Machine Learning Enabled Reusable Adhesion, Entangled Network-Based Hydrogel for Long-Term, High-Fidelity EEG Recording and Attention Assessment

Kai Zheng; Chengcheng Zheng; Lixian Zhu; Bihai Yang; Xiaokun Jin; Su Wang; Zikai Song; Jingyu Liu; Yan Xiong; Fuze Tian; Ran Cai; Bin Hu

doi:10.1007/s40820-025-01780-7

Machine Learning Enabled Reusable Adhesion, Entangled Network-Based Hydrogel for Long-Term, High-Fidelity EEG Recording and Attention Assessment

Kai Zheng, Chengcheng Zheng, Lixian Zhu, Bihai Yang, Xiaokun Jin, Su Wang, Zikai Song, Jingyu Liu, Yan Xiong, Fuze Tian^*, Ran Cai^*, Bin Hu^*

^*Corresponding author for this work

School of Medical and Technology

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

A dual-network hydrogel (PGEH) cross-linked via liquid metal induction was developed exhibiting remarkable mechanical properties and skin-temperature-triggered on-demand adhesion capabilities. The PGEH capacitive sensor demonstrates exceptional sensitivity (1.25 kPa), rapid dynamic response (30 ms), and long-term cycling stability (20,000 cycles), enabling precise monitoring of human motion and reliable signal transmission. Low-impedance electrophysiological sensor (310 ohms) maintains 14-day signal fidelity (25.2 dB), paired with machine learning-based attention monitoring (91.38% of accuracy) for real-time cognitive feedback in focus-demanding scenarios.

Original language	English
Article number	281
Journal	Nano-Micro Letters
Volume	17
Issue number	1
DOIs	http://doi.org/10.1007/s40820-025-01780-7
Publication status	Published - Dec 2025

Keywords

Attention assessment
Entangled network
Epidermal sensor
Machine learning
Reusable adhesion

Access to Document

10.1007/s40820-025-01780-7

Cite this

@article{d7bed2b159e04a838c4af29e6fb6358e,

title = "Machine Learning Enabled Reusable Adhesion, Entangled Network-Based Hydrogel for Long-Term, High-Fidelity EEG Recording and Attention Assessment",

abstract = "A dual-network hydrogel (PGEH) cross-linked via liquid metal induction was developed exhibiting remarkable mechanical properties and skin-temperature-triggered on-demand adhesion capabilities. The PGEH capacitive sensor demonstrates exceptional sensitivity (1.25 kPa), rapid dynamic response (30 ms), and long-term cycling stability (20,000 cycles), enabling precise monitoring of human motion and reliable signal transmission. Low-impedance electrophysiological sensor (310 ohms) maintains 14-day signal fidelity (25.2 dB), paired with machine learning-based attention monitoring (91.38\% of accuracy) for real-time cognitive feedback in focus-demanding scenarios.",

keywords = "Attention assessment, Entangled network, Epidermal sensor, Machine learning, Reusable adhesion",

author = "Kai Zheng and Chengcheng Zheng and Lixian Zhu and Bihai Yang and Xiaokun Jin and Su Wang and Zikai Song and Jingyu Liu and Yan Xiong and Fuze Tian and Ran Cai and Bin Hu",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",

year = "2025",

month = dec,

doi = "10.1007/s40820-025-01780-7",

language = "English",

volume = "17",

journal = "Nano-Micro Letters",

issn = "2311-6706",

publisher = "Open Access Science Online",

number = "1",

}

TY - JOUR

T1 - Machine Learning Enabled Reusable Adhesion, Entangled Network-Based Hydrogel for Long-Term, High-Fidelity EEG Recording and Attention Assessment

AU - Zheng, Kai

AU - Zheng, Chengcheng

AU - Zhu, Lixian

AU - Yang, Bihai

AU - Jin, Xiaokun

AU - Wang, Su

AU - Song, Zikai

AU - Liu, Jingyu

AU - Xiong, Yan

AU - Tian, Fuze

AU - Cai, Ran

AU - Hu, Bin

PY - 2025/12

Y1 - 2025/12

N2 - A dual-network hydrogel (PGEH) cross-linked via liquid metal induction was developed exhibiting remarkable mechanical properties and skin-temperature-triggered on-demand adhesion capabilities. The PGEH capacitive sensor demonstrates exceptional sensitivity (1.25 kPa), rapid dynamic response (30 ms), and long-term cycling stability (20,000 cycles), enabling precise monitoring of human motion and reliable signal transmission. Low-impedance electrophysiological sensor (310 ohms) maintains 14-day signal fidelity (25.2 dB), paired with machine learning-based attention monitoring (91.38% of accuracy) for real-time cognitive feedback in focus-demanding scenarios.

AB - A dual-network hydrogel (PGEH) cross-linked via liquid metal induction was developed exhibiting remarkable mechanical properties and skin-temperature-triggered on-demand adhesion capabilities. The PGEH capacitive sensor demonstrates exceptional sensitivity (1.25 kPa), rapid dynamic response (30 ms), and long-term cycling stability (20,000 cycles), enabling precise monitoring of human motion and reliable signal transmission. Low-impedance electrophysiological sensor (310 ohms) maintains 14-day signal fidelity (25.2 dB), paired with machine learning-based attention monitoring (91.38% of accuracy) for real-time cognitive feedback in focus-demanding scenarios.

KW - Attention assessment

KW - Entangled network

KW - Epidermal sensor

KW - Machine learning

KW - Reusable adhesion

UR - http://www.scopus.com/pages/publications/105006885678

U2 - 10.1007/s40820-025-01780-7

DO - 10.1007/s40820-025-01780-7

M3 - Article

AN - SCOPUS:105006885678

SN - 2311-6706

VL - 17

JO - Nano-Micro Letters

JF - Nano-Micro Letters

IS - 1

M1 - 281

ER -

Machine Learning Enabled Reusable Adhesion, Entangled Network-Based Hydrogel for Long-Term, High-Fidelity EEG Recording and Attention Assessment

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this