EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STORM: Hardware-Aware Tiny Transformer Co-Design for Low-Power Inertial Human Activity Recognition

Alessandro Varaldi, Claudio Genta, Alberto Manzone, Marco Vacca

Electronics · 01.05.2026 · 15 (9) · 1924

DOI: 10.3390/electronics15091924 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 01.05.2026. Verfasst von Alessandro Varaldi und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: project PNRR-NGEU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human Activity Recognition (HAR) from inertial sensors must run continuously on battery-powered wearables under tight latency, memory, and energy budgets. While tiny Transformers can be effective on inertial time series, end-to-end co-design across quantized inference and heterogeneous low-power platforms remains underexplored. We present STORM (Small Transformer for On-node Recognition of Motion), a deployment-oriented 19.7k-parameter 1D Transformer co-designed with X-HEEP, an open-source low-power single-core RISC-V SoC, and a tightly coupled streaming CGRA for nonlinear primitives (e.g., softmax). We build a cross-source 8-class benchmark by harmonizing 3 public datasets under a stringent, deployment-aligned protocol that exposes both cross-subject and cross-source shift. Using 1.280 s windows with 0.640 s stride, the protocol models continuous on-node HAR under cross-dataset generalization. After quantization-aware training and INT8 C inference export, STORM achieves 0.799/0.801 accuracy/macro-F1 on this benchmark. Deployed on an FPGA prototype of X-HEEP with the streaming CGRA backend, STORM requires 67.4 ms per inference at 100 MHz, while activity-based power analysis estimates a total inference energy of 632.4 μJ, satisfying the stride-driven real-time constraint. These results support the practical viability of compact attention-based HAR on low-power wearable-class embedded platforms.

Förderung

  • project PNRR-NGEU

Zitieren

APA

Varaldi, A., Genta, C., Manzone, A., & Vacca, M. (2026). STORM: Hardware-Aware Tiny Transformer Co-Design for Low-Power Inertial Human Activity Recognition. Electronics, 15(9), 1924. https://doi.org/10.3390/electronics15091924

Vancouver

Varaldi A, Genta C, Manzone A, Vacca M. STORM: Hardware-Aware Tiny Transformer Co-Design for Low-Power Inertial Human Activity Recognition. Electronics. 2026;15(9):1924. doi:10.3390/electronics15091924

BibTeX
@article{Varaldi2026,
  author = {Varaldi, Alessandro and Genta, Claudio and Manzone, Alberto and Vacca, Marco},
  title = {STORM: Hardware-Aware Tiny Transformer Co-Design for Low-Power Inertial Human Activity Recognition},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {1924},
  doi = {10.3390/electronics15091924}
}
Kostenlos starten →