Efficacy and Efficiency of Multivariate Linear Regression for Rapid Prediction of Femoral Strain Fields during Activity

Simple item page
dc.contributor.author Ziaeipoor, Hamed en_US
dc.contributor.author Martelli, Saulo en_US
dc.contributor.author Pandy, Marcus G en_US
dc.contributor.author Taylor, Mark en_US
dc.date.accessioned 2019-05-07T05:00:01Z
dc.date.available 2019-05-07T05:00:01Z
dc.date.issued 2018-12-11
dc.description © 2018 IPEM. Published by Elsevier Ltd. This manuscript version is made available under the CC-BY-NC-ND 4.0 license: http://creativecommons.org/licenses/by-nc-nd/4.0/ This author accepted manuscript is made available following 12 month embargo from date of publication (December 2018) in accordance with the publisher’s archiving policy. en_US
dc.description.abstract Multivariate Linear Regression-based (MLR) surrogate models were explored to reduce the computational cost of predicting femoral strains during normal activity in comparison with finite element analysis. The musculoskeletal model of one individual, the finite-element model of the right femur, and experimental force and motion data for normal walking, fast walking, stair ascent, stair descent, and rising from a chair were obtained from a previous study. Equivalent Von Mises strain was calculated for 1000 frames uniformly distributed across activities. MLR surrogate models were generated using training sets of 50, 100, 200 and 300 samples. The finite-element and MLR analyses were compared using linear regression. The Root Mean Square Error (RMSE) and the 95th percentile of the strain error distribution were used as indicators of average and peak error. The MLR model trained using 200 samples (RMSE < 108 µε; peak error < 228 µε) was used as a reference. The finite-element method required 66 s per frame on a standard desktop computer. The MLR model required 0.1 s per frame plus 1848 s of training time. RMSE ranged from 1.2% to 1.3% while peak error ranged from 2.2% to 3.6% of the maximum micro-strain (5020 µε). Performance within an activity was lower during early and late stance, with RMSE of 4.1% and peak error of 8.6% of the maximum computed micro-strain. These results show that MLR surrogate models may be used to rapidly and accurately estimate strain fields in long bones during daily physical activity. en_US
dc.identifier.citation Ziaeipoor, H., Martelli, S., Pandy, M., & Taylor, M. (2019). Efficacy and efficiency of multivariate linear regression for rapid prediction of femoral strain fields during activity. Medical Engineering & Physics, 63, 88–92. https://doi.org/10.1016/j.medengphy.2018.12.001 en_US
dc.identifier.doi https://doi.org/10.1016/j.medengphy.2018.12.001 en_US
dc.identifier.issn 1350-4533
dc.identifier.uri http://hdl.handle.net/2328/39187
dc.language.iso en en_US
dc.oaire.license.condition.license CC-BY-NC-ND
dc.publisher Elsevier en_US
dc.relation http://purl.org/au-research/grants/arc/DP180103146 en_US
dc.relation.grantnumber ARC/DP180103146 en_US
dc.rights © 2018 IPEM en_US
dc.rights.holder IPEM en_US
dc.subject Musculoskeletal en_US
dc.subject Finite-element en_US
dc.subject Surrogate model en_US
dc.subject Human gait en_US
dc.title Efficacy and Efficiency of Multivariate Linear Regression for Rapid Prediction of Femoral Strain Fields during Activity en_US
dc.type Article en_US
local.contributor.authorOrcidLookup Martelli, Saulo: https://orcid.org/0000-0002-0012-8122 en_US
local.contributor.authorOrcidLookup Taylor, Mark: https://orcid.org/0000-0001-7842-6472 en_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Ziaeipoor_Efficacy_AM2019.pdf
Size:
1.39 MB
Format:
Adobe Portable Document Format
Description:
Author version
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.84 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Environment - Collected Works
 Flinders Open Access Research