Conformable Multimodal Sensory Facemask for Decoding Biological and Environmental Signals

Facemasks are considered to be a key instrument in reducing exposure to viruses and other environmental hazards such as air pollution. Current wearable electronics applicable to the facemask have been designed only to monitor biological information such as breathing patterns. However, it remains difficult for the public to assess the status of their facemasks with regard to wearing habits and fit quality. In this work, we developed a widely-deployable, conformable, miniaturized sensory interface, which seamlessly attaches onto the internal side of any user-supplied facemask without compromising fit and protection quality, along with a user-interface capable of interpreting a participant’s mask-wearing behavior under various use-case scenarios. Multimodal signals from a variety of sensors were wirelessly transmitted to a server through a custom-made mobile app. Based on the collected data, it was shown that various biological signals related to the signature of infectious diseases could be monitored while determining the fit status of the facemask without using a conventional mask fit tester. A machine learning algorithm was further used to enable the reliable decoding of the facemask position. The novelty of this work lies not only in the system integration, but also in the development of devices which provides real-time mask fit and position analysis, which may benefit medical institutes, industries and the general public in selecting proper facemasks and maintaining a desired mask fit. Additionally, our work could be deployed to multidisciplinary studies such as human behavioral and social sciences to analyze the fit change in real world situations.