Journal of biomechanics
-
Journal of biomechanics · Apr 2020
What is the best way to collect maximum forward lumbar spine flexion values for normalizing posture to range of motion?
Spine angles are an important measure in biomechanics research and are commonly normalized to a percentage of range of motion. However, standardized methods to collect the reference posture trials for this normalization do not exist. The purpose of this study was to determine posture (seated or standing) and number of trials that should be collected and how to calculate the angle that best represents the maximum range. ⋯ The maximum angle of all 10 flexion trials was significantly greater than the angle of the first standing or seated trial only but not significantly greater than the maximum of all seated or standing flexion trials respectively. Secondarily, no differences in the maximum lumbar angle were found between sexes. This study suggests that 6 flexion trials, involving both standing and seated flexion, should be collected to best represent the maximum end range of spine flexion.
-
Journal of biomechanics · Apr 2020
Adversarial autoencoder for visualization and classification of human activity: Application to a low-cost commercial force plate.
The ability to visualize and interpret high dimensional time-series data will be critical as wearable and other sensors are adopted in rehabilitation protocols. This study proposes a latent space representation of high dimensional time-series data for data visualization. For that purpose, a deep learning model called Adversarial AutoEncoder (AAE) is proposed to perform efficient data dimensionality reduction by considering unsupervised and semi-supervised adversarial training. ⋯ Data dimensionality reduction with conventional Machine Learning (ML) and supervised Deep Learning (DL) classification are also performed to compare the efficiency of AAE approaches. The results showed that AAE can outperform conventional ML approaches while providing close results to DL supervised classification. AAE approaches for data visualization are a promising approach to monitor the subject's movements and detect adverse events or similarity with previous data, providing an intuitive way to monitor the patient's progress and provide potential information for rehabilitation tracking.