Low-back electromyography (EMG) data-driven load classification for dynamic lifting tasks

Deema Totah; Lauro Ojeda; Daniel D Johnson; Deanna Gates; Emily Mower Provost; Kira Barton

doi:10.1371/journal.pone.0192938

Back

Journal article

Open access

Peer reviewed

Low-back electromyography (EMG) data-driven load classification for dynamic lifting tasks

Deema Totah, Lauro Ojeda, Daniel D Johnson, Deanna Gates, Emily Mower Provost and Kira Barton

PloS one, Vol.13(2), pp.e0192938-e0192938

2018

DOI: 10.1371/journal.pone.0192938

PMCID: PMC5814006

PMID: 29447252

Files and links (1)

url

https://doi.org/10.1371/journal.pone.0192938View

Published (Version of record) Open Access

Abstract

Numerous devices have been designed to support the back during lifting tasks. To improve the utility of such devices, this research explores the use of preparatory muscle activity to classify muscle loading and initiate appropriate device activation. The goal of this study was to determine the earliest time window that enabled accurate load classification during a dynamic lifting task. Nine subjects performed thirty symmetrical lifts, split evenly across three weight conditions (no-weight, 10-lbs and 24-lbs), while low-back muscle activity data was collected. Seven descriptive statistics features were extracted from 100 ms windows of data. A multinomial logistic regression (MLR) classifier was trained and tested, employing leave-one subject out cross-validation, to classify lifted load values. Dimensionality reduction was achieved through feature cross-correlation analysis and greedy feedforward selection. The time of full load support by the subject was defined as load-onset. Regions of highest average classification accuracy started at 200 ms before until 200 ms after load-onset with average accuracies ranging from 80% (±10%) to 81% (±7%). The average recall for each class ranged from 69-92%. These inter-subject classification results indicate that preparatory muscle activity can be leveraged to identify the intent to lift a weight up to 100 ms prior to load-onset. The high accuracies shown indicate the potential to utilize intent classification for assistive device applications. Active assistive devices, e.g. exoskeletons, could prevent back injury by off-loading low-back muscles. Early intent classification allows more time for actuators to respond and integrate seamlessly with the user.

Back - physiology

Back Muscles - physiology

Electromyography - methods

Female

Humans

Lifting

Logistic Models

Male

Motor Activity - physiology

Signal Processing, Computer-Assisted

Young Adult

Details

Title: Subtitle: Low-back electromyography (EMG) data-driven load classification for dynamic lifting tasks
Creators: Deema Totah - University of Michigan
Lauro Ojeda - University of Michigan
Daniel D Johnson - University of Michigan
Deanna Gates - University of Michigan
Emily Mower Provost - University of Michigan
Kira Barton - University of Michigan
Resource Type: Journal article
Publication Details: PloS one, Vol.13(2), pp.e0192938-e0192938
DOI: 10.1371/journal.pone.0192938
PMID: 29447252
PMCID: PMC5814006
NLM abbreviation: PLoS One
ISSN: 1932-6203
eISSN: 1932-6203
Grant note: DOI: 10.13039/100000001, name: National Science Foundation (US), award: 1534003; name: Horace H. Rackham School of Graduate Studies, University of Michigan (US), award: Rackham Graduate Research Grant; name: Mechanical Engineering Department, University of Michigan, award: Start Up Funds
Language: English
Date published: 2018
Academic Unit: Mechanical Engineering
Record Identifier: 9984196558502771

Metrics

73 Record Views

17 Times Cited - Web of Science