EUVIMEDEUVIMED entdecken
Crossref

Wood-Framed Conductive Aerogel with Switch-like Response for Machine Learning-Assisted Digit Handwritten Recognition

Guihua Yan, Fengyu Liu, Yilian Song, Zhiming Du, Xue Song, Yongde Liu

ACS Sustainable Chemistry & Engineering · 13.07.2026 · 14 (27) · 12349-12358

DOI: 10.1021/acssuschemeng.6c04120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Sustainable Chemistry & Engineering, online erschienen am 29.06.2026. Verfasst von Guihua Yan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Handwriting recognition based on flexible sensor arrays holds promise for human−machine interaction, yet developing sensing materials with high sensitivity, stability, and scalable fabrication remains challenging. Here, we present a wood-framed conductive aerogel fabricated through self-assembly, utilizing wood's natural anisotropic porous structure as a template for PEDOT:PSS-Cu2+ coating. The material exhibits a fluff-like microstructure enabling a switch-like “compression conductive-release insulating” mechanism. Mechanical characterization reveals excellent compressive recovery over 8000 cycles with a gauge factor of ∼10 within 0−8% strain. Using this material, we construct a 5 × 5 tactile sensor array for handwritten digit recognition. Three machine learning approaches—logistic regression, artificial neural network, and random forest—are systematically evaluated. The random forest model achieves the highest recognition accuracy and stability, successfully identifying digits with clear boundary visualization after dimensionality reduction. Testing on a random digit sequence demonstrates 100% prediction accuracy with reliable probability heatmaps. This work provides a green approach for fabricating high-performance fiber-based electronics and establishes a complete framework from sensor fabrication to machine learning-enabled intelligent recognition.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yan, G., Liu, F., Song, Y., Du, Z., Song, X., & Liu, Y. (2026). Wood-Framed Conductive Aerogel with Switch-like Response for Machine Learning-Assisted Digit Handwritten Recognition. ACS Sustainable Chemistry & Engineering, 14(27), 12349-12358. https://doi.org/10.1021/acssuschemeng.6c04120

Vancouver

Yan G, Liu F, Song Y, Du Z, Song X, Liu Y. Wood-Framed Conductive Aerogel with Switch-like Response for Machine Learning-Assisted Digit Handwritten Recognition. ACS Sustainable Chemistry & Engineering. 2026;14(27):12349-12358. doi:10.1021/acssuschemeng.6c04120

BibTeX
@article{Yan2026,
  author = {Yan, Guihua and Liu, Fengyu and Song, Yilian and Du, Zhiming and Song, Xue and Liu, Yongde},
  title = {Wood-Framed Conductive Aerogel with Switch-like Response for Machine Learning-Assisted Digit Handwritten Recognition},
  journal = {ACS Sustainable Chemistry & Engineering},
  year = {2026},
  volume = {14},
  number = {27},
  pages = {12349--12358},
  doi = {10.1021/acssuschemeng.6c04120}
}
Kostenlos starten →