SImpHAR: Advancing impedance-based human activity recognition using 3D simulation and text-to-motion models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918086987218944 |
|---|---|
| author | Ray, Lala Shakti Swarup Liu, Mengxi Gurung, Deepika Zhou, Bo Suh, Sungho Lukowicz, Paul |
| author_facet | Ray, Lala Shakti Swarup Liu, Mengxi Gurung, Deepika Zhou, Bo Suh, Sungho Lukowicz, Paul |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06405 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SImpHAR: Advancing impedance-based human activity recognition using 3D simulation and text-to-motion models Ray, Lala Shakti Swarup Liu, Mengxi Gurung, Deepika Zhou, Bo Suh, Sungho Lukowicz, Paul Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | SImpHAR: Advancing impedance-based human activity recognition using 3D simulation and text-to-motion models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.06405 |