Shengshun Duan,Yucheng Lin,Chenyu Zhang,Yinghui Li,Di Zhu,Jun Wu,Wei Lei
Waterproofness is of value and critical for electronic systems, especially involving underwater interactivities. Yet, the most reported works are related to waterproof flexible sensors. System-level waterproof platforms integrating with sensing, processing and wirelessly transmitting to provide consumer-grade performance have been seldom reported. Herein, we construct a machine-learning-assisted waterproof hybrid electronic system via the whole encapsulation technique integrating fiber sensors and processing center based on flexible printed circuit board (FPCB) so as to achieve fully underwater interactivities. The fiber sensors can be seamlessly integrated with the FPCB through knitting techniques, which exhibit excellent robustness, washability, and waterproofness, with resistance varying within in ± 0.6% in tape water, sweat, and saline solution for up to 15 days. The hybrid platform is demonstrated for an underwater piano playing “Happy birthday to you” and the remote control of a robotic hand in water using the multilayer perceptron that achieves a 98.1% classification accuracy for 20 kinds of hand gestures. Our work may promote advances in waterproof system-level electronics from device design, system integration to algorithm optimization.
Hand gesture recognition, one of the most popular research topics in human–machine interaction, is extensively used in visual and augmented reality, sign language translation, prosthesis control, and so on. To improve the flexibility and interactivity of wearable gesture sensing interfaces, flexible electronic systems for gesture recognition have been widely studied. However, these systems are limited in terms of wearability, stability, scalability, and robustness. Herein, we report a flexible wearable hand gesture recognition system that is based on an iontronic capacitive pressure sensing array and deep convolutional neural networks. The entire capacitive array is integrated into a flexible silicone wristband and can be comfortably and conveniently wrapped around the wrist. The pressure sensing array, which is composed of an iontronic film sandwiched between two flexible screen-printed electrode arrays, exhibits a high sensitivity (775.8 kPa−1), fast response time (65 ms), and high durability (over 6000 cycles). Image processing techniques and deep convolutional neural networks are applied for sensor signal feature extraction and hand gesture recognition. Several contexts such as intertrial test (average accuracy of 99.9%), intersession rewearing (average accuracy of 93.2%), electrode shift (average accuracy of 83.2%), and different arm positions during measurement (average accuracy of 93.1%) are evaluated.
危险品化学品经营许可证（带存储）