Evaluation of AIoT performance in Cloud and Edge computational models for mask detection

Main Article Content

Felipe Quiñonez-Cuenca https://orcid.org/0000-0001-7221-4700
Cristian Maza-Merchán https://orcid.org/0000-0002-2078-8267
Nilvar Cuenca-Maldonado https://orcid.org/0000-0002-2611-1310
Manuel Quiñones-Cuenca https://orcid.org/0000-0002-2932-1524
Rommel Torres https://orcid.org/0000-0003-2313-0118
Francisco Sandoval https://orcid.org/0000-0001-5167-0256
Patricia Ludeña-González https://orcid.org/0000-0002-8909-4837


COVID-19 has caused serious health damage, infecting millions of people and unfortunately causing the death of several ones around the world. The vaccination programs of each government have influenced in declining those rates. Nevertheless, new coronavirus mutations have emerged in different countries, which are highly contagious, causing concern with vaccination effectiveness. So far, wearing facemasks in public continues being the most effective protocol to avoid and prevent COVID-19 spread. In this context, there is a demand of automatic facemask detection services to remind people the importance of wearing them appropriately. In this work, a performance evaluation of an AIoT system to detect correct, inappropriate, and non- facemask wearing, based on two computational models: Cloud and Edge, was conducted. Having as objective to determine which model better suites a real environment (indoor and \emph{outdoor}), based on: reliability of the detector algorithm, use of computational resources, and response time. Experimental results show that Edge-implementation got better performance in comparison to Cloud-implementation.
Abstract 247 | PDF (Español (España)) Downloads 34 PDF Downloads 22


