Comparative study between multivariate statistical techniques and arti-ficial neural networks for the optimization of the surveillance of water quality for human consumption in the Abancay health network 2022
Article Sidebar
Main Article Content
Abstract
Abstract— Currently, in most institutions, including the Abancay health network, traditional statistics are used in order to determine trends on a data set that focuses on a single variable, it is complicated to apply this type of analysis to multivariate data sets, which are those usually obtained in water quality control programs, and which exclude differences between the variables analyzed and their relationships. The objective of the study was to make a comparison between different multivariate statistical techniques and artificial neural networks, in order to relate and classify variables. To do this, two multivariate statistical techniques were chosen, principal component analysis (PCA) and discriminant analysis (DA) and two types of artificial neural networks, unsupervised learning, hebbian (RNAH), and supervised learning, multilayer perceptron (RNAPM), the type of research I used in the study will be applied research of quantitative approach, with an explanatory level of research and with a cross-sectional design. Given the comparison between the principal component analysis and the Hebbian type artificial neural network, I obtained that the neural networks were able to associate the variables better than the principal component analysis. In the second comparison between the discriminant analysis and the multilayer perceptron artificial neural network, the results were good for the discriminant analysis because it obtained 95% of correct classification, while the artificial neural network obtained 74.6%, however, due to the limitations of the discriminant analysis, I inferred that the multilayer perceptron artificial neural network is a better model to choose.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
When an author creates an article and publishes it in a journal, the copyright passes to the journal as part of the publishing agreement. Therefore, the journal becomes the owner of the rights to reproduce, distribute and sell the article. The author retains some rights, such as the right to be recognized as the creator of the article and the right to use the article for his or her own scholarly or research purposes, unless otherwise agreed in the publication agreement.
How to Cite
References
M. Greenacre, P.J.F. Groenen, T. Hastie, et al, “Principal component analysis”, Nat Rev Methods Primers vol. 2, pp. 100, 2022, https://doi.org/10.1038/s43586-022-00184-w DOI: https://doi.org/10.1038/s43586-022-00184-w
S. Mishra, U. Sarkar. et al, “Principal Component Analysis,” International Journal of Livestock Research, 2017, https://doi.org/10.5455/ijlr.20170415115235 DOI: https://doi.org/10.5455/ijlr.20170415115235
D. Dhamnetiya, MK. Goel, RP. Jha, S. Shalini, K. Bhattacharyya, “How to Perform Discriminant Analysis in Medical Research? Explained with Illustrations,” J Lab Physicians, vol. 14(4), pp. 511-520, 2022 https://doi.org/10.1055/s-0042-1747675 DOI: https://doi.org/10.1055/s-0042-1747675
R. Flóres y J. Fernández, “Las Redes Neuronales Artificiales: Fundamentos teóri-cos y aplicaciones prácticas,” La Coruña, NETBIBLO. 2008 S. L, 2008. ISBN: 978-84-9745-246-5.
M. W. Gardner and S. Dorling, “Artificial neural networks (the multilayer percep-tron)—a review of applications in the atmospheric sciences,” Atmospheric envi-ronment, vol. 32, pp. 2627–2636, 1998 DOI: https://doi.org/10.1016/S1352-2310(97)00447-0
R. Aroca, “Redes neuronales para el análisis y control de calidad del aceite de oliva virgen extra,” Universidad Complutense de Madrid, Madrid, 2019.
N. Rodríguez, “Pronóstico de Demanda de Agua potable mediante Redes Neu-ronales,” Universidad Técnica Federico Santamaria, Valparaiso, 2016.
S. Gour y M Gour, “Neural Network Approach In Water Quality Data Analysis For The River Narmada,”, Binary Journal of Data Mining & Networking, vol. 4, pp. 49-53, 2014.
S. Heddam, A. Bermad y N. Dechime, “Applications of Radial-Basis Function and Generalized Regression Neural Networks for Modeling of Coagulant Dosage in a Drinking Water-Treatment Plant: Comparative Study,” Journal of Environ-mental Engineering, vol. 137, pp. 1209-1214, New York, 2011, https://doi.org/10.1061/(ASCE)EE.1943-7870.0000435 DOI: https://doi.org/10.1061/(ASCE)EE.1943-7870.0000435
J.C. Rodríguez, “Estudio Comparativo de Técnicas Estadísticas Multivariadas versus las Redes Neuronales Artificiales en el análisis de datos de Calidad de Agua,” Pontificia Universidad Javeriana, Bogotá, 2008.
