En el presente artículo se planteó como objetivo buscar la detección del uso de la mascarilla en las personas mediante un programa de visión artificial, aplicando el modelo de redes neuronales, donde se identifica si la persona lleva la mascarilla, así buscando un aporte para la mitigación y reducción de casos de contagio del Covid-19. Además, se utiliza el lenguaje Python junto con Frameworks como TensorFlow para la ejecución de las redes neuronales entrenadas y librerías como Keras y Sklearn, utilizadas principalmente en el proceso de aprendizaje. Parte de la metodología se enfocó en la descarga y clonación de materiales, creación y entrenamiento de la red neuronal, la preparación de Anaconda junto con Jupyter Notebook para la verificación del sistema. En los resultados encontramos que la programación detectó correctamente mediante un medio local, usando el Google Colab, para lo cual se tomó como referencia un banco de imágenes preestablecido y se realizó el reconocimiento. Por otra parte, se utiliza Jupyter Notebook para la detección mediante video en tiempo real. Por último, se concluye que se logró detectar dos tipos de imágenes de personas que están usando o no mascarilla con las variables “mask” y “no mask”, mediante el entrenamiento de las redes neurales con un batch size de 8, steps de 50 y epochs de 25, con un resultado de classification loss de 0.2120.
In recent months, the Peruvian Society of Industrial Engineering (SPII) has presented a series of problems in its logistics, financial and sales processes. This research was developed with the objective of implementing quality processes to solve the management problems of the Peruvian Society of Industrial Engineering (SPII), with the purpose of generating value by eliminating the root causes identified. The quality process was defined as the dependent variable and the solution of the company's management problems as the independent variable. The study was conducted under an exploratory and descriptive approach, for which an analysis method was used. In the methodology; On the one hand, tools such as: Process Operations Diagram (POD), Quality Function Deployment (QFD), Six Sigma and Failure Mode and Effect Analysis (FMEA) were used; On the other hand, for statistical tests the Ishikawa, Indicator Matrix, Pareto diagram, measures of central tendency, histograms and control charts developed in Minitab were used. A loss of S/. 368,388.40 was obtained in the sum of the 4 root causes, identifying that RQ3 and RQ4 have the greatest impact (74%), followed by RQ2 (18%) and ending with RQ1 (8%). The results of the proposed toolsmanaged to reduce the overall loss to S/. 233,847.70; due to the fact that the indicators of each loss were optimized with the Six Sigma tools, obtaining a benefit equivalent to S/. 134,540.70. In conclusion, the application of the proposed quality tools and processes, manage to control the value processes of the company, and therefore reduce the respective losses of each problem.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.