Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System
Accurately measuring the lower extremities and L5/S1 moments is important since L5/S1 moments are the principal parameters that measure the risk of musculoskeletal diseases during lifting. In this study, protocol that predicts lower extremities and L5/S1 moments with an insole sensor was proposed to...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/24/11735 |
| _version_ | 1797506825134800896 |
|---|---|
| author | Seungheon Chae Ahnryul Choi Hyunwoo Jung Tae Hyong Kim Kyungran Kim Joung Hwan Mun |
| author_facet | Seungheon Chae Ahnryul Choi Hyunwoo Jung Tae Hyong Kim Kyungran Kim Joung Hwan Mun |
| author_sort | Seungheon Chae |
| collection | DOAJ |
| description | Accurately measuring the lower extremities and L5/S1 moments is important since L5/S1 moments are the principal parameters that measure the risk of musculoskeletal diseases during lifting. In this study, protocol that predicts lower extremities and L5/S1 moments with an insole sensor was proposed to replace the prior methods that have spatial constraints. The protocol is hierarchically composed of a classification model and a regression model to predict joint moments. Additionally, a single LSTM model was developed to compare with proposed protocol. To optimize hyperparameters of the machine learning model and input feature, Bayesian optimization method was adopted. As a result, the proposed protocol showed a relative root mean square error (rRMSE) of 8.06~13.88% while the single LSTM showed 9.30~18.66% rRMSE. This protocol in this research is expected to be a starting point for developing a system for estimating the lower extremity and L5/S1 moment during lifting that can replace the complex prior method and adopted to workplace environments. This novel study has the potential to precisely design a feedback iterative control system of an exoskeleton for the appropriate generation of an actuator torque. |
| first_indexed | 2024-03-10T04:37:58Z |
| format | Article |
| id | doaj.art-caeca0dff9d04c3fa64aae214d138f88 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:37:58Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-caeca0dff9d04c3fa64aae214d138f882023-11-23T03:37:31ZengMDPI AGApplied Sciences2076-34172021-12-0111241173510.3390/app112411735Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control SystemSeungheon Chae0Ahnryul Choi1Hyunwoo Jung2Tae Hyong Kim3Kyungran Kim4Joung Hwan Mun5Department of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, KoreaAgricultural Health and Safety Division, National Institute of Agricultural Sciences, Rural Development Administration, Jeonju 54875, KoreaDepartment of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, KoreaAccurately measuring the lower extremities and L5/S1 moments is important since L5/S1 moments are the principal parameters that measure the risk of musculoskeletal diseases during lifting. In this study, protocol that predicts lower extremities and L5/S1 moments with an insole sensor was proposed to replace the prior methods that have spatial constraints. The protocol is hierarchically composed of a classification model and a regression model to predict joint moments. Additionally, a single LSTM model was developed to compare with proposed protocol. To optimize hyperparameters of the machine learning model and input feature, Bayesian optimization method was adopted. As a result, the proposed protocol showed a relative root mean square error (rRMSE) of 8.06~13.88% while the single LSTM showed 9.30~18.66% rRMSE. This protocol in this research is expected to be a starting point for developing a system for estimating the lower extremity and L5/S1 moment during lifting that can replace the complex prior method and adopted to workplace environments. This novel study has the potential to precisely design a feedback iterative control system of an exoskeleton for the appropriate generation of an actuator torque.https://www.mdpi.com/2076-3417/11/24/11735human motion analysislifting taskmachine learninglower body joint momentwork-related musculoskeletal disordersinsole system |
| spellingShingle | Seungheon Chae Ahnryul Choi Hyunwoo Jung Tae Hyong Kim Kyungran Kim Joung Hwan Mun Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System Applied Sciences human motion analysis lifting task machine learning lower body joint moment work-related musculoskeletal disorders insole system |
| title | Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System |
| title_full | Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System |
| title_fullStr | Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System |
| title_full_unstemmed | Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System |
| title_short | Machine Learning Model to Estimate Net Joint Moments during Lifting Task Using Wearable Sensors: A Preliminary Study for Design of Exoskeleton Control System |
| title_sort | machine learning model to estimate net joint moments during lifting task using wearable sensors a preliminary study for design of exoskeleton control system |
| topic | human motion analysis lifting task machine learning lower body joint moment work-related musculoskeletal disorders insole system |
| url | https://www.mdpi.com/2076-3417/11/24/11735 |
| work_keys_str_mv | AT seungheonchae machinelearningmodeltoestimatenetjointmomentsduringliftingtaskusingwearablesensorsapreliminarystudyfordesignofexoskeletoncontrolsystem AT ahnryulchoi machinelearningmodeltoestimatenetjointmomentsduringliftingtaskusingwearablesensorsapreliminarystudyfordesignofexoskeletoncontrolsystem AT hyunwoojung machinelearningmodeltoestimatenetjointmomentsduringliftingtaskusingwearablesensorsapreliminarystudyfordesignofexoskeletoncontrolsystem AT taehyongkim machinelearningmodeltoestimatenetjointmomentsduringliftingtaskusingwearablesensorsapreliminarystudyfordesignofexoskeletoncontrolsystem AT kyungrankim machinelearningmodeltoestimatenetjointmomentsduringliftingtaskusingwearablesensorsapreliminarystudyfordesignofexoskeletoncontrolsystem AT jounghwanmun machinelearningmodeltoestimatenetjointmomentsduringliftingtaskusingwearablesensorsapreliminarystudyfordesignofexoskeletoncontrolsystem |