Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors
Background: In this study, an automatic scoring system for the functional movement screen (FMS) was developed. Methods: Thirty healthy adults fitted with full-body inertial measurement unit sensors completed six FMS exercises. The system recorded kinematics data, and a professional athletic trainer...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/1/96 |
id |
doaj-be8492885b8744078ea1fd820240a705 |
---|---|
record_format |
Article |
spelling |
doaj-be8492885b8744078ea1fd820240a7052020-12-25T00:03:09ZengMDPI AGApplied Sciences2076-34172021-12-0111969610.3390/app11010096Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit SensorsWen-Lan Wu0Meng-Hua Lee1Hsiu-Tao Hsu2Wen-Hsien Ho3Jing-Min Liang4Department of Sports Medicine, Kaohsiung Medical University, Kaohsiung 80708, TaiwanDepartment of Sports Medicine, Kaohsiung Medical University, Kaohsiung 80708, TaiwanCenter for Physical and Health Education, National Sun Yat-Sen University, Kaohsiung 80424, TaiwanDepartment of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung 80708, TaiwanDepartment of Sports Medicine, Kaohsiung Medical University, Kaohsiung 80708, TaiwanBackground: In this study, an automatic scoring system for the functional movement screen (FMS) was developed. Methods: Thirty healthy adults fitted with full-body inertial measurement unit sensors completed six FMS exercises. The system recorded kinematics data, and a professional athletic trainer graded each participant. To reduce the number of input variables for the predictive model, ordinal logistic regression was used for subset feature selection. The ensemble learning algorithm AdaBoost.M1 was used to construct classifiers. Accuracy and F score were used for classification model evaluation. The consistency between automatic and manual scoring was assessed using a weighted kappa statistic. Results: When all the features were used, the predict model presented moderate to high accuracy, with kappa values between fair to very good agreement. After feature selection, model accuracy decreased about 10%, with kappa values between poor to moderate agreement. Conclusions: The results indicate that higher prediction accuracy was achieved using the full feature set compared with using the reduced feature set.https://www.mdpi.com/2076-3417/11/1/96FMSIMU sensormachine learningordinal logistic regressionconfusion matrixkappa |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wen-Lan Wu Meng-Hua Lee Hsiu-Tao Hsu Wen-Hsien Ho Jing-Min Liang |
spellingShingle |
Wen-Lan Wu Meng-Hua Lee Hsiu-Tao Hsu Wen-Hsien Ho Jing-Min Liang Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors Applied Sciences FMS IMU sensor machine learning ordinal logistic regression confusion matrix kappa |
author_facet |
Wen-Lan Wu Meng-Hua Lee Hsiu-Tao Hsu Wen-Hsien Ho Jing-Min Liang |
author_sort |
Wen-Lan Wu |
title |
Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors |
title_short |
Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors |
title_full |
Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors |
title_fullStr |
Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors |
title_full_unstemmed |
Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors |
title_sort |
development of an automatic functional movement screening system with inertial measurement unit sensors |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-12-01 |
description |
Background: In this study, an automatic scoring system for the functional movement screen (FMS) was developed. Methods: Thirty healthy adults fitted with full-body inertial measurement unit sensors completed six FMS exercises. The system recorded kinematics data, and a professional athletic trainer graded each participant. To reduce the number of input variables for the predictive model, ordinal logistic regression was used for subset feature selection. The ensemble learning algorithm AdaBoost.M1 was used to construct classifiers. Accuracy and F score were used for classification model evaluation. The consistency between automatic and manual scoring was assessed using a weighted kappa statistic. Results: When all the features were used, the predict model presented moderate to high accuracy, with kappa values between fair to very good agreement. After feature selection, model accuracy decreased about 10%, with kappa values between poor to moderate agreement. Conclusions: The results indicate that higher prediction accuracy was achieved using the full feature set compared with using the reduced feature set. |
topic |
FMS IMU sensor machine learning ordinal logistic regression confusion matrix kappa |
url |
https://www.mdpi.com/2076-3417/11/1/96 |
work_keys_str_mv |
AT wenlanwu developmentofanautomaticfunctionalmovementscreeningsystemwithinertialmeasurementunitsensors AT menghualee developmentofanautomaticfunctionalmovementscreeningsystemwithinertialmeasurementunitsensors AT hsiutaohsu developmentofanautomaticfunctionalmovementscreeningsystemwithinertialmeasurementunitsensors AT wenhsienho developmentofanautomaticfunctionalmovementscreeningsystemwithinertialmeasurementunitsensors AT jingminliang developmentofanautomaticfunctionalmovementscreeningsystemwithinertialmeasurementunitsensors |
_version_ |
1724371580523380736 |