A Deep‐Learning‐Assisted On‐Mask Sensor Network for Adaptive Respiratory Monitoring

Abstract

Wearable respiratory monitoring is a fast, non‐invasive, and convenient approach to provide early recognition of human health abnormalities like restrictive and obstructive lung diseases. Here, a computational fluid dynamics assisted on‐mask sensor network is reported, which can overcome different user facial contours and environmental interferences to collect highly accurate respiratory signals. Inspired by cribellate silk, Rayleigh‐instability‐induced spindle‐knot fibers are knitted for the fabrication of permeable and moisture‐proof textile triboelectric sensors that hold a decent signal‐to‐noise ratio of 51.2 dB, a response time of 0.28 s, and a sensitivity of 0.46 V kPa−1. With the assistance of deep learning, the on‐mask sensor network can realize the respiration pattern recognition with a classification accuracy up to 100%, showing great improvement over a single respiratory sensor. Additionally, a customized user‐friendly cellphone application is developed to connect the processed respiratory signals for real‐time data‐driven diagnosis and one‐click health data sharing with the clinicians. The deep‐learning‐assisted on‐mask sensor network opens a new avenue for personalized respiration management in the era of the Internet of Things.

Self-Powered Respiratory Monitoring Strategy Based on Adaptive Dual-Network Thermogalvanic Hydrogels

“…The normal, deep, and fast breaths (Figure 5d) were tested with our thermoelectric hydrogel patch sensor, which showed that three breathing patterns were caught unmistakably with discernible characteristics. 53 Since the ambient temperature varies greatly with the seasons, whereas human respiratory waste heat is relatively stable, we tested the normal respiratory frequency at 273, 298, and 306 K and found that the lower the temperature, the larger the amplitude of the signal (Figure 5e). Even below zero, the gel patch-based mask can operate normally, implying it fits into low-temperature environments.…”

Printable Carbon Nanotube-Liquid Elastomer-Based Multifunctional Adhesive Sensors for Monitoring Physiological Parameters

“…Unfortunately, such RR monitoring often leverages costly and not so user-friendly monitoring devices/techniques ranging from computed tomography angiography and polysomnography. 54 A volunteer (26 years, male) attached the sensor to a surgical mask and The vibration of the vocal cord due to the epidermis motion while speaking different words was evaluated by measuring relative change in resistance. The repeatability of forming a pattern when speaking the same word frequently decides the quality and stability of the sensor.…”

“…RR is a critical parameter because the RR shades a vital perspective about the conditions of the lungs. Unfortunately, such RR monitoring often leverages costly and not so user-friendly monitoring devices/techniques ranging from computed tomography angiography and polysomnography . A volunteer (26 years, male) attached the sensor to a surgical mask and monitored relative resistance change.…”

Self‐Powered Smart Gloves Based on Triboelectric Nanogenerators

“…[113][114][115][116] Thus, TENGs can also be made into textiles to improve biocompatibility and comfort. [117][118][119][120] In fact, many TENGs have been developed for a wide variety of purposes in the field of wearable biosensors such as cardiovascular monitoring, [121][122][123][124][125][126][127][128][129] respiration monitoring, [94,[130][131][132][133] breath gas analysis, [134][135][136][137][138] sleep monitoring, [130][131][132][133][134][135][136][137][138][139][140][141] wound healing, [142][143][144][145][146][147] acoustic monitoring, [148] and environment monitoring. [149]…”