Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models
Gait analysis has been studied over the last few decades as the best way to objectively assess the technical outcome of a procedure designed to improve gait. The treating physician can understand the type of gait problem, gain insight into the etiology, and find the best treatment with gait analysis...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/3/734 |
| _version_ | 1797318256208379904 |
|---|---|
| author | Shing-Hong Liu Chi-En Ting Jia-Jung Wang Chun-Ju Chang Wenxi Chen Alok Kumar Sharma |
| author_facet | Shing-Hong Liu Chi-En Ting Jia-Jung Wang Chun-Ju Chang Wenxi Chen Alok Kumar Sharma |
| author_sort | Shing-Hong Liu |
| collection | DOAJ |
| description | Gait analysis has been studied over the last few decades as the best way to objectively assess the technical outcome of a procedure designed to improve gait. The treating physician can understand the type of gait problem, gain insight into the etiology, and find the best treatment with gait analysis. The gait parameters are the kinematics, including the temporal and spatial parameters, and lack the activity information of skeletal muscles. Thus, the gait analysis measures not only the three-dimensional temporal and spatial graphs of kinematics but also the surface electromyograms (sEMGs) of the lower limbs. Now, the shoe-worn GaitUp Physilog<sup>®</sup> wearable inertial sensors can easily measure the gait parameters when subjects are walking on the general ground. However, it cannot measure muscle activity. The aim of this study is to measure the gait parameters using the sEMGs of the lower limbs. A self-made wireless device was used to measure the sEMGs from the vastus lateralis and gastrocnemius muscles of the left and right feet. Twenty young female subjects with a skeletal muscle index (SMI) below 5.7 kg/m<sup>2</sup> were recruited for this study and examined by the InBody 270 instrument. Four parameters of sEMG were used to estimate 23 gait parameters. They were measured using the GaitUp Physilog<sup>®</sup> wearable inertial sensors with three machine learning models, including random forest (RF), decision tree (DT), and XGBoost. The results show that 14 gait parameters could be well-estimated, and their correlation coefficients are above 0.800. This study signifies a step towards a more comprehensive analysis of gait with only sEMGs. |
| first_indexed | 2024-03-08T03:49:48Z |
| format | Article |
| id | doaj.art-67c3a79c5e6d44a28cb5fba43bfa349b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T03:49:48Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-67c3a79c5e6d44a28cb5fba43bfa349b2024-02-09T15:21:40ZengMDPI AGSensors1424-82202024-01-0124373410.3390/s24030734Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning ModelsShing-Hong Liu0Chi-En Ting1Jia-Jung Wang2Chun-Ju Chang3Wenxi Chen4Alok Kumar Sharma5Department of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung City 41349, TaiwanDepartment of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung City 41349, TaiwanDepartment of Biomedical Engineering, I-Shou University, Kaohsiung 82445, TaiwanDepartment of Golden-Ager Industry Management, Chaoyang University of Technology, Taichung City 41349, TaiwanDivision of Information Systems, School of Computer Science and Engineering, The University of Aizu, Aizu-Wakamatsu City 965-8580, Fukushima, JapanDepartment of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung City 41349, TaiwanGait analysis has been studied over the last few decades as the best way to objectively assess the technical outcome of a procedure designed to improve gait. The treating physician can understand the type of gait problem, gain insight into the etiology, and find the best treatment with gait analysis. The gait parameters are the kinematics, including the temporal and spatial parameters, and lack the activity information of skeletal muscles. Thus, the gait analysis measures not only the three-dimensional temporal and spatial graphs of kinematics but also the surface electromyograms (sEMGs) of the lower limbs. Now, the shoe-worn GaitUp Physilog<sup>®</sup> wearable inertial sensors can easily measure the gait parameters when subjects are walking on the general ground. However, it cannot measure muscle activity. The aim of this study is to measure the gait parameters using the sEMGs of the lower limbs. A self-made wireless device was used to measure the sEMGs from the vastus lateralis and gastrocnemius muscles of the left and right feet. Twenty young female subjects with a skeletal muscle index (SMI) below 5.7 kg/m<sup>2</sup> were recruited for this study and examined by the InBody 270 instrument. Four parameters of sEMG were used to estimate 23 gait parameters. They were measured using the GaitUp Physilog<sup>®</sup> wearable inertial sensors with three machine learning models, including random forest (RF), decision tree (DT), and XGBoost. The results show that 14 gait parameters could be well-estimated, and their correlation coefficients are above 0.800. This study signifies a step towards a more comprehensive analysis of gait with only sEMGs.https://www.mdpi.com/1424-8220/24/3/734surface electromyogramgait parametersmachine learningdecision treerandom forestXGBoost |
| spellingShingle | Shing-Hong Liu Chi-En Ting Jia-Jung Wang Chun-Ju Chang Wenxi Chen Alok Kumar Sharma Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models Sensors surface electromyogram gait parameters machine learning decision tree random forest XGBoost |
| title | Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models |
| title_full | Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models |
| title_fullStr | Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models |
| title_full_unstemmed | Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models |
| title_short | Estimation of Gait Parameters for Adults with Surface Electromyogram Based on Machine Learning Models |
| title_sort | estimation of gait parameters for adults with surface electromyogram based on machine learning models |
| topic | surface electromyogram gait parameters machine learning decision tree random forest XGBoost |
| url | https://www.mdpi.com/1424-8220/24/3/734 |
| work_keys_str_mv | AT shinghongliu estimationofgaitparametersforadultswithsurfaceelectromyogrambasedonmachinelearningmodels AT chienting estimationofgaitparametersforadultswithsurfaceelectromyogrambasedonmachinelearningmodels AT jiajungwang estimationofgaitparametersforadultswithsurfaceelectromyogrambasedonmachinelearningmodels AT chunjuchang estimationofgaitparametersforadultswithsurfaceelectromyogrambasedonmachinelearningmodels AT wenxichen estimationofgaitparametersforadultswithsurfaceelectromyogrambasedonmachinelearningmodels AT alokkumarsharma estimationofgaitparametersforadultswithsurfaceelectromyogrambasedonmachinelearningmodels |