Researchers have developed an Internet of Things (IoT) smart mask, integrating an ultrathin nanocomposite sponge structure-based soundwave sensor. It can detect and classify various respiratory sounds (breathing, coughing, and speaking) using deep learning, thus helping to improve personal and public health.
The smart mask integrates an ultrathin flexible wide-bandwidth soundwave sensor made of carbon nanotube/polydimethylsiloxane (CNT/PDMS) nanocomposites, which is as thin as 400 µm and enables high sensitivity in both static and dynamic pressure measurement ranges — up to 4000 Hz — for tracking, classifying, and recognizing three different types of respiratory activities — breathing, speaking, and coughing — and identifying speech.
Thirty-one human subjects were recruited for the study, from whom respiratory activity was collected while they wore the smart mask. The data were processed and classified using deep-learning methods: namely, a support vector machine and convolutional neural networks. All human subjects had macro recalls above 90 percent (with a maximum as high as 100 percent), and the average reached 95.23 percent for all three types of respiratory sounds, showing stable and robust performance.