[1] R. Aragón Nogales, I. Vargas Almanza, and M. G. Miranda Novales, “COVID-19 por SARS-CoV-2: la nueva emergencia de salud,” Revista Mexicana de Pediatría, vol. 86, pp. 213–218, 2020. [Online]. Available: https://dx.doi.org/10.35366/91871
[2] WHO, “Listings of WHO’s response to COVID-19,” World Health Organization. [Online]. Available: https://bit.ly/3mAZ6LH
[3] ——, “Vías de transmisión del virus de la COVID-19: Repercusiones para las recomendaciones relativas a las precauciones en materia de prevención y control de las infecciones.” [Online]. Available: https://bit.ly/3epu4Sq
[4] OMS, “Who coronavirus (COVID-19) dashboard,” 2021. [Online]. Available: https://bit.ly/3mDAO3r
[5] OPS, “Vacunas contra la COVID-19,” 2020. [Online]. Available: https://bit.ly/3z0JGFs
[6] H. Ritchie, E. Mathieu, L. Rodés-Guirao, C. Appel, C. Giattino, E. Ortiz-Ospina, J. Hasell, B. Macdonald, D. Beltekian, M. Roser, and et al., “Coronavirus (COVID-19) vaccinations - statistics and research,” 2020. [Online]. Available: https://bit.ly/3sEmtro
[7] C. Costa and C. Tombesi, “COVID-19: Cuánto tiempo se demoró en encontrar la vacuna para algunas enfermedades (y por qué este coronavirus es un caso histórico),” 2020. [Online]. Available: https://bbc.in/3pEV0Eh
[8] “Comparative research grant,” Anthropology News, vol. 36, no. 8, pp. 43–43, 1995. [Online]. Available: https://doi.org/10.1111/an.1995.
[9] S. S. Bibak Sareshkeh, E. Magli, and P. Dal Zovo, “Combined ict technologies for supervision of complex operations in resilient communities,” Master’s thesis, 2020. [Online]. Available: https://bit.ly/3HaioPE
[10] I. Santos-González, A. Rivero-García, J. Molina-Gil, and P. Caballero-Gil, Implementation and Analysis of Real-Time Streaming Protocols, vol. 17, no. 4, 2017. [Online]. Available: https://doi.org/10.3390/s17040846
[11] A. Nurrohman and M. Abdurohman, “High performance streaming based on H264 and real time messaging protocol (RTMP),” in 2018 6th International Conference on Information and Communication Technology (ICoICT), 2018, pp. 174–177. [Online]. Available: https://doi.org/10.1109/ICoICT.2018.8528770
[12] S. Basu, “What are video streaming codecs & container formats: Muvi live server,” 2020. [Online]. Available: https://bit.ly/3ErJPCZ
[13] J. S. Katz, “Aiot: Thoughts on artificial intelligence and the internet of things,” IEEE Internet if Things, 2019. [Online]. Available: https://bit.ly/3sBwGEZ
[14] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” ArXiv, vol. abs/1804.02767, 2018. [Online]. Available: https://bit.ly/3psJLyp
[15] A. M. Porcelli, “La inteligencia artificial y la robótica: sus dilemas sociales, éticos y jurídicos,” Derecho global. Estudios sobre derecho y justicia, vol. 6, pp. 49–105, 2020. [Online]. Available: https://doi.org/10.32870/dgedj.v6i16.286
[16] X. Jiang, T. Gao, Z. Zhu, and Y. Zhao, “Real-time face mask detection method based on YOLOv3,” Electronics, vol. 10, no. 7, p. 837, 2021. [Online]. Available: https://doi.org/10.3390/electronics10070837
[17] S. Sethi, M. Kathuria, and T. Kaushik, “Face mask detection using deep learning: An approach to reduce risk of coronavirus spread,” Journal of Biomedical Informatics, vol. 120, p. 103848, 2021. [Online]. Available: https://doi.org/10.1016/j.jbi.2021.103848
[18] D. González Dondo, J. A. Redolfi, R. G. Araguás, and D. García, “Application of deep-learning methods to real time face mask detection,” IEEE Latin America Transactions, vol. 19, no. 6, pp. 994–1001, 2021. [Online]. Available: https://bit.ly/3pw7DkM
[19] S. Sethi, M. Kathuria, and T. Kaushik, “A real-time integrated face mask detector to curtail spread of coronavirus,” Computer Modeling in Engineering & Sciences, vol. 127, no. 2, pp. 389–409, 2021. [Online]. Available: https://doi.org/10.32604/cmes.2021.014478
[20] I. Vich, “Medical masks dataset images tfrecords,” Kaggle, 2020. [Online]. Available: https://bit.ly/3er0tb8
[21] S. Ge, J. Li, Q. Ye, and Z. Luo, “MAFA,” 2018. [Online]. Available: https://bit.ly/3FBC52o
[22] S. Yadav and S. Shukla, “Analysis of k-Fold Cross-validation over hold-out validation on colossal datasets for quality classification,” in 2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016, pp. 78–83. [Online]. Available: https://doi.org/10.1109/IACC.2016.25
[23] E. Allibhai, “Holdout vs. Cross-validation in machine learning.” 2018. [Online]. Available: https://bit.ly/3z2TbE0
[24] F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He, “A comprehensive survey on transfer learning,” Proceedings of the IEEE, vol. 109, no. 1, pp. 43–76, 2021. [Online]. Available: https://doi.org/10.1109/JPROC.2020.3004555
[25] R. K. Indla, “An overview on amazon rekognition technology,” 2021.
[26] L. Herrera-Izquierdo and M. Grob, “A performance evaluation between docker container and virtual machines in cloud computing architectures,” Maskana, vol. 8, pp. 127–133, 2017. [Online]. Available: https://bit.ly/3z12oNf
[27] NVIDIA, “Jetpack sdk 4.5.1 archive,” 2021. [Online]. Available: https://bit.ly/32BxzT1
[28] Python, “Welcome to python.org,” 2021. [Online]. Available: https://bit.ly/3qqTd4Q
[29] NVIDIA, “Quickstart guide - deepstream 6.0 release documentation,” 2021. [Online]. Available: https://bit.ly/3sDTa8s
[30] ProminenceAI, “Prominenceai/deepstreamservices-library: A shared library of ondemand deepstream pipeline services for Python and C/C++,” GitHub. [Online]. Available: https://bit.ly/3pyxM2y
[31] MongoDB, “The application data platform,” MongoDB. [Online]. Available: https://bit.ly/3qrRsUL
[32] N. Craig-Wood, “Rclone syncs your files to cloud storage,” 2014. [Online]. Available: https://bit.ly/3JlPNsu
[33] Docker, “Empowering app development for developers,” 2020. [Online]. Available: https://www.docker.com/
[34] A. Thakur, C. Clauss, C. Hollinger, V. Boivin, B. Lowe, M. Schoentgen, and R. Bouckenooghe, “abhiTronix/vidgear: VidGear v0.2.3,” Oct. 2021. [Online]. Available: https://doi.org/10.5281/zenodo.5602375
[35] OpenCV. (2021) Opencv courses holiday sale. [Online]. Available: https://bit.ly/3ezvAS1
[36] Google Developers, “Firebase,” 2020. [Online]. Available: https://bit.ly/3JinCeh
[37] Pallets, “Flask web development, one drop at a time,” Pallet, 2010. [Online]. Available: https://bit.ly/3Hemy9h
[38] J. T. Mark Otto. (2021) Build fast, responsive sites with bootstrap. [Online]. Available: https://bit.ly/32Nl5rK
[39] Google. (2021) Colaboratory. Google Research. [Online]. Available: https://bit.ly/3EC3mk0
[40] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in Computer Vision – ECCV 2014, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds. Springer International Publishing, 2014, pp. 740–755. [Online]. Available: https://bit.ly/3sxpZUu
[41] M. S. Aslanpour, S. S. Gill, and A. N. Toosi, “Performance evaluation metrics for cloud, fog and edge computing: A review, taxonomy, benchmarks and standards for future research.” Internet of Things, vol. 12, p. 100273, 2020. [Online]. Available: https://doi.org/10.1016/j.iot.2020.100273
[42] M. Ashouri, F. Lorig, P. Davidsson, and R. Spalazzese, “Edge computing simulators for iot system design: An analysis of qualities and metrics,” Future Internet, vol. 11, no. 11, p. 235, 2019. [Online]. Available: https://doi.org/10.3390/fi11110235
[43] F. Oliveira-Teixeira, T. P. Donadon-Homem, and A. Pereira-Junior, “Aplicación de inteligencia artificial para monitorear el uso de mascarillas de protección,” Revista Científica General José María Córdova, vol. 19, no. 33, pp. 205–222, 2021. [Online]. Available: https://doi.org/10.21830/19006586.725