SImpHAR: Advancing impedance-based human activity recognition using 3D simulation and text-to-motion models

TL;DR

SImpHAR introduces a simulation-based data augmentation and a modular training approach to improve impedance-based human activity recognition, achieving significant accuracy gains on multiple datasets.

Contribution

The paper presents a novel simulation pipeline for generating bio-impedance signals and a two-stage training strategy that enhances activity recognition without requiring labeled synthetic data.

Findings

Achieved up to 22.3% accuracy improvement.

Demonstrated effectiveness on multiple benchmarks.

Validated the simulation and training approach.

Abstract

Human Activity Recognition (HAR) with wearable sensors is essential for applications in healthcare, fitness, and human-computer interaction. Bio-impedance sensing offers unique advantages for fine-grained motion capture but remains underutilized due to the scarcity of labeled data. We introduce SImpHAR, a novel framework addressing this limitation through two core contributions. First, we propose a simulation pipeline that generates realistic bio-impedance signals from 3D human meshes using shortest-path estimation, soft-body physics, and text-to-motion generation serving as a digital twin for data augmentation. Second, we design a two-stage training strategy with decoupled approach that enables broader activity coverage without requiring label-aligned synthetic data. We evaluate SImpHAR on our collected ImpAct dataset and two public benchmarks, showing consistent improvements over state-of-the-art methods, with gains of up to 22.3% and 21.8%, in terms of accuracy and macro F1 score, respectively. Our results highlight the promise of simulation-driven augmentation and modular training for impedance-based HAR.