Joab Maquera Ramirez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Joab Maquera Ramirez has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Domingo Jesús Cabel Moscoso
Department of Environmental Engineering, Universidad Nacional San Luis Gonzaga, Ica 11001, Peru
1 shared publication - Edgar Eloy Carpio Vargas
Departamento Académico de Ingeniería Estadística e Informática, Universidad Nacional del Altiplano-Puno, Puno 21001, Peru
1 shared publication - Freddy Martin Marrero Saucedo
Universidad Nacional de Juliaca
1 shared publication - Hugo David Calderon Vilca
Software Engineering Department, Systems Engineering and Computer Science, National University of San Marcos, Peru
1 shared publication - Jhon Richard Huanca-Suaquita
Universidad Nacional del Juliaca,Departamento de Ingenier a Textil y de Confecciones,Juliaca,Per
1 shared publication - José Miguel Barrón-Adame
Universidad Tecnológica del Suroeste de Guanajuato
1 shared publication
Latest Publications
- 14 July 2023
- Published by Springer Nature
- p. 395-404
Using OMR for Grading MCQ-Type Answer Sheets Based on Bubble Marks
- 14 July 2023
- Published by Springer Nature
- p. 395-404
Using OMR for Grading MCQ-Type Answer Sheets Based on Bubble Marks
- Open Access
- 20 March 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (6) , 3945
Modeling Job Satisfaction of Peruvian Basic Education Teachers Using Machine Learning Techniques
Teacher job satisfaction is an important aspect of academic performance, student retention, and teacher retention. We propose to determine the predictive model of job satisfaction of basic education teachers using machine learning techniques. The original data set consisted of 15,087 instances and 942 attributes from the national survey of teachers from public and private educational institutions of regular basic education (ENDO-2018) carried out by the Ministry of Education of Peru. We used the ANOVA F-test filter and the Chi-Square filter as feature selection techniques. In the modeling phase, the logistic regression algorithms, Gradient Boosting, Random Forest, XGBoost and Decision Trees-CART were used. Among the algorithms evaluated, XGBoost and Random Forest stand out, obtaining similar results in 4 of the 8 metrics evaluated, these are: balanced accuracy of 74%, sensitivity of 74%, F1-Score of 0.48 and negative predictive value of 0.94. However, in terms of the area under the ROC curve, XGBoost scores 0.83, while Random Forest scores 0.82. These algorithms also obtain the highest true-positive values (479 instances) and lowest false-negative values (168 instances) in the confusion matrix. Economic income, satisfaction with life, self-esteem, teaching activity, relationship with the director, perception of living conditions, family relationships; health problems related to depression and satisfaction with the relationship with colleagues turned out to be the most important predictors of job satisfaction in basic education teachers.
- 20 March 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (6) , 3945
Open AccessModeling Job Satisfaction of Peruvian Basic Education Teachers Using Machine Learning Techniques
Teacher job satisfaction is an important aspect of academic performance, student retention, and teacher retention. We propose to determine the predictive model of job satisfaction of basic education teachers using machine learning techniques. The original data set consisted of 15,087 instances and 942 attributes from the national survey of teachers from public and private educational institutions of regular basic education (ENDO-2018) carried out by the Ministry of Education of Peru. We used the ANOVA F-test filter and the Chi-Square filter as feature selection techniques. In the modeling phase, the logistic regression algorithms, Gradient Boosting, Random Forest, XGBoost and Decision Trees-CART were used. Among the algorithms evaluated, XGBoost and Random Forest stand out, obtaining similar results in 4 of the 8 metrics evaluated, these are: balanced accuracy of 74%, sensitivity of 74%, F1-Score of 0.48 and negative predictive value of 0.94. However, in terms of the area under the ROC curve, XGBoost scores 0.83, while Random Forest scores 0.82. These algorithms also obtain the highest true-positive values (479 instances) and lowest false-negative values (168 instances) in the confusion matrix. Economic income, satisfaction with life, self-esteem, teaching activity, relationship with the director, perception of living conditions, family relationships; health problems related to depression and satisfaction with the relationship with colleagues turned out to be the most important predictors of job satisfaction in basic education teachers.
- Open Access
- 25 January 2022
- Published by Universidad Nacional Amazonica de Madre de Dios in Revista Amazonía Digital
- Vol. 1 (1) , e161
Plataforma virtual de evaluación y seguimiento del graduado para la acreditación universitaria
El objetivo de la investigación fue implementar y determinar la incidencia del prototipo de una plataforma virtual de evaluación y seguimiento del graduado como herramienta para la acreditación de la Escuela Profesional de Ingeniería de Sistemas e Informática (EP-ISI) de la Universidad Nacional Amazónica de Madre de Dios (UNAMAD). La investigación fue de tipo básica, diseño no experimental, nivel explicativo causal, enfoque cuantitativo, con muestra no probabilística por conveniencia, conformada por 10 estudiantes graduados; el instrumento aplicado fue la encuesta. Los resultados permitieron deducir y explicar los hechos que determinaron el desarrollo del proceso de aplicación del prototipo, obteniendo un grado de correlación de p-valor “sig. Bilateral” = 0,001<0,05; con un coeficiente de correlación de Pearson equivalente a 0,447; con una “t” aproximada equivalente a 3.523 y con un nivel de significación de 95%. El estudio concluye que aplicación del prototipo de la plataforma virtual de evaluación y seguimiento del graduado incide significativamente como herramienta para la acreditación de la EP-ISI de la UNAMAD.
- 25 January 2022
- Published by Universidad Nacional Amazonica de Madre de Dios in Revista Amazonía Digital
- Vol. 1 (1) , e161
Open AccessPlataforma virtual de evaluación y seguimiento del graduado para la acreditación universitaria
El objetivo de la investigación fue implementar y determinar la incidencia del prototipo de una plataforma virtual de evaluación y seguimiento del graduado como herramienta para la acreditación de la Escuela Profesional de Ingeniería de Sistemas e Informática (EP-ISI) de la Universidad Nacional Amazónica de Madre de Dios (UNAMAD). La investigación fue de tipo básica, diseño no experimental, nivel explicativo causal, enfoque cuantitativo, con muestra no probabilística por conveniencia, conformada por 10 estudiantes graduados; el instrumento aplicado fue la encuesta. Los resultados permitieron deducir y explicar los hechos que determinaron el desarrollo del proceso de aplicación del prototipo, obteniendo un grado de correlación de p-valor “sig. Bilateral” = 0,001<0,05; con un coeficiente de correlación de Pearson equivalente a 0,447; con una “t” aproximada equivalente a 3.523 y con un nivel de significación de 95%. El estudio concluye que aplicación del prototipo de la plataforma virtual de evaluación y seguimiento del graduado incide significativamente como herramienta para la acreditación de la EP-ISI de la UNAMAD.