Using Gait Dynamics to Estimate Load from a Body-Worn Accelerometer

Abstract

Heavy loads increase the risk of musculoskeletal injury for foot soldiers and first responders. Continuous monitoring of load carriage in the field has proven difficult. We propose an algorithm for estimating load from a single body-worn accelerometer. The algorithm utilizes three different methods for characterizing torso movement dynamics, and maps the extracted dynamics features to load estimates using two machine learning multivariate regression techniques. The algorithm is applied to two field collections of soldiers and civilians walking with varying loads. The effect of load on features is analyzed and the feature utility in conjunction with two regression techniques is assessed. Load estimation is done using a fixed set of machine learning parameters and leave-one-subject-out cross-validation. Accurate load estimates are obtained, demonstrating robustness to changes in equipment configuration, walking conditions, and walking speeds. On soldier data with loads ranging from 45 to 89 lbs, load estimates result in mean absolute error (MAE) of 6.64 lbs and correlation of r = 0.81. On combined soldier and civilian data, with loads ranging from 0 to 89 lbs, results are MAE = 9.57 lbs and r = 0.91.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 05, 2016
Accession Number
AD1033866

Entities

People

  • Andrew Dumas
  • Austin R. Hess
  • Greg Ciccarelli
  • James R. Williamson
  • Mark J. Buller

Organizations

  • MIT Lincoln Laboratory

Tags

Communities of Interest

  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Accelerometers
  • Algorithms
  • Autocorrelation
  • Brain Injuries
  • Covariance
  • Data Science
  • Data Sets
  • Detection
  • Dimensionality Reduction
  • Dynamics
  • Factor Analysis
  • Feature Extraction
  • Frequency Bands
  • Information Science
  • Prostheses And Implants
  • Statistics
  • Two Dimensional

Readers

  • Exercise and Sports Science.
  • Neural Network Machine Learning.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference