Journal article
Short: A data-driven respirator fit test model via human speech signal
Smart Health, Vol.28, 100400
06/2023
DOI: 10.1016/j.smhl.2023.100400
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 new noninvasive 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.
Details
- Title: Subtitle
- Short: A data-driven respirator fit test model via human speech signal
- Creators
- Jinmiao Chen - University of OklahomaZhaohe (John) Zhang - University of OklahomaShangqing Zhao - University of OklahomaSong Fang - University of OklahomaThomas M. Peters - University of IowaEvan L. Floyd - University of OklahomaChangjie Cai - University of Oklahoma
- Resource Type
- Journal article
- Publication Details
- Smart Health, Vol.28, 100400
- Publisher
- Elsevier Inc
- DOI
- 10.1016/j.smhl.2023.100400
- ISSN
- 2352-6483
- Grant note
- DOI: 10.13039/100000001, name: National Science Foundation, award: 1948547, 2155181; DOI: 10.13039/100000030, name: Centers for Disease Control and Prevention, award: 75D30121C10674
- Language
- English
- Date published
- 06/2023
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Occupational and Environmental Health
- Record Identifier
- 9984388756502771
Metrics
52 Record Views