Analítica de datos de canales digitales, su influencia previo al establecimiento de la radio online UPEC MINDALAE

Marco Antonio  Yandún Velasteguí; Jorge Humberto  Miranda Realpe; Luis Homero    Viveros Almeida

doi:10.32645/13906925.1453

Authors

Marco Antonio Yandún Velasteguí Universidad Politécnica Estatal del Carchi https://orcid.org/0000-0001-5627-9838
Jorge Humberto Miranda Realpe Universidad Politécnica Estatal del Carchi https://orcid.org/0000-0003-1653-7059
Luis Homero Viveros Almeida Universidad Politécnica Estatal del Carchi https://orcid.org/0000-0003-3612-1798

DOI:

https://doi.org/10.32645/13906925.1453

Keywords:

Digital channels, data analysis, K-Nearest Neighbors, Machine Learning, artificial neural network

Abstract

Within the Research Project "Digital channels for research and continuous training, advanced innovation and knowledge transfer" of the State Polytechnic University of Carchi -UPEC, this document aims to perform the analysis of the data collected through a survey of UPEC academic staff and students. The original dataset is generated with the data, it is composed of 16 attributes and 1911 records that constitute the analysis material to which Automatic Learning is applied with the K-Nearest-Neighbors algorithm as an analysis methodology, in addition the trees are used. of decision, the Artificial Neural Networks and some libraries of data analysis incorporated in the Python Programming Language. As results, the Role instances (students, teacher) and the Gender of the participants are determined, to make histograms with some attributes, the confusion matrix, the correlation matrix and determine the importance of the Role and Gender fields in relation to the fields of the used dataset. As conclusions, applying the K-Nearest Neighbors algorithm for the Role field, the Accuracy (precision) of 48.3263% is determined, the Gender field of 48.3263%, on the other hand, applying the decision tree is 95.82245% compared to 55.09138% to the Gender attribute .

Downloads

Download data is not yet available.

References

Bahramian, A., Parastesh, F., Pham, V., Kapitaniak, T., Jafari, S., y Perc, M. (2021). Collective behavior in a two-layer neuronal network with time-varying chemical connections that are controlled by a Petri net. Chaos, 31 3, 033138.

Booth, J., Margetts, B.K., Bryant, W.A., Issitt, R.W., Hutchinson, C., Martin, N., y Sebire, N.J. (2021). Machine Learning Approaches to Determine Feature Importance for Predicting Infant Autopsy Outcome. Pediatric and Developmental Pathology, 24, 351 - 360.

Bravo, M., Molero, A., Rojas, J., Prieto, K., y Gómez, Á. (2017). Desarrollo de un sensor virtual de flujo usando Redes Neuronales Artificiales para Bombas de Cavidades Progresivas en el campo San Diego de Cabrutica

Canto, F.J. (2020). Eficacia de diferentes reglas hebbianas en el Aprendizaje Supervisado.

Collins, J.M., Collins, M.R., McKenzie, T., & Marino, M.J. (2021). The Role of CoLab and GAITS in Enabling the RADx Tech Program. IEEE Open Journal of Engineering in Medicine and Biology, 2, 119-124.

Estrella, Á. M. C., Pareja, E. M. D., & Ortega-Tudela, J. M. (2018). Service-learning at university: Helping schools respond to diversity using ICT, Bordon. Revista De Pedagogia, 69(3), 73-87.

Fan, A., Gardent, C., Braud, C., y Bordes, A. (2021). Augmenting Transformers with KNN-Based Composite Memory for Dialog. Transactions of the Association for Computational Linguistics, 9, 82-99.

Hagedorn, S. (2020). When sweet and cute isn't enough anymore: Solving scalability issues in Python Pandas with Grizzly. CIDR.

Harris, C.R., Millman, K.J., Walt, S.V., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N.J., Kern, R., Picus, M., Hoyer, S., Kerkwijk, M.H., Brett, M., Haldane, A., R'io, J.F., Wiebe, M., Peterson, P., G'erard-Marchant, P., Sheppard, K., Reddy, T., Weckesser, W., Abbasi, H., Gohlke, C., y Oliphant, T.E. (2020). Array programming with NumPy. Nature, 585, 357 - 362.

Hidalgo, J., Guevara, C., y Yandún, M. (2020). Generation of User Profiles in UNIX Scripts Applying Evolutionary Neural Networks. In International Conference on Applied Human Factors and Ergonomics (pp. 56-63). Springer, Cham.

Hsieh, K., Phanishayee, A., Mutlu, O., y Gibbons, P.B. (2020). The Non-IID Data Quagmire of Decentralized Machine Learning. ArXiv, abs/1910.00189.

Lemenkova, P. (2020). Python Libraries Matplotlib, Seaborn and Pandas for Visualization Geo-spatial Datasets Generated by QGIS. Social Science Research Network.

Namazkhan, M., Albers, C., y Steg, L. (2020). A decision tree method for explaining household gas consumption: The role of building characteristics, socio-demographic variables, psychological factors and household behaviour. Renewable and Sustainable Energy Reviews, 119, 109542.

Patel, H. H., y Prajapati, P. (2018). Study and analysis of decision tree based classification algorithms. International Journal of Computer Sciences and Engineering, 6(10), 74-78.

Rubiales A. (2020). Vecinos Cercanos (K-Nearest Neighbors) en Sklearn.

Sánchez-Galán, J. MACHINE LEARNING Y SUS APLICACIONES. In ACTAS DEL V CONGRESO INVESTIGACIÓN, DESARROLLO E INNOVACIÓN DE LA UNIVERSIDAD INTERNACIONAL DE CIENCIA Y TECNOLOGÍA IDI-UNICYT 2020 _ (p. 54).

Szukala, A., & Davies, I. (2020). The interconnections between research and impact in social sciences education. Journal of Social Science Education, 19(2), 1-7. doi:10.4119/jsse-3537

Vidal-Silva, C. L., Sánchez-Ortiz, A., Serrano, J., y Rubio, J. M. (2021). Experiencia académica en desarrollo rápido de sistemas de información web con Python y Django. Formación universitaria, 14(5), 85-94.