PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 17, 2026Advanced Functional Materials4 citations

Nanomesh Reinforced Eutectogel by Interfacial Engineering for Human Motion Monitoring and Machine Learning‐Enabled Gesture Recognition

View Full Paper
HDHaitao DengZCZiquan CaoJYJianmin Yang

Key Points

  • The aim is to engineer a hybrid gel for improved motion monitoring and gesture recognition in wearable devices.
  • Incorporated an electrospun polyurethane nanomesh into a eutectogel matrix.
  • Characterized the tensile strength, stretchability, and fatigue resistance of the hybrid gel.
  • Evaluated the sensitivity of the gel as a strain sensor and its efficacy in detecting temperature and humidity.
  • Coupled the output from electromyography with a convolutional neural network for gesture recognition.
  • Achieved tensile strength of 12.6 MPa and stretchability of 1376%.
  • Demonstrated ability to record physiological signals like EMG and ECG under various conditions.
  • Attained gesture recognition accuracy of 98.7% using CNN.

Abstract

ABSTRACT Engineering soft conductors that simultaneously offer high strength, extreme stretchability, and environmental stability remains a central challenge for next‐generation wearable electronics. Here, we incorporate an electrospun polyurethane (PU) nanomesh rich in hydrogen bonding sites into a eutectogel matrix. Benefiting from designable interfacial interactions, the thin hybrid gel (≈45 µm) exhibits high tensile strength (12.6 MPa), remarkable stretchability (1376%) and fatigue resistance. Based on its good sensitivity, the hybrid gel can serve as a strain sensor for wide range human motion monitoring, as well as a multifunctional sensor for humidity and temperature detection. Moreover, its high water vapor transmission rate (1176 g·m −2 ·d −1 ) and robust anti‐freezing and anti‐drying properties enable reliable recording of physiological signals such as electromyography (EMG) and electrocardiography (ECG). By coupling the EMG output with a convolutional neural network (CNN), the system attains a high gesture recognition accuracy of 98.7%. This work demonstrates great potential for next‐generation wearable healthcare and human‐machine interfaces.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Deng et al. (2026) studied this question.

synapsesocial.com/papers/699405254e9c9e835dfd5ff9https://doi.org/10.1002/adfm.74510
Ask AI
Helpful
Bookmark
Share
View Full Paper