Saltar al contenido
República del Perú · Observatorio de la producción científica universitaria
OApol.org Observatorio de Inteligencia Científica Universitaria del Perú
OApol.org
Inicio Universidades Publicaciones Investigadores
Repositorios
Tesis y trabajos académicosRevistas
Indicadores
Ranking trimestralRanking por carreraObjetivos de Desarrollo SostenibleReporte OCDERed neuronal 3D
Acerca
MetodologíaPrivacidad

Gaps and Proposals for ICT use in Rural Quechua-Aymaras Higher Technological Education During COVID-19 Using Data Mining and Machine Learning

Apaza-Tarqui A.; Cayo-Velasquez N.E.; Cardenas-Marino F.C.; Ticona Arapa H.C.; Auquitias-Condori G.M.; Huanca-Suaquita J.R. · Proceedings - 9th International Symposium on Accreditation of Engineering and Computing Education, ICACIT 2023 (2023) · DOI: 10.1109/icacit59946.2023.10403726

Resumen

The Institutes of Higher Public Technological Education (IHPTE) of the rural environment in the Altiplano of the Puno region - Peru, located above 4000 meters above sea level, these students are going through the worst economic crisis due to social confinement in the context of the covid-19 pandemic, without minimum conditions to face the biosecurity measures to contain the massive contagion, submerged to educational abandonment, technological postponement and lack of basic services. The research aims to determine gaps and proposals for the appropriate use of Information Technologies (IT) in the IESTP of Nuñoa in the Quechua zone and in the IESTP of Ilave in the Aymara zone in the context of the pandemic, was designed a questionnaire which was validated with 0.637 Kaiser-Meyer-Olkin test (KMO) and significant Bartlett's test, was collected dataset of 416 students, employing Data Mining Techniques was selected the influential attributes for (Deserters), the results show that the influential attributes are: 'Economic support','Source of infection', 'Synchronous Virtual Classroom','Use of virtual system', 'Cultural identity','Dimensional Cause'; considering the reduced dataset was submitted to the classification algorithms of the machine learning with the significant metrics: Decision tree J48 (Recall 81. 5%), Naive Bayes (Recall 84.7%), Support Vector Machines (Recall 83.7%), the interpreting the leaves of the J48 tree as decision rules, with which was proposed strategies to close the gaps in access to educational technology.

Instituciones: Universidad Nacional Mayor de San Marcos; Universidad Nacional del Altiplano; Universidad Nacional de Juliaca