Logo image
Poster: Noninvasive Respirator Fit Factor Inference by Semi-Supervised Learning
Conference proceeding   Open access

Poster: Noninvasive Respirator Fit Factor Inference by Semi-Supervised Learning

Jinmiao Chen, Zhaohe (John) Zhang, Shangqing Zhao, Song Fang, Thomas M. Peters, Evan L. Floyd and Changjie Cai
2023 IEEE/ACM CONFERENCE ON CONNECTED HEALTH: APPLICATIONS, SYSTEMS AND ENGINEERING TECHNOLOGIES, CHASE, pp.200-202
IEEE International Conference on Connected Health-Applications, Systems and Engineering Technologies
01/01/2023
DOI: 10.1145/3580252.3589420
url
https://doi.org/10.1145/3580252.3589420View
Published (Version of record) Open Access

Abstract

The need for personal protective equipment, such as respirators, has been emphasized by pandemics as they provide protection against infectious diseases. Adequate protection is only possible when respirators fit properly and are worn correctly. Therefore, it is especially critical to closely monitor and ensure respirator fit, particularly during a pandemic. To ensure proper fit and continuous monitoring, we propose a newnoninvasive method that uses speech signals to measure the attenuation of sound caused by the respirator. This method provides a quantitative measure of respirator Fit Factor (FF, the ratio of the concentration of a substance in ambient air to its concentration inside the respirator). This method is also cost-effective and easy to implement. By collecting limited labeled and unlabeled speech data, augmenting labeled data, extracting time and frequency domain features, we achieved up to 86.24% accuracy in respirator fit detection using semi-supervised learning model.
Computer Science Engineering Medical Informatics Technology Computer Science, Cybernetics Computer Science, Interdisciplinary Applications Engineering, Biomedical Life Sciences & Biomedicine Science & Technology

Details

Metrics

Logo image