Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor
Wearable sensors facilitate running kinematics analysis of joint kinematics in real running environments. The use of a few sensors or, ideally, a single inertial measurement unit (IMU) is preferable for accurate gait analysis. This study aimed to use a convolutional neural network (CNN) to predict l...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4633 |
| _version_ | 1797526147221684224 |
|---|---|
| author | Daniel Hung Kay Chow Luc Tremblay Chor Yin Lam Adrian Wai Yin Yeung Wilson Ho Wu Cheng Peter Tin Wah Tse |
| author_facet | Daniel Hung Kay Chow Luc Tremblay Chor Yin Lam Adrian Wai Yin Yeung Wilson Ho Wu Cheng Peter Tin Wah Tse |
| author_sort | Daniel Hung Kay Chow |
| collection | DOAJ |
| description | Wearable sensors facilitate running kinematics analysis of joint kinematics in real running environments. The use of a few sensors or, ideally, a single inertial measurement unit (IMU) is preferable for accurate gait analysis. This study aimed to use a convolutional neural network (CNN) to predict level-ground running kinematics (measured by four IMUs on the lower extremities) by using treadmill running kinematics training data measured using a single IMU on the anteromedial side of the right tibia and to compare the performance of level-ground running kinematics predictions between raw accelerometer and gyroscope data. The CNN model performed regression for intraparticipant and interparticipant scenarios and predicted running kinematics. Ten recreational runners were recruited. Accelerometer and gyroscope data were collected. Intraparticipant and interparticipant R<sup>2</sup> values of actual and predicted running kinematics ranged from 0.85 to 0.96 and from 0.7 to 0.92, respectively. Normalized root mean squared error values of actual and predicted running kinematics ranged from 3.6% to 10.8% and from 7.4% to 10.8% in intraparticipant and interparticipant tests, respectively. Kinematics predictions in the sagittal plane were found to be better for the knee joint than for the hip joint, and predictions using the gyroscope as the regressor were demonstrated to be significantly better than those using the accelerometer as the regressor. |
| first_indexed | 2024-03-10T09:25:05Z |
| format | Article |
| id | doaj.art-ccd475acf60444b1b4b34d59f8c2a517 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:25:05Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ccd475acf60444b1b4b34d59f8c2a5172023-11-22T04:53:47ZengMDPI AGSensors1424-82202021-07-012114463310.3390/s21144633Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable SensorDaniel Hung Kay Chow0Luc Tremblay1Chor Yin Lam2Adrian Wai Yin Yeung3Wilson Ho Wu Cheng4Peter Tin Wah Tse5Department of Health & Physical Education, The Education University of Hong Kong, Hong Kong, ChinaFaculty of Kinesiology & Physical Education, University of Toronto, Toronto, ON M5S 2W6, CanadaDepartment of Orthopaedics & Traumatology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Health & Physical Education, The Education University of Hong Kong, Hong Kong, ChinaDepartment of Health & Physical Education, The Education University of Hong Kong, Hong Kong, ChinaDepartment of Health & Physical Education, The Education University of Hong Kong, Hong Kong, ChinaWearable sensors facilitate running kinematics analysis of joint kinematics in real running environments. The use of a few sensors or, ideally, a single inertial measurement unit (IMU) is preferable for accurate gait analysis. This study aimed to use a convolutional neural network (CNN) to predict level-ground running kinematics (measured by four IMUs on the lower extremities) by using treadmill running kinematics training data measured using a single IMU on the anteromedial side of the right tibia and to compare the performance of level-ground running kinematics predictions between raw accelerometer and gyroscope data. The CNN model performed regression for intraparticipant and interparticipant scenarios and predicted running kinematics. Ten recreational runners were recruited. Accelerometer and gyroscope data were collected. Intraparticipant and interparticipant R<sup>2</sup> values of actual and predicted running kinematics ranged from 0.85 to 0.96 and from 0.7 to 0.92, respectively. Normalized root mean squared error values of actual and predicted running kinematics ranged from 3.6% to 10.8% and from 7.4% to 10.8% in intraparticipant and interparticipant tests, respectively. Kinematics predictions in the sagittal plane were found to be better for the knee joint than for the hip joint, and predictions using the gyroscope as the regressor were demonstrated to be significantly better than those using the accelerometer as the regressor.https://www.mdpi.com/1424-8220/21/14/4633deep learningconvolutional neural networkrunningkinematicswearable sensorrunning kinematics analysis |
| spellingShingle | Daniel Hung Kay Chow Luc Tremblay Chor Yin Lam Adrian Wai Yin Yeung Wilson Ho Wu Cheng Peter Tin Wah Tse Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor Sensors deep learning convolutional neural network running kinematics wearable sensor running kinematics analysis |
| title | Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor |
| title_full | Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor |
| title_fullStr | Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor |
| title_full_unstemmed | Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor |
| title_short | Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor |
| title_sort | comparison between accelerometer and gyroscope in predicting level ground running kinematics by treadmill running kinematics using a single wearable sensor |
| topic | deep learning convolutional neural network running kinematics wearable sensor running kinematics analysis |
| url | https://www.mdpi.com/1424-8220/21/14/4633 |
| work_keys_str_mv | AT danielhungkaychow comparisonbetweenaccelerometerandgyroscopeinpredictinglevelgroundrunningkinematicsbytreadmillrunningkinematicsusingasinglewearablesensor AT luctremblay comparisonbetweenaccelerometerandgyroscopeinpredictinglevelgroundrunningkinematicsbytreadmillrunningkinematicsusingasinglewearablesensor AT choryinlam comparisonbetweenaccelerometerandgyroscopeinpredictinglevelgroundrunningkinematicsbytreadmillrunningkinematicsusingasinglewearablesensor AT adrianwaiyinyeung comparisonbetweenaccelerometerandgyroscopeinpredictinglevelgroundrunningkinematicsbytreadmillrunningkinematicsusingasinglewearablesensor AT wilsonhowucheng comparisonbetweenaccelerometerandgyroscopeinpredictinglevelgroundrunningkinematicsbytreadmillrunningkinematicsusingasinglewearablesensor AT petertinwahtse comparisonbetweenaccelerometerandgyroscopeinpredictinglevelgroundrunningkinematicsbytreadmillrunningkinematicsusingasinglewearablesensor |