Autonomic Face Mask Detection with Deep Learning: an IoT Application

Víctor Hugo Benitez Baltazar; Jesús Horacio Pacheco Ramírez; Jose Roberto; Cristian Nuñez Gurrola

doi:10.17488/RMIB.42.2.13

Autores/as

Víctor Hugo Benitez Baltazar Universidad de Sonora, México https://orcid.org/0000-0002-3926-9352
Jesús Horacio Pacheco Ramírez Universidad de Sonora, México
Jose Roberto Universidad de Sonora, México
Cristian Nuñez Gurrola Universidad de Sonora, México https://orcid.org/0000-0002-6120-984X

DOI:

https://doi.org/10.17488/RMIB.42.2.13

Palabras clave:

Machine learning, COVID - 19, Cyber-Physical Systems, Internet of Things

Resumen

Un virus nuevo y letal conocido como SARS-CoV-2, responsable de la enfermedad del coronavirus (COVID-19), se está propagando rápidamente por el mundo y ha provocado más de 3 millones de muertes. Por tal razón, existe una necesidad urgente de encontrar formas nuevas e innovadoras de reducir la probabilidad de infección. Una de las formas usuales de contraer el virus es al estar en contacto con las gotas de saliva de una persona enferma. Este riesgo se puede reducir usando una mascarilla tipo cubrebocas como sugiere la Organización Mundial de la Salud (OMS), especialmente en entornos cerrados como aulas, hospitales y supermercados. Sin embargo, las personas dudan en usar una mascarilla, lo que aumenta el riesgo de propagar la enfermedad, además, cuando se usa la mascarilla, a veces se usa de manera incorrecta. En este trabajo de investigación se propone un sistema autonómico de detección de mascarilla con aprendizaje profundo empoderada con la técnica de detección de imágenes que se utiliza en desarrollos de realidad aumentada como mecanismo para solicitar el correcto uso de mascarilla para permitir el acceso de personas a zonas críticas. Para lograr esto, se construyó un modelo de aprendizaje máquina basado en redes neuronales convolucionales con un enfoque de IoT para hacer cumplir el uso correcto de la máscara facial en las áreas requeridas, tal como lo exige la ley en algunas regiones.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Stilianakis NI, Drossinos Y. Dynamics of infectious disease transmission by inhalable respiratory droplets. J R Soc Interface [Internet]. 2010;7(50):1355-1366. Available from: https://doi.org/10.1098/rsif.2010.0026

Çelik I, Saatçi E, Eyüboğlu FO. Emerging and reemerging respiratory viral infections up to Covid-19. Turk J Med Sci [Internet]. 2020;50(SI-1):557-562. Available from: https://doi.org/10.3906/sag-2004-126

Lipsitch M, Cohen T, Cooper B, Robins JM, et al. Transmission Dynamics and Control of Severe Acute Respiratory Syndrome. Science [Internet]. 2003;300 (5627):1966-70. Available from: https://doi.org/10.1126/science.1086616

Blackburn RM, Frampton D, Smith CM, Fragaszy EB, et al. Nosocomial transmission of influenza: A retrospective cross‐sectional study using next generation sequencing at a hospital in England (2012‐2014). Influenza Other Respir Viruses [Internet]. 2019;13(6): 556-563. Available from: https://doi.org/10.1111/irv.12679

Mendelson L. Facing Your Face Mask Duties – A List of Statewide Orders. Insight [Internet]; 2021. Available from: https://www.littler.com/publication-press/publication/facing-your-face-mask-duties-list-statewide-orders

World Health Organization. Advice on the use of masks in the context of COVID-19: interim guidance-2. World Health Organization [Internet]; 2020. Available from: https://apps.who.int/iris/handle/10665/332293

Fadinger H, Schymik J. The Costs and Benefits of Home Office during the Covid-19 Pandemic - Evidence from Infections and an Input-Output Model for Germany. COVID Economics [Internet]. 2020;9(1):107-134. Available from: https://doi.org/10.3886/E124902V2

Otoom M, Otoum N, Alzubaidi MA, Etoom Y, et al. An IoT-based framework for early identification and monitoring of COVID-19 cases. Biomed Signal Process Control [Internet]. 2020;62:102149. Available from: https://doi.org/10.1016/j.bspc.2020.102149

Sahlol AT, Yousri D, Ewees AA, Al-Qaness MAA, et al. COVID-19 image classification using deep features and fractional-order marine predators algorithm. Sci Rep [Internet]. 2020;10(1):15364. Available from: https://doi.org/10.1038/s41598-020-71294-2

Khaleghi A, Moin MS. Improved anomaly detection in surveillance videos based on a deep learning method. 2018 8th Conference of AI & Robotics and 10th RoboCup Iranopen International Symposium (IRANOPEN) [Internet]. Qazvin: IEEE; 2018:73-81. Available from: http://doi.org/10.1109/RIOS.2018.8406634

Lee EA, Seshia SA. Introduction to Embedded Systems, A Cyber-Physical Systems Approach [Internet]. Version 1.8. Berckeley: MIT Press; 2011. Available from: https://ptolemy.berkeley.edu/books/leeseshia/releases/LeeSeshia_DigitalV1_08.pdf

Lee EA. Cyber Physical Systems: Design Challenges. 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC) [Internet]. Orlando: IEEE; 2008:363-369. Available from: http://doi.org/10.1109/ISORC.2008.25

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature [Internet]. 2015;521(7553):436-444. Available from: https://doi.org/10.1038/nature14539

Jin KH, McCann MT, Froustey E, Unser M. Deep Convolutional Neural Network for Inverse Problems in Imaging. IEEE Trans Image Process [Internet]. 2017;26(9):4509-4522. Available from: http://doi.org/10.1109/TIP.2017.2713099

Li H, Lin Z, Shen X, Brandt J, et al. A convolutional neural network cascade for face detection. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Boston: IEEE; 2015:5325-5334. Available from: http://doi.org/10.1109/CVPR.2015.7299170

Zhu W, Ma Y, Zhou Y, Benton M, et al. Deep Learning Based Soft Sensor and Its Application on a Pyrolysis Reactor for Compositions Predictions of Gas Phase Components. Comput Aided Chem Eng [Internet]. 2018;44(1):2245–2250. Available from: http://doi.org/10.1016/b978-0-444-64241-7.50369-4

Chan T, Jia K, Gao S, Lu J, et al. PCANet: A Simple Deep Learning Baseline for Image Classification? IEEE Trans Image Process [Internet]. 2015;24(12):5017-5032. Available from: http://doi.org/10.1109/TIP.2015.2475625

Shorten C, Khoshgoftaar T. A survey on Image Data Augmentation for Deep Learning. J Big Data [Internet]. 2019;6:60. Available from: https://doi.org/10.1186/s40537-019-0197-0

Escamilla-Ambrosio PJ, Rodríguez-Mota A, Aguirre-Anaya E, Acosta-Bermejo R, et al. Distributing Computing in the Internet of Things: Cloud, Fog and Edge Computing Overview. In Maldonado Y, Trujillo L, Schütze O, Riccardi A, et al (eds). Studies in Computational Intelligence [Internet]. Vol 731. Cham: Springer; 2018. Available from: http://doi.org/10.1007%2F978-3-319-64063-1_4

Al-Bahri M, Yankovsky A, Borodin A, Kirichek R. Testbed for Identify IoT-Devices Based on Digital Object Architecture. In: Galinina O, Andreev S, Balandin S, Koucheryavy Y (eds). Internet of Things, Smart Spaces, and Next Generation Networks and Systems. NEW2AN 2018, ruSMART 2018 [Internet]. Vol. 11118. Cham: Springer. 2018. Available from: https://doi.org/10.1007/978-3-030-01168-0_12

Yassein MB, Shatnawi MQ, Aljwarneh S, Al-Hatmi R. Internet of Things: Survey and open issues of MQTT protocol. 2017 International Conference on Engineering & MIS (ICEMIS) [Internet]. Monastir: IEEE; 2017:1-6. Available from: https://doi.org/10.1109/ICEMIS.2017.8273112

Pacheco J, Tunc C, Satam P, Hariri S. Secure and Resilient Cloud Services for Enhanced Living Environments. IEEE Cloud Comput [Internet]. 2016;3(6):44–52. Available from: https://doi.org/10.1109/MCC.2016.129

Gurav O. Face Mask Detection Dataset. Kaggle [Internet]; 2021. Available from: https://www.kaggle.com/omkargurav/face-mask-dataset

Getting Started with Vuforia Engine in Unity | VuforiaLibrary. PTC Inc [Internet]. [cited 2021 May 24]. Available from: https://library.vuforia.com/articles/Training/getting-started-with-vuforia-in-unity.html

Amin D, Govilkar S. Comparative Study of Augmented Reality SDK’s. Int J Comput Sci Appl [Internet]. 2015;5(1):11–26. Available from: https://doi.org/10.5121/ijcsa.2015.5102