Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method
A high-accuracy gait data prediction model can be used to design prosthesis and orthosis for people having amputations or ailments of the lower limb. The objective of this study is to observe the gait data of different subjects and design a neural network to predict future gait angles for fixed spee...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2021-01-01
|
Series: | Journal of Healthcare Engineering |
Online Access: | http://dx.doi.org/10.1155/2021/5541255 |
id |
doaj-4b1605f7f8154a42ae4088801f4ab56c |
---|---|
record_format |
Article |
spelling |
doaj-4b1605f7f8154a42ae4088801f4ab56c2021-03-01T01:13:41ZengHindawi LimitedJournal of Healthcare Engineering2040-23092021-01-01202110.1155/2021/5541255Human Gait Analysis and Prediction Using the Levenberg-Marquardt MethodAbdullah Alharbi0Kamran Equbal1Sultan Ahmad2Haseeb Ur Rahman3Hashem Alyami4Department of Information TechnologyBiomedical EngineeringDepartment of Computer ScienceDepartment of Computer Science & Information TechnologyDepartment of Computer ScienceA high-accuracy gait data prediction model can be used to design prosthesis and orthosis for people having amputations or ailments of the lower limb. The objective of this study is to observe the gait data of different subjects and design a neural network to predict future gait angles for fixed speeds. The data were recorded via a Biometrics goniometer, while the subjects were walking on a treadmill for 20 seconds each at 2.4 kmph, 3.6 kmph, and 5.4 kmph. The data were then imported into Matlab, filtered to remove movement artifacts, and then used to design a neural network with 60% data for training, 20% for validation, and remaining 20% for testing using the LevenbergMarquardt method. The mean-squared error for all the cases was in the order of 10−3 or lower confirming that our method is correct. For further comparison, we randomly tested the neural network function with untrained data and compared the expected output with actual output of the neural network function using Pearson’s correlation coefficient and correlation plots. We conclude that our framework can be successfully used to design prosthesis and orthosis for lower limb. It can also be used to validate gait data and compare it to expected data in rehabilitation engineering.http://dx.doi.org/10.1155/2021/5541255 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Abdullah Alharbi Kamran Equbal Sultan Ahmad Haseeb Ur Rahman Hashem Alyami |
spellingShingle |
Abdullah Alharbi Kamran Equbal Sultan Ahmad Haseeb Ur Rahman Hashem Alyami Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method Journal of Healthcare Engineering |
author_facet |
Abdullah Alharbi Kamran Equbal Sultan Ahmad Haseeb Ur Rahman Hashem Alyami |
author_sort |
Abdullah Alharbi |
title |
Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method |
title_short |
Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method |
title_full |
Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method |
title_fullStr |
Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method |
title_full_unstemmed |
Human Gait Analysis and Prediction Using the Levenberg-Marquardt Method |
title_sort |
human gait analysis and prediction using the levenberg-marquardt method |
publisher |
Hindawi Limited |
series |
Journal of Healthcare Engineering |
issn |
2040-2309 |
publishDate |
2021-01-01 |
description |
A high-accuracy gait data prediction model can be used to design prosthesis and orthosis for people having amputations or ailments of the lower limb. The objective of this study is to observe the gait data of different subjects and design a neural network to predict future gait angles for fixed speeds. The data were recorded via a Biometrics goniometer, while the subjects were walking on a treadmill for 20 seconds each at 2.4 kmph, 3.6 kmph, and 5.4 kmph. The data were then imported into Matlab, filtered to remove movement artifacts, and then used to design a neural network with 60% data for training, 20% for validation, and remaining 20% for testing using the LevenbergMarquardt method. The mean-squared error for all the cases was in the order of 10−3 or lower confirming that our method is correct. For further comparison, we randomly tested the neural network function with untrained data and compared the expected output with actual output of the neural network function using Pearson’s correlation coefficient and correlation plots. We conclude that our framework can be successfully used to design prosthesis and orthosis for lower limb. It can also be used to validate gait data and compare it to expected data in rehabilitation engineering. |
url |
http://dx.doi.org/10.1155/2021/5541255 |
work_keys_str_mv |
AT abdullahalharbi humangaitanalysisandpredictionusingthelevenbergmarquardtmethod AT kamranequbal humangaitanalysisandpredictionusingthelevenbergmarquardtmethod AT sultanahmad humangaitanalysisandpredictionusingthelevenbergmarquardtmethod AT haseeburrahman humangaitanalysisandpredictionusingthelevenbergmarquardtmethod AT hashemalyami humangaitanalysisandpredictionusingthelevenbergmarquardtmethod |
_version_ |
1714842444250480640 |