Self-expressive subspace clustering to recognize motion dynamics for chronic ankle instability

GaitNet+ARL: A Deep Learning Algorithm for Interpretable Gait Analysis of Chronic Ankle Instability

Chronic ankle instability (CAI) is a major public health concern and adversely affects people's mobility and quality of life. Traditional assessment methods are subjective and qualitative by means of clinician observation and patient self-reporting, which may lead to inaccurate assessment and reduce the effectiveness of treatment in clinical practice. Gait analysis becomes a commonly used approach for monitoring human motion behaviors, which can be applied to specific diagnosis and assessment of CAI. However, it is still challenging to recognize the pathological gait pattern for CAI subjects. In this paper, we propose an integrated deep learning framework to solve the CAI recognition problem using kinematic data. Specifically, inspired by the biomechanics of human body system, we create a simple graph neural network (GNN), termed GaitNet, that operates on a spatial domain and exploits interactions among 3-D joint coordinates. We also develop an attention reinforcement learning (ARL) model that determines attention weights of frames on a temporal domain, which is combined with GaitNet for prediction. The effectiveness of our method is validated on the kinematic NEU-CAI dataset which is collected in our institution using a stereophotogrammetric system. According to extensive experiments, we demonstrate that the selected key phases (i.e., sequences of frames with high attentions) significantly increase the predictability of the proposed biomechanics-based GNN model to differentiate between CAI cohort and control cohort. Moreover, we show a significant prediction accuracy improvement (20%-25%) by our approach compared to state-of-the-art machine learning and deep learning methods.

Effect of legroom proportions and individual factors for sitting with crossed legs: implications on the interior design of automated driving vehicles

Sitting with crossed legs is a commonly adopted sitting posture in everyday situations. Yet, little is known about suitable design criteria to facilitate such a position inside a vehicle. This study is aimed at determining how much space is necessary for crossing the legs while considering legroom restrictions, anthropometric measures, and individual flexibility. More specifically, 3 D-kinematics of an ankle-on-knee leg-crossing task and the easiness to move ratings of 30 participants were assessed with restrictions of the legroom (2 heights × 3 distances) as well as without restrictions. Functional regression models revealed adaptations to a legroom restriction in the execution of movement, which occurred mainly in the knee joint and increased with more restricted legroom proportions. Therefore, the present study suggests a distance of 120% of the buttock-knee length between the dashboard and the occupant, as it requires only moderate adaptations and does not affect the perceived easiness of move. Practitioner Summary: This research investigated how much space is needed to cross the legs while sitting in a vehicle, finding that the movement execution is affected by legroom proportions, as well as individual anthropometry and flexibility. The study further presents the use of predicted motion traces to determine spatial requirements of movements. Abbreviations: BKL: buttock-knee length; H-point: hip point.