This paper introduces a novel triple-layer humidity sensor designed to overcome limitations of traditional humidity sensors in respiration monitoring. The sensor uses a nanoforest-based sensing capacitor, a thermistor, a microheater, and a reference capacitor to achieve significantly improved sensitivity (8 times higher than polyimide-based sensors), reduced recovery time (5s), elimination of parasitic capacitance, and temperature compensation. Machine learning algorithms further enhance its ability to distinguish respiration states with 94% accuracy, making it suitable for consumer electronics and medical applications.

Guidong Chen, Ruofei Guan, Meng Shi, Xin Dai, Hongbo Li, Na Zhou, Dapeng Chen, Haiyang Mao