Gait analysis plays an important role in the fields of healthcare and sports sciences. Conventional gait analysis relies on costly equipment such as optical motion capture cameras and wearable sensors, some of which require trained assessors for data collection and processing. With the recent developments in computer vision and deep neural networks, using monocular RGB cameras for 3D human pose estimation has shown tremendous promise as a cost-effective and efficient solution for clinical gait analysis. In this paper, a markerless human pose technique is developed using motion captured by a consumer monocular camera (800 × 600 pixels and 30 FPS) for clinical gait analysis. The experimental results have shown that the proposed post-processing algorithm significantly improved the original human pose detection model (BlazePose)’s prediction performance compared to the gold-standard gait signals by 10.7% using the MoVi dataset. In addition, the predicted T² score has an excellent correlation with ground truth (r = 0.99 and y = 0.94x + 0.01 regression line), which supports that our approach can be a potential alternative to the conventional marker-based solution to assist the clinical gait assessment.

The application of machine learning-based tele-rehabilitation faces the challenge of limited availability of data. To overcome this challenge, data augmentation techniques are commonly employed to generate synthetic data that reflect the configurations of real data. One such promising data augmentation technique is the Generative Adversarial Network (GAN). However, GANs have been found to suffer from mode collapse, a common issue where the generated data fails to capture all the relevant information from the original dataset. In this paper, we aim to address the problem of mode collapse in GAN-based data augmentation techniques for post-stroke assessment. We applied the GAN to generate synthetic data for two post-stroke rehabilitation datasets and observed that the original GAN suffered from mode collapse, as expected. To address this issue, we propose a Time Series Siamese GAN (TS-SGAN) that incorporates a Siamese network and an additional discriminator. Our analysis, using the longest common sub-sequence (LCSS), demonstrates that TS-SGAN generates data uniformly for all elements of two testing datasets, in contrast to the original GAN. To further evaluate the effectiveness of TS-SGAN, we encode the generated dataset into images using Gramian Angular Field and classify them using ResNet-18. Our results show that TS-SGAN achieves a significant accuracy increase of classification accuracy (35.2%-42.07%) for both selected datasets. This represents a substantial improvement over the original GAN.

Knee joint moments are commonly calculated to provide an indirect measure of knee joint loads. A shortcoming of inverse dynamics approaches is that the process of collecting and processing human motion data can be time-consuming. This study aimed to benchmark five different deep learning methods in using walking segment kinematics for predicting internal knee abduction impulse during walking. Three-dimensional kinematic and kinetic data used for the present analyses came from a publicly available dataset on walking (participants n = 33). The outcome for prediction was the internal knee abduction impulse over the stance phase. Three-dimensional (3D) angular and linear displacement, velocity, and acceleration of the seven lower body segment’s center of mass (COM), relative to a fixed global coordinate system were derived and formed the predictor space (126 time-series predictors). The total number of observations in the dataset was 6,737. The datasets were split into training (75%, n = 5,052) and testing (25%, n = 1685) datasets. Five deep learning models were benchmarked against inverse dynamics in quantifying knee abduction impulse. A baseline 2D convolutional network model achieved a mean absolute percentage error (MAPE) of 10.80%. Transfer learning with InceptionTime was the best performing model, achieving the best MAPE of 8.28%. Encoding the time-series as images then using a 2D convolutional model performed worse than the baseline model with a MAPE of 16.17%. Time-series based deep learning models were superior to an image-based method when predicting knee abduction moment impulse during walking. Future studies looking to develop wearable technologies will benefit from knowing the optimal network architecture, and the benefit of transfer learning for predicting joint moments.

In healthcare applications, often it is not possible to record sufficient data as required for deep learning or data-driven classification and feature detection systems due to the patient condition, various clinical or experimental limitations, or time constraints. On the other hand, data imbalance invalidates many of the test results crucial for clinical approvals. Generating synthetic (artificial or dummy) data has become a potential solution to address this issue. Such data should possess adequate information, properties, and characteristics to mimic the real-world data recorded in natural circumstances. Several methods have been proposed for this purpose, and results often show that adding surrogates improves the decision-making accuracy. This article evaluates the most recent surrogate data generation and data synthesis methods to investigate the effects of the number of surrogates on improving the classification results. It is shown that the data analysis/classification results improve with an increasing number of surrogates, but this no longer continues after a certain number of surrogates. This achievement helps in deciding on the number of surrogates for each strategy, resulting in the alleviation of the computation cost.