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

• DOI: 10.1007/s40820-025-01780-7
• Publication Date: 2025-05-29T08:12:39Z
• Authors: Kai Zheng; Chengcheng Zheng; Lixian Zhu; Bihai Yang; Xiaokun Jin; Su Wang; Zikai Song; Jingyu Liu; Yan Xiong; Fuze Tian; Ran Cai; Bin Hu
• Keywords: Biocompatibility

Abstract Due to their high mechanical compliance and excellent biocompatibility, conductive hydrogels exhibit significant potential for applications in flexible electronics. However, as the demand sensitivity, superior properties, strong adhesion performance continues grow, many conventional fabrication methods remain complex costly. Herein, we propose a simple efficient strategy construct an entangled network hydrogel through liquid–metal-induced cross-linking reaction, demonstrates outstanding including exceptional stretchability (1643%), tensile strength (366.54 kPa), toughness (350.2 kJ m −3 ), relatively low hysteresis. The exhibits long-term stable reusable (104 enabling conformal human skin. This capability allows it effectively capture high-quality epidermal electrophysiological signals with signal-to-noise ratio (25.2 dB) impedance (310 ohms). Furthermore, by integrating advanced machine learning algorithms, achieving attention classification accuracy of 91.38%, which will significantly impact fields like education, healthcare, artificial intelligence.