Abstract

Gait is a key health metric, sometimes described as the sixth vital sign. Temporal, spatial and kinetic gait parameters are valuable in enhancing sport performance and early health diagnostics of health conditions such as Parkinson’s disease. Full gait assessment requires a gait clinic and existing wearable gait tracking systems typically measure isolated subsets of parameters tailored to specific applications. This is useful when the condition to be monitored is known but fails to offer a comprehensive view of an individual’s gait traits when their pathology is unknown or changing, or a general assessment is required. To support holistic walking gait tracking, we introduce WalkEar a sensing platform designed to simultaneously track a set of walking gait parameters using commodity ear-worn wearables. WalkEar operates by detecting gait events using them to derive temporal gait parameters and segment the IMU data. We then use regression techniques to predict kinetic gait parameters and estimate the full vertical reaction force. Each parameter is calculated on a step-to-step basis to enable assessment of gait variability and asymmetry. We developed an earbud prototype and collected data from 30 subjects using gold standard force plates and instrumented treadmill ground truth. Experiments show strong agreement between our system and the ground truth showing the promise of using ubiquitous earbuds for continuous gait monitoring.