PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 16, 2026Advanced Functional Materials6 citationsOpen Access

Ionic Conductive Organohydrogel with Multi‐Environmental Stability for Machine Learning‐Assisted Health Monitoring

View Full Paper
YNYimeng NiSLShuhui LiSYShuai Yin

Key Points

  • The aim is to fabricate a multi-environmental stable ionic conductive organohydrogel for health monitoring.
  • Fabricated a binary-network ionic organohydrogel using acrylamide and polyvinyl alcohol.
  • Tested the hydrogel's performance in various temperature conditions ranging from -20°C to 60°C.
  • Evaluated the sensor's strain sensitivity and stability over 1000 cycles.
  • Utilized machine learning to recognize different breathing patterns based on sensor data.
  • Achieved over 95% transparency and over 1400% stretchability in the organohydrogel.
  • Sensors demonstrated high strain sensitivity and a sensing range between 2% and 500%.
  • The hydrogel maintained stable performance across extreme temperatures.
  • Machine learning methods showed an average prediction accuracy of 98.4% for breathing patterns.

Abstract

ABSTRACT Ionic conductive organohydrogels have attracted significant attention in wearable sensing due to their transparency, conductivity, and flexibility. However, simultaneously achieving mechanical softness, high transparency, environmental stability, and excellent sensing performance remains a significant challenge. Herein, a binary‐network ionic organohydrogel was fabricated using acrylamide and polyvinyl alcohol within a water/glycerol solvent system to impart anti‐freezing properties. The resulting organohydrogel exhibits high transparency (>95%) and remarkable stretchability (>1400%). Notably, the hydrogel‐based sensor demonstrates high strain sensitivity, a broad sensing range (2%–500%), and outstanding stability and durability over 1000 cycles. It can effectively monitor human motion across various joints, such as the wrist, elbow, and knee. Moreover, the sensor maintains reliable performance at both low (–20°C) and high (60°C) temperatures, showcasing excellent anti‐freezing and anti‐drying capabilities. It also possesses notable thermal sensitivity across a wide temperature range. Leveraging its dual sensitivity to strain and temperature, machine learning‐assisted technology was employed to recognize different breathing patterns, achieving an average prediction accuracy of 98.4%. This work lays a foundation for comprehensive respiratory health monitoring and holds promise for applications in daily health management and clinical practice.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ni et al. (2026) studied this question.

synapsesocial.com/papers/6992b4ad9b75e639e9b09a9ahttps://doi.org/10.1002/adfm.74485
Ask AI
Helpful
Bookmark
Share
View Full Paper