Search

Ground reaction force and moment (GRF&M) measurements are vital for biomechanical analysis and significantly impact the clinical domain for early abnormality detection for different neurodegenerative diseases. Force platforms have become the de facto standard for measuring GRF&M signals in recent years. Although the signal quality achieved from these devices is unparalleled, they are expensive and require laboratory setup, making them unsuitable for many clinical applications. For these reasons, predicting GRF&M from cheaper and more feasible alternatives has become a topic of interest. Several works have been done on predicting GRF&M from kinematic data captured from the subject's body with the help of motion capture cameras. The problem with these solutions is that they rely on markers placed on the whole body to capture the movements, which can be very infeasible in many practical scenarios. This paper proposes a novel deep learning-based approach to predict 3D GRF&M from only 5 markers placed on the shoe. The proposed network "Attention Guided MultiResUNet" can predict the force and moment signals accurately and reliably compared to the techniques relying on full-body markers. The proposed deep learning model is tested on two publicly available datasets containing data from 66 healthy subjects to validate the approach. The framework has achieved an average correlation coefficient of 0.96 for 3D ground reaction force prediction and 0.86 for 3D ground reaction momentum prediction in cross-dataset validation. The framework can provide a cheaper and more feasible alternative for predicting GRF&M in many practical applications. [ABSTRACT FROM AUTHOR]

Neurodegenerative diseases damage neuromuscular tissues and deteriorate motor neurons which affects the motor capacity of the patient. Particularly the walking gait is greatly influenced by the deterioration process. Early detection of anomalous gait patterns caused by neurodegenerative diseases can help the patient to prevent associated risks. Previous studies in this domain relied on either features extracted from gait parameters or the Ground Reaction Force (GRF) signal. In this work, we aim to combine both GRF signals and extracted features to provide a better analysis of walking gait patterns. For this, we designed NDDNet, a novel neural network architecture to process both of these data simultaneously to detect 3 different Neurodegenerative Diseases (NDDs). We have done several experiments on the data collected from 64 participants and got 96.75% accuracy on average in detecting 3 types of NDDs. The proposed method might provide a way to get the most out of the data in hand while working with GRF signals and help diagnose patients with an anomalous gait more effectively. [ABSTRACT FROM AUTHOR]