Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics
Efficient, adaptive, locomotor function is critically important for maintaining our health and independence, but falls-related injuries when walking are a significant risk factor, particularly for more vulnerable populations such as older people and post-stroke individuals. Tripping is the leading c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/18/6960 |
| _version_ | 1797482568842477568 |
|---|---|
| author | Clement Ogugua Asogwa Hanatsu Nagano Kai Wang Rezaul Begg |
| author_facet | Clement Ogugua Asogwa Hanatsu Nagano Kai Wang Rezaul Begg |
| author_sort | Clement Ogugua Asogwa |
| collection | DOAJ |
| description | Efficient, adaptive, locomotor function is critically important for maintaining our health and independence, but falls-related injuries when walking are a significant risk factor, particularly for more vulnerable populations such as older people and post-stroke individuals. Tripping is the leading cause of falls, and the swing-phase event Minimum Foot Clearance (MFC) is recognised as the key biomechanical determinant of tripping probability. MFC is defined as the minimum swing foot clearance, which is seen approximately mid-swing, and it is routinely measured in gait biomechanics laboratories using precise, high-speed, camera-based 3D motion capture systems. For practical intervention strategies designed to predict, and possibly assist, swing foot trajectory to prevent tripping, identification of the MFC event is essential; however, no technique is currently available to determine MFC timing in real-life settings outside the laboratory. One strategy has been to use wearable sensors, such as Inertial Measurement Units (IMUs), but these data are limited to primarily providing only tri-axial linear acceleration and angular velocity. The aim of this study was to develop Machine Learning (ML) algorithms to predict MFC timing based on the preceding toe-off gait event. The ML algorithms were trained using 13 young adults’ foot trajectory data recorded from an Optotrak 3D motion capture system. A Deep Learning configuration was developed based on a Recurrent Neural Network with a Long Short-Term Memory (LSTM) architecture and Huber loss-functions to minimise MFC-timing prediction error. We succeeded in predicting MFC timing from toe-off characteristics with a mean absolute error of 0.07 s. Although further algorithm training using population-specific inputs are needed. The ML algorithms designed here can be used for real-time actuation of wearable active devices to increase foot clearance at critical MFC and reduce devastating tripping falls. Further developments in ML-guided actuation for active exoskeletons could prove highly effective in developing technologies to reduce tripping-related falls across a range of gait impaired populations. |
| first_indexed | 2024-03-09T22:34:17Z |
| format | Article |
| id | doaj.art-e2328b415cc549f9a4859559ef2a496c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:34:17Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e2328b415cc549f9a4859559ef2a496c2023-11-23T18:52:09ZengMDPI AGSensors1424-82202022-09-012218696010.3390/s22186960Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off KinematicsClement Ogugua Asogwa0Hanatsu Nagano1Kai Wang2Rezaul Begg3Institute for Health and Sport (IHES), Victoria University, Melbourne, VIC 8001, AustraliaInstitute for Health and Sport (IHES), Victoria University, Melbourne, VIC 8001, AustraliaUniversity of Tsukuba, Tsukuba 305-8577, JapanInstitute for Health and Sport (IHES), Victoria University, Melbourne, VIC 8001, AustraliaEfficient, adaptive, locomotor function is critically important for maintaining our health and independence, but falls-related injuries when walking are a significant risk factor, particularly for more vulnerable populations such as older people and post-stroke individuals. Tripping is the leading cause of falls, and the swing-phase event Minimum Foot Clearance (MFC) is recognised as the key biomechanical determinant of tripping probability. MFC is defined as the minimum swing foot clearance, which is seen approximately mid-swing, and it is routinely measured in gait biomechanics laboratories using precise, high-speed, camera-based 3D motion capture systems. For practical intervention strategies designed to predict, and possibly assist, swing foot trajectory to prevent tripping, identification of the MFC event is essential; however, no technique is currently available to determine MFC timing in real-life settings outside the laboratory. One strategy has been to use wearable sensors, such as Inertial Measurement Units (IMUs), but these data are limited to primarily providing only tri-axial linear acceleration and angular velocity. The aim of this study was to develop Machine Learning (ML) algorithms to predict MFC timing based on the preceding toe-off gait event. The ML algorithms were trained using 13 young adults’ foot trajectory data recorded from an Optotrak 3D motion capture system. A Deep Learning configuration was developed based on a Recurrent Neural Network with a Long Short-Term Memory (LSTM) architecture and Huber loss-functions to minimise MFC-timing prediction error. We succeeded in predicting MFC timing from toe-off characteristics with a mean absolute error of 0.07 s. Although further algorithm training using population-specific inputs are needed. The ML algorithms designed here can be used for real-time actuation of wearable active devices to increase foot clearance at critical MFC and reduce devastating tripping falls. Further developments in ML-guided actuation for active exoskeletons could prove highly effective in developing technologies to reduce tripping-related falls across a range of gait impaired populations.https://www.mdpi.com/1424-8220/22/18/6960minimum foot clearancetripping preventionfalls preventiondeep learningmachine learninggait biomechanics |
| spellingShingle | Clement Ogugua Asogwa Hanatsu Nagano Kai Wang Rezaul Begg Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics Sensors minimum foot clearance tripping prevention falls prevention deep learning machine learning gait biomechanics |
| title | Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics |
| title_full | Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics |
| title_fullStr | Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics |
| title_full_unstemmed | Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics |
| title_short | Using Deep Learning to Predict Minimum Foot–Ground Clearance Event from Toe-Off Kinematics |
| title_sort | using deep learning to predict minimum foot ground clearance event from toe off kinematics |
| topic | minimum foot clearance tripping prevention falls prevention deep learning machine learning gait biomechanics |
| url | https://www.mdpi.com/1424-8220/22/18/6960 |
| work_keys_str_mv | AT clementoguguaasogwa usingdeeplearningtopredictminimumfootgroundclearanceeventfromtoeoffkinematics AT hanatsunagano usingdeeplearningtopredictminimumfootgroundclearanceeventfromtoeoffkinematics AT kaiwang usingdeeplearningtopredictminimumfootgroundclearanceeventfromtoeoffkinematics AT rezaulbegg usingdeeplearningtopredictminimumfootgroundclearanceeventfromtoeoffkinematics |