Predicting gait events from tibial acceleration in rearfoot running: A structured machine learning approach |
| |
| Institution: | 1. Department of Computer Science, KU Leuven, Celestijnenlaan 200A Box 2402, 3001, Heverlee, Belgium;2. Department of Movement and Sports Sciences, Ghent University, Watersportlaan 2, 9000, Gent, Belgium;1. School of Exercise Science, Australian Catholic University, Australia;2. Centre for Musculoskeletal Research, Mary MacKillop Institute for Health Research, Australian Catholic University, Australia;1. Institute for Applied Training Science (IAT), Leipzig, Germany;2. Hochschule Koblenz, University of Applied Science, Koblenz, Remagen, Höhr-Grenzhausen, Germany;3. German Athletics Association, Dortmund, Leipzig, Darmstadt, Germany;4. Department of Movement and Training Science, University of Wuppertal, Wuppertal, Germany;5. Department of Orthopaedics, Trauma, Hand and Neuro Surgery, Klinikum Osnabrück, Osnabrück, Germany;1. Institute of Industrial Science, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo, 153-8505, Japan;2. Biomedical Engineering Department, Al-Khwarizmi College of Engineering, University of Baghdad, Jaderyia, 10072, Baghdad, Iraq;3. Experimental Mechanics Laboratory Mechanical Engineering Department, San Diego State University, 5500 Campanile Drive, San Diego, CA, 92182-1323, United States;1. Australian Institute of Sport, Discipline of Physical Therapies, Australia;2. Australian Institute of Sport, Discipline of Movement Science, Australia;3. Australian Institute of Sport, Discipline of Performance Research, Australia;4. University of Canberra, Discipline of Physiotherapy, University Drive, Australia;5. University of Canberra, Research Institute for Sport and Exercise, University Drive, Australia;6. Federation University, Australian Centre for Research in Sports Prevention, Australia;7. Geelong Cats Football Club, Department of Physiotherapy and Medicine, Kardinia Park, Australia;1. University of Calgary, Faculty of Kinesiology, 2500 University Dr. NW, Calgary, AB T2N 1N4, Canada;2. Running Injury Clinic, Calgary, AB T2N 1N4, Canada;3. University of Calgary, Faculty of Nursing, 2500 University Dr. NW, Calgary, AB T2N 1N4, Canada |
| |
| Abstract: | BackgroundGait event detection of the initial contact and toe off is essential for running gait analysis, allowing the derivation of parameters such as stance time. Heuristic-based methods exist to estimate these key gait events from tibial accelerometry. However, these methods are tailored to very specific acceleration profiles, which may offer complications when dealing with larger data sets and inherent biological variability.Research questionCan a structured machine learning approach achieve a more accurate prediction of running gait event timings from tibial accelerometry, compared to the previously utilised heuristic approaches?MethodsForce-based event detection acted as the criterion measure in order to assess the accuracy, repeatability and sensitivity of the predicted gait events. 3D tibial acceleration and ground reaction force data from 93 rearfoot runners were captured. A heuristic method and two structured machine learning methods were employed to derive initial contact, toe off and stance time from tibial acceleration signals.ResultsBoth a structured perceptron model (median absolute error of stance time estimation: 10.00 ± 8.73 ms) and a structured recurrent neural network model (median absolute error of stance time estimation: 6.50 ± 5.74 ms) significantly outperformed the existing heuristic approach (median absolute error of stance time estimation: 11.25 ± 9.52 ms). Thus, results indicate that a structured recurrent neural network machine learning model offers the most accurate and consistent estimation of the gait events and its derived stance time during level overground running.SignificanceThe machine learning methods seem less affected by intra- and inter-subject variation within the data, allowing for accurate and efficient automated data output during rearfoot overground running. Furthermore offering possibilities for real-time monitoring and biofeedback during prolonged measurements, even outside the laboratory. |
| |
| Keywords: | Running Gait event detection Machine learning Structured prediction |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
