Deep Learning Assisted Body Area Triboelectric Hydrogel Sensor Network for Infant Care

Infants are physically vulnerable and cannot express their feelings. Continuous monitoring and measuring the biomechanical pressure to which an infant body is exposed remains critical to avoid infant injury and illness. Here, a body area sensor network comprising edible triboelectric hydrogel sensors for all-around infant motion monitoring is reported. Each soft sensor holds a collection of compelling features of high signal-to-noise ratio of 23.1 dB, high sensitivity of 0.28 V kPa⁻¹, and fast response time of 50 ms. With the assistance of deep learning algorithms, the body area sensor network can realize infant motion pattern identification and recognition with classification accuracy as high as 100%. Additionally, a customized user-friendly cellphone application is developed to provide real-time warning and one-click guardian interaction. This self-powered body area sensor network system provides a promising paradigm for reliable infant care in the era of the Internet of Things.