Smart Respiratory Mask Selector: AI and Facial Scan Analytics for Personalised Mask Fitting
DOI:
https://doi.org/10.22399/ijcesen.4770Keywords:
Respiratory protection, Facial scan analytics, Mask fitting, Seal integrity, Fit factor, MicroleakageAbstract
This paper aims to assess the potential of a Smart Respiratory Mask Selector to combine artificial intelligence (AI) and facial scan analytics to provide customised masking to facilitate healthcare and industrial users. Traditional techniques of respirator fitting do not consider the craniofacial variations, causing the loss of seal integrity and decreased resistance to airborne pathogens. The study utilises a secondary approach that involves combining clinical trials on fit testing, ergonomic tests, and facial recognition standards to address the issue of the advantages of AI-based personalisation in a critical manner. Findings suggest that the system has better respiratory fit accuracy, and minimises microleakage by more than 40 percent and is still within NIOSH and EN 149 standards. Facial landmark observation was found to be very specific, and thus, it was found to be able to map mask-to-face interfaces effectively in different populations. The ergonomic results showed an increase in comfort measures, alleviation of skin irritation caused by pressure, and increased compliance with a long-term application. Notably, the algorithmic suggestions of the system guaranteed regulatory adherence and considered the difference in demographics that are usually ignored in standardised designs. Taken together, these results affirm the notion that the AI-assisted mask-fitter is effective in improving the level of both safety and convenience, and it is a scalable intervention in terms of infection control and occupational wellness. The research finds that the inclusion of biometric analytics in respiratory protection is an important innovation in both the accuracy of public health and frontline safety.
References
[1] Byrd, A., Conway, S.H., Delclos, G.L. and Pompeii, L., 2016. The American Association of Occupational Health Nurses' respiratory protection education program and resources Webkit for occupational health professionals.
[2] Cañizares-Gaztelu, J.C., 2018. The Information Society: Technological, socio-economic and cultural aspects-Prolegomena for a sustainability-oriented ethics of ICTs.
[3] Davies, M.A., Morden, E., Rosseau, P., Arendse, J., Bam, J.L., Boloko, L., Cloete, K., Cohen, C., Chetty, N., Dane, P. and Heekes, A., 2019. Outcomes of laboratory-confirmed SARS-CoV-2 infection during resurgence. International Journal of Population Data Science, 4(2).
[4] Feng, Z.H., Hu, G., Kittler, J., Christmas, W. and Wu, X.J., 2015. Cascaded collaborative regression for robust facial landmark detection trained using a mixture of synthetic and real images with dynamic weighting. IEEE Transactions on Image Processing, 24(11), pp.3425-3440.
[5] Grinshpun, S.A., Leppänen, M., Wu, B. and Yermakov, M., 2018. Utility of an optical particle counting instrument for quantitative respirator fit testing with N95 filtering facepieces.
[6] Guo, X., Li, S., Yu, J., Zhang, J., Ma, J., Ma, L., Liu, W. and Ling, H., 2019. PFLD: A practical facial landmark detector. arXiv preprint arXiv:1902.10859.
[7] Huang, M.H. and Rust, R.T., 2018. Artificial intelligence in service. Journal of Service Research, 21(2), pp.155-172.
[8] Johnston, B. and Chazal, P.D., 2018. A review of image-based automatic facial landmark identification techniques. EURASIP Journal on Image and Video Processing, 2018(1), p.86.
[9] Li, H., Lin, Z., Shen, X., Brandt, J. and Hua, G., 2015. A convolutional neural network cascade for face detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5325-5334).
[10] Liu, Q., Yang, J., Deng, J. and Zhang, K., 2017. Robust facial landmark tracking via cascade regression. Pattern Recognition, 66, pp.53-62.
[11] Majchrzycka, K., Okrasa, M., Szulc, J. and Gutarowska, B., 2017. Safety of workers exposed to harmful airborne bioaerosols–legal status and innovations. Biotechnology and Food Science, 81(2), pp.159-168.
[12] Patra, G.K., Rajaram, S.K. and Boddapati, V.N., 2019. Ai And Big Data In Digital Payments: A Comprehensive Model For Secure Biometric Authentication. Educational Administration: Theory and Practice.
[13] Reidy, M., Ryan, F., Hogan, D., Lacey, S. and Buckley, C., 2015. Preparedness of hospitals in the Republic of Ireland for an influenza pandemic, an infection control perspective. BMC Public Health, 15(1), p.847.
[14] Rigano, C., 2019. Using artificial intelligence to address criminal justice needs. National Institute of Justice Journal, 280(1-10), p.17.
[15] Sadeghi, S., Fakharian, A., Nasri, P. and Kiani, A., 2017. Comparison of comfort and effectiveness of total face mask and oronasal mask in noninvasive positive pressure ventilation in patients with acute respiratory failure: a clinical trial. Canadian Respiratory Journal, 2017(1), p.2048032.
[16] Sedenberg, E. and Chuang, J., 2017. Smile for the camera: Privacy and policy implications of emotion AI. arXiv preprint arXiv:1709.00396.
[17] Smith, J.D., MacDougall, C.C., Johnstone, J., Copes, R.A., Schwartz, B. and Garber, G.E., 2016. Effectiveness of N95 respirators versus surgical masks in protecting health care workers from acute respiratory infection: a systematic review and meta-analysis. Cmaj, 188(8), pp.567-574.
[18] Stanfill, M.H. and Marc, D.T., 2019. Health information management: implications of artificial intelligence on healthcare data and information management. Yearbook of medical informatics, 28(01), pp.056-064.
[19] Trybou, J., Gemmel, P. and Annemans, L., 2015. Provider accountability as a driving force towards physician–hospital integration: a systematic review. International journal of integrated care, 15, p.e010.
[20] Wang, Y., Dong, X., Li, G., Dong, J. and Yu, H., 2021. Cascade regression-based face frontalization for dynamic facial expression analysis. Cognitive Computation, 14(5), pp.1571-1584.
[21] Zhang, Q., Sun, H., Wu, X. and Zhong, H., 2019. Edge video analytics for public safety: A review. Proceedings of the IEEE, 107(8), pp.1675-1696.
[22] Zhao, Y., Xu, Q., Chen, W., Du, C., Xing, J., Huang, X. and Yang, R., 2019, March. Mask-off: Synthesizing face images in the presence of head-mounted displays. In 2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR) (pp. 267-276). IEEE.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