J. Valencia, “Estudio Estadístico de la Calidad de las aguas en la cuenca hidrográ-fica del río Ebro,” Universidad Politécnica de Madrid, Madrid, 2007.
R. Padilla, “Modelo de Red Neuronal para mejorar la Dosificación de Cloro Gas en la planta de tratamiento de agua potable de la municipalidad provincial de Tayacaja,” Universidad Nacional del Centro del Perú, Huancayo, Perú, 2021.
A. Peña, L. Flores del Pino, “Redes neuronales para el tratamiento de agua potable en zona de altitud del Perú,” Ambiente y Desarrollo vol. 18, pp. 109-116, 2014, https://doi.org/10.11144/Javeriana.AyD18-35.rnta DOI: https://doi.org/10.11144/Javeriana.AyD18-35.rnta
R. Álvarez, “Estadistica mutivariante y no parametrica con SPSS. Aplicacion a las ciencias de la salud,” Ediciones Diaz de Santos, S. A., Madrid, 1995. ISBN: 978-84-7978-180-4.
M. Andersson, J. Palm, “Forecasting the Stock Market - A Neural Network Ap-proach,” MÄLARDALEN UNIVERSITY, Västerås, 2009.
L. Díaz, “Estadística Multivariada: Inferencia y Métodos”, Bogota, 2007. ISBN 978-958-701-195-1.
D. Hahs-Vaughn, “Applied Multivariate Statical Concepts,” New York, 2017. ISBN: 978-1-315-81668-5.
J. Hilera. y V. Martínez. “Redes Neuronales Artificiales: Fundamentos, modelos y aplicaciones,” Madrid, 1995. ISBN: 84-7897-155-6.
P. Isasi y I. Galván, “Redes de Neuronas Artificiales: Un enfoque práctico,” Ma-drid, 2004. ISBN: 84-205-4025-0.
R. Johnson y D. Wichern, “Applied Multivariate Statistical Analysis,” vol. 6a, New Jersey, 2007. ISBN 13: 9780131877153.
J. Rodríguez, M. Ferreras y A. Núñez, “Inferencia Estadística, niveles de precisión y diseño muestral,” Madrid, 1991.
C. Sierra, “CALIDAD DEL AGUA – Evaluación y diagnóstico,” Medellín, 2011. ISBN: 978-958-8692-06-7.
Y. Vidaurre, “Aplicación de las redes neuronales artificiales para el pronóstico de la demanda de agua potable en la empresa EPSEL S.A de la ciudad de Lambaye-que,” Universidad Católica Santo Toribio de Mogrovejo, Chiclayo, Perú, 2012.
F. Murtaghl, “The Multilayer Perceptron for Discriminant Analysis: Two Exam-ples,” Springer, Berlin, Heidelberg, 1992 doi: https://doi.org/10.1007/978-3-642-46757-8_32 DOI: https://doi.org/10.1007/978-3-642-46757-8_32
L. Heazlewood, J. Walsh, M. Climstein, J. Kettunen, K. Adams, M. DeBeliso, “A Comparison of Classification Accuracy for Gender Using Neural Networks Mul-tilayer Perceptron (MLP), Radial Basis Function (RBF) Procedures Compared to Discriminant Function Analysis and Logistic Regression Based on Nine Sports Psychological Constructs to Measure Motivations to Participate in Masters Sports Competing at the 2009 World Masters Games,” Advances in Intelligent Systems and Computing, vol. 392, Springer, Cham, 2016, doi: 10.1007/978-3-319-24560-7_12 DOI: https://doi.org/10.1007/978-3-319-24560-7_12
E.I. Altman, G. Marco, F. Varetto, “Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks (the Italian experience),” Journal of Banking & Finance, vol. 18, pp. 505-529, 1994, https://doi.org/10.1016/0378-4266(94)90007-8 DOI: https://doi.org/10.1016/0378-4266(94)90007-8
K. Diamantaras, “Robust hebbian learning and noisy principal component analysis,” International Journal of Computer Mathematics, vol. 67, pp. 5-24, 1998, https://doi.org/10.1080/00207169808804649 DOI: https://doi.org/10.1080/00207169808804649