NEST: A Novel Ensemble Method for Estimating Spatio-Temporal Gait Parameters Using Inertial Measurement Units

Accurately estimating spatio-temporal gait parameters such as stride height, stride length, stance time, swing time, and stride speed, is crucial for sports medicine and preventive healthcare. To enable users to measure their spatio-temporal gait parameters in real-life scenarios, several existing studies propose to install one inertial measurement unit (IMU) in each shoe, and design methods to estimate these gait parameters according to the readings of IMUs. Therefore, this paper proposes a novel ensemble method, NEST (standing for Novel Ensemble method for Spatio-Temporal gait parameters measurement), for the multi-task measurement of the aforementioned five spatio-temporal gait parameters. NEST consists of a K-Nearest Neighbor (KNN) regressor branch and a deep learning branch. The KNN regressor branch provides initial estimates, allowing other neural networks to learn to reduce the residual between these estimates and the ground truths. This helps NEST rapidly identify a good optimization direction during the early stage of fine-tuning and expedite convergence speed. The deep learning branch facilitates information sharing among multiple task-specific representations through fully-connected layers, effectively preserving the interdependencies among gait parameters. Several experiments are conducted to evaluate the performance of NEST and other prior methods. Compared to prior handcrafted-statistics-based methods, NEST demonstrates over 65.1% improvement in RMSE (Root-Mean-Square Error) when predicting spatial parameters.