EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Deep Learning-Based EIT System for Robust Gesture Recognition Under Confounding Factors

Hancong Wu iD, Guanghong Huang, Wentao Wang, Yuan Wen

Biosensors · 01.04.2026 · 16 (4) · 200

DOI: 10.3390/bios16040200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors, online erschienen am 01.04.2026. Verfasst von Hancong Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Future Technology, South China University of Technology, Guangzhou 511442, China. Hauptthemen laut MEDLINE: Tomography, Deep Learning, Gestures. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Pearl River Talent Program, Guangzhou Basic and Applied Basic Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gesture recognition with electrical impedance tomography (EIT) is an enormous potential tool for human–machine interaction because of its low cost, low complexity and high temporal resolution. Although high-precision EIT-based gesture recognition has been achieved in ideal scenarios, ensuring its consistent performance under interference remains challenging. This article presents a novel method to alleviate the effect of confounding factors on EIT gesture recognition. An EIT armband was designed to mitigate the effect of contact impedance variation based on equivalent circuit analysis, and a spatial–temporal fusion network, named the Fold Atrous Spatial Pyramid Pooling-Gated Recurrent Unit (FASPP-GRU), was developed for robust gesture classification. The results showed that the proposed two-layer electrode maintained a stable contact impedance when its contact force with the skin was changed. Although confounding factors caused significant changes in baseline forearm impedance, FASPP-GRU achieved 80% accuracy under the effect of limb position changes and dynamic changes in muscle state over time, which outperforms conventional classifiers. With an 87 μs inference time, the proposed system shows enormous potential in real-time applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TomographyDeep LearningGesturesElectric ImpedanceHumansElectrodes

Stichwörter der Autor:innen

confounding factorsdeep learningelectrical impedance tomographygesture recognitionstretchable sensor

Autor:innen und Institutionen

  • School of Future Technology, South China University of Technology, Guangzhou 511442, China.
  • Pazhou Lab, Guangzhou 510320, China.
  • School of Natural and Computing Sciences, The University of Aberdeen, Aberdeen AB24 3UE, UK.

ORCID-Profile: Hancong Wu

Förderung

  • National Natural Science Foundation of China
  • Guangdong Pearl River Talent Program
  • Guangzhou Basic and Applied Basic Research Foundation
  • Guangdong Provincial Key Laboratory of Human Digital Twin
  • Pazhou Lab

Zitieren

APA

Wu, H., Huang, G., Wang, W., & Wen, Y. (2026). A Deep Learning-Based EIT System for Robust Gesture Recognition Under Confounding Factors. Biosensors, 16(4), 200. https://doi.org/10.3390/bios16040200

Vancouver

Wu H, Huang G, Wang W, Wen Y. A Deep Learning-Based EIT System for Robust Gesture Recognition Under Confounding Factors. Biosensors. 2026;16(4):200. doi:10.3390/bios16040200

BibTeX
@article{Wu2026,
  author = {Wu, Hancong and Huang, Guanghong and Wang, Wentao and Wen, Yuan},
  title = {A Deep Learning-Based EIT System for Robust Gesture Recognition Under Confounding Factors},
  journal = {Biosensors},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {200},
  doi = {10.3390/bios16040200}
}
Kostenlos starten →