Ground Reaction Force Estimation via Time-aware Knowledge Distillation

TL;DR

This paper introduces a novel Time-aware Knowledge Distillation framework that improves the accuracy of ground reaction force estimation from wearable insole sensors, making gait analysis more portable and reliable.

Contribution

It presents a new knowledge distillation method that captures temporal and similarity features to enhance GRF estimation from noisy wearable sensor data.

Findings

Outperforms existing baselines in GRF estimation accuracy

Demonstrates effectiveness of temporal feature integration

Validates approach with real-world treadmill comparison

Abstract

Human gait analysis with wearable sensors has been widely used in various applications, such as daily life healthcare, rehabilitation, physical therapy, and clinical diagnostics and monitoring. In particular, ground reaction force (GRF) provides critical information about how the body interacts with the ground during locomotion. Although instrumented treadmills have been widely used as the gold standard for measuring GRF during walking, their lack of portability and high cost make them impractical for many applications. As an alternative, low-cost, portable, wearable insole sensors have been utilized to measure GRF; however, these sensors are susceptible to noise and disturbance and are less accurate than treadmill measurements. To address these challenges, we propose a Time-aware Knowledge Distillation framework for GRF estimation from insole sensor data. This framework leverages similarity and temporal features within a mini-batch during the knowledge distillation process, effectively capturing the complementary relationships between features and the sequential properties of the target and input data. The performance of the lightweight models distilled through this framework was evaluated by comparing GRF estimations from insole sensor data against measurements from an instrumented treadmill. Empirical results demonstrated that Time-aware Knowledge Distillation outperforms current baselines in GRF estimation from wearable sensor data.