Load distribution model underlying the publication: Towards an accurate rolling resistance: Estimating intra-cycle load distribution between front- and rear wheels during wheelchair propulsion

Based on the 'dataset of the front-wheel load of a set of wheelchair propulsion experiments' in https://doi.org/10.4121/bc9a8588-5e50-4dff-aa77-5114ff7626f7, a machine learning model is trained. The model, and the python-code to run the model on acquired kinematic data, is attached.<br>Wheelchair propulsion experiments were executed on a treadmill. During the treadmill sessions, front wheel load was assessed with load pins to determine the load distribution between the front and rear wheels. Accordingly, a machine learning model was trained to predict load distribution from kinematic data of the wheelchair and trunk. Input of the model was data of two inertial sensors (one attached to the trunk and one attached to the wheelchair) and output of the model was the relative front wheel load (or 'The load on the front wheels is expressed as percentage of the total weight (of wheelchair user/athlete + wheelchair)'.

本研究基于DOI为10.4121/bc9a8588-5e50-4dff-aa77-5114ff7626f7的「轮椅推进实验前轮载荷数据集」训练了一款机器学习模型，并附带该模型与可在采集得到的运动学数据上运行该模型的Python代码。<br>本研究在跑台上开展轮椅推进实验，实验过程中通过测力销（load pins）采集前轮载荷数据，以确定轮椅前后轮之间的载荷分布。据此，本研究训练了一款机器学习模型，可从轮椅与躯干的运动学数据中预测载荷分布：该模型的输入为两套惯性传感器（inertial sensors）的数据（一套安装于躯干，另一套安装于轮椅），输出为相对前轮载荷，即「前轮载荷占轮椅使用者/运动员与轮椅总重量的百分比」。