Derechos de autor 2022 Investigación e Innovación en Ingenierías
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Red Neuronal Profunda (RNP) Aplicada al Análisis de Deserción Estudiantil en una Institución de Educación Superior
Corresponding Author(s) : Marco Javier Suárez Barón
Investigación e Innovación en Ingenierías,
Vol. 10 Núm. 1 (2022): Enero-Junio
Resumen
Objetivo: Presentar el diseño de una red neuronal profunda (DNN) enfocada a predecir patrones de deserción estudiantil en la Universidad UPTC de Colombia. Metodología: Aplicamos algoritmos especializados de inteligencia artificial (IA) para la implementación de la DNN específicamente utilizando una máquina de aprendizaje para tareas de clasificación y agrupación. Adicionalmente, se estructuró un dataset que contiene 17 atributos de 3000 estudiantes académicamente activos; el conjunto de datos ha sido preparado para ser entrenado como una entrada a la red neuronal. Resultados: En la investigación se analiza un modelo predictivo entrenado a través de la DNN validado por varias métricas de calidad que demuestran la confiabilidad y precisión de los resultados logrados a través del modelo. Conclusiones: Hemos centrado nuestro estudio en la aplicación de la arquitectura de redes neuronales para abordar este problema de abandono. Nuestro modelo logra no solo una alta precisión, sino también una baja tasa de falsos negativos mientras predice abandonos en el conjunto de datos recopilados.
Palabras clave
Descargar cita
Endnote/Zotero/Mendeley (RIS)BibTeX
- R.L. do Nascimento, R. Fagundes, & R.M, de Souza, Statistical Learning for Predicting School Dropout in Elementary Education: A Comparative Study. Annals of Data Science, vol 1,pp.1-28, 2021. https://doi.org/10.1007/s40745-021-00321-4
- O. Spositto, M. Etcheverry, H. Ryckeboer, & J. Bossero, “Aplicación de técnicas de mineria de datos para la evaluación del rendimiento académico y la deserción estudiantil.” Novena Conferencia Iberoamericana En Sistemas, Cibernética e Informática, CISCI, 29, 2–6. DOI: https://doi.org/10.18259/acs.2018005
- B. Castro-Montoya, C.M. Lopera-Gómez,R.D. Manrique-Hernández, & D. Gonzalez-Gómez, “A competing dropout and graduation risk survival analysis of undergraduate students at a private university in Medellín (Colombia).” Formación universitaria, vol 14(1), pp. 81-9, 2021. DOI:https://doi.org/10.4067/S0718-50062021000100081
- H. Luan, & C.Tsai. “A Review of Using Machine Learning Approaches for Precision Education”. Educational Technology & Society, vol 24(1), pp. 250–266. 2021. DOI:https:// A Review of Using Machine Learning Approaches for Precision Education .www.jstor.org/stable/26977871
- T. Cardona, E. Cudney, R. Hoerl, & J. Snyder, “Data Mining and Machine Learning Retention Models in Higher Education”. Journal of College Student Retention: Research, Theory & Practice, 2020. DOI:https://doi.org/10.1177/1521025120964920
- M. Ha