Classification of runners' performance levels with concurrent prediction of biomechanical parameters using data from inertial measurement units
| Autor: | Vincent C. K. Cheung, Roy T.H. Cheung, Rosa H. M. Chan, Shuotong Wang, Ben M. F. Cheung, Shiwei Mo, Peter P.K. Chan, Qi Liu, Akash Malhotra |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Gradient boosting decision tree
Inertial frame of reference Computer science 0206 medical engineering Biomedical Engineering Biophysics 02 engineering and technology Convolutional neural network Running Machine Learning 03 medical and health sciences Units of measurement 0302 clinical medicine Inertial measurement unit Humans Orthopedics and Sports Medicine business.industry Rehabilitation Pattern recognition 020601 biomedical engineering Biomechanical Phenomena Multilayer perceptron Artificial intelligence Neural Networks Computer Performance enhancement business 030217 neurology & neurosurgery |
| Zdroj: | Journal of biomechanics. 112 |
| ISSN: | 1873-2380 |
| Popis: | Identification of runner’s performance level is critical to coaching, performance enhancement and injury prevention. Machine learning techniques have been developed to measure biomechanical parameters with body-worn inertial measurement unit (IMU) sensors. However, a robust method to classify runners is still unavailable. In this paper, we developed two models to classify running performance and predict biomechanical parameters of 30 subjects. We named the models RunNet-CNN and RunNet-MLP based on their architectures: convolutional neural network (CNN) and multilayer perceptron (MLP), respectively. In addition, we examined two validation approaches, subject-wise (leave-one-subject-out) and record-wise. RunNet-MLP classified runner’s performance levels with an overall accuracy of 97.1%. Our results also showed that RunNet-CNN outperformed RunNet-MLP and gradient boosting decision tree in predicting biomechanical parameters. RunNet-CNN showed good agreement (R2 > 0.9) with the ground-truth reference on biomechanical parameters. The prediction accuracy for the record-wise method was better than the subject-wise method regardless of biomechanical parameters or models. Our findings showed the viability of using IMUs to produce reliable prediction of runners’ performance levels and biomechanical parameters. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect