D} and Morrow, {Melissa (Missy) M.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.jelekin.2019.07.007",
language = "English (US)",
journal = "Journal of Electromyography and Kinesiology",
issn = "1050-6411",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Estimation of manual wheelchair-based activities in the free-living environment using a neural network model with inertial body-worn sensors

AU - Fortune, Emma

AU - Cloud-Biebl, Beth A.

AU - Madansingh, Stefan I.

AU - Ngufor, Che

AU - Van Straaten, Meegan G.

AU - Goodwin, Brianna M.

AU - Murphree, Dennis H.

AU - Zhao, Kristin D

AU - Morrow, Melissa (Missy) M.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Shoulder pain is common in manual wheelchair (MWC) users. Overuse is thought to be a major cause, but little is known about exposure to activities of daily living (ADLs). The study goal was to develop a method to estimate three conditions in the field: (1) non-propulsion activity, (2) MWC propulsion, and (3) static time using an inertial measurement unit (IMU). Upper arm IMU data were collected as ten MWC users performed lab-based MWC-related ADLs. A neural network model was developed to classify data as non-propulsion activity, propulsion, or static, and validated for the lab-based data collection by video comparison. Six of the participants’ free-living IMU data were collected and the lab-based model was applied to estimate daily non-propulsion activity, propulsion, and static time. The neural network model yielded lab-based validity measures ≥0.87 for differentiating non-propulsion activity, propulsion, and static time. A quasi-validation of one participant's field-based data yielded validity measures ≥0.66 for identifying propulsion. Participants’ estimated mean daily non-propulsion activity, propulsion, and static time ranged from 158 to 409, 13 to 25, and 367 to 609 min, respectively. The preliminary results suggest the model may be able to accurately identify MWC users’ field-based activities. The inclusion of field-based IMU data in the model could further improve field-based classification.

AB - Shoulder pain is common in manual wheelchair (MWC) users. Overuse is thought to be a major cause, but little is known about exposure to activities of daily living (ADLs). The study goal was to develop a method to estimate three conditions in the field: (1) non-propulsion activity, (2) MWC propulsion, and (3) static time using an inertial measurement unit (IMU). Upper arm IMU data were collected as ten MWC users performed lab-based MWC-related ADLs. A neural network model was developed to classify data as non-propulsion activity, propulsion, or static, and validated for the lab-based data collection by video comparison. Six of the participants’ free-living IMU data were collected and the lab-based model was applied to estimate daily non-propulsion activity, propulsion, and static time. The neural network model yielded lab-based validity measures ≥0.87 for differentiating non-propulsion activity, propulsion, and static time. A quasi-validation of one participant's field-based data yielded validity measures ≥0.66 for identifying propulsion. Participants’ estimated mean daily non-propulsion activity, propulsion, and static time ranged from 158 to 409, 13 to 25, and 367 to 609 min, respectively. The preliminary results suggest the model may be able to accurately identify MWC users’ field-based activities. The inclusion of field-based IMU data in the model could further improve field-based classification.

KW - Activity classification

KW - Body-worn sensors

KW - Inertial measurement units

KW - Shoulder overuse

KW - Spinal cord injury

KW - Wheelchair propulsion

UR - http://www.scopus.com/inward/record.url?scp=85071360736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071360736&partnerID=8YFLogxK

U2 - 10.1016/j.jelekin.2019.07.007

DO - 10.1016/j.jelekin.2019.07.007

M3 - Article

AN - SCOPUS:85071360736

JO - Journal of Electromyography and Kinesiology

JF - Journal of Electromyography and Kinesiology

SN - 1050-6411

ER -