In-home Health Monitoring using Floor-based Gait Tracking

Gait assessments are commonly used for clinical evaluations of neurocognitive disease progression and general wellness. However, gait measurements in clinical settings do not accurately reflect gait in daily life. We present a non-wearable and unobtrusive method of detecting gait parameters in the home through the vibrations in the floor created by footfalls. Gait characteristics and gait asymmetry are estimated despite a low sensor density of 6.7 m(2)/sensor. Features from each footfall vibration signal is extracted and used to estimate gait parameters with gradient boosting regression and probabilistic models. Temporal gait asymmetry, locations of the footfalls, and peak tibial acceleration asymmetry can be predicted with a root mean square error of 0.013 s, 0.42 m, and 0.34 g respectively. This system allows for continuous at-home monitoring of gait which aids in early detection of gait anomalies.