Machine Learning-Enabled Environmentally Adaptable Skin-Electronic Sensor for Human Gesture Recognition

Abstract

Stretchable sensors have been widely investigated and developed for the purpose of human motion detection, touch sensors, and healthcare monitoring, typically converting mechanical/structural deformation into electrical signals. The viscoelastic strain of stretchable materials often results in nonlinear stress−strain characteristics over a broad range of strains, consequently making the stretchable sensors at the body joints less accurate in predicting and recognizing human gestures. Accurate recognition of human gestures can be further deteriorated by environmental changes such as temperature and humidity. Here, we demonstrated an environmentadaptable high stress−strain linearity (up to ε = 150%) and highdurability (>100,000 cycles) stretchable sensor conformally laminated onto the body joints for human gesture recognition. The serpentine configuration of our ionic liquid-based stretchable film enabled us to construct broad data sets of mechanical strain and temperature changes for machine learning-based gesture recognition. Signal recognition and training of distinct strains and environmental stimuli using a machine learning-based algorithm analysis successfully measured and predicted the joint motion in a temperature-changing environment with an accuracy of 92.86% (R-squared). Therefore, we believe that our serpentine-shaped ion gel-based stretchable sensor harmonized with machine-learning analysis will be a significant achievement toward environmentally adaptive and multianalyte sensing applications. Our proposed machine learning-enabled multisensor system may enable the development of future electronic devices such as wearable electronics, soft robotics, electronic skin, and human-machine interaction systems.

Real-time Hand-Tracking with Skin-Conformal Force Myography based on Wrist-Worn Laser Induced Graphene Strain Sensor Arrays

“…To address these challenges, stretchable and skin conformal devices are attractive solutions for FMG, allowing long-term use without fatigue since the sensors conform to changes in the skin [30]. Some sensor systems directly place strain sensors across the joint of interest to measure the actuations [31][32][33]. Even though accurate, these systems are complex in the sense that all target joints require a sensor.…”

Stretchable MXene/Carbon Nanotube Bilayer Strain Sensors with Tunable Sensitivity and Working Ranges

“…Accurate and precise gesture recognition capability is essential for the development of smart human–machine interfaces. , Monitoring complex movements requires the integration of multiple stretchable strain sensors on various parts of the body . These sensors should have tailored sensitivity and working windows for each body location . However, the variations in body size and motion range among individuals pose significant challenges to the effectiveness of such sensing systems, requiring independent calibration for each use to achieve accurate detection. , Apart from research efforts on sensor developments, data acquisition and processing provide an appealing opportunity to improve these systems .…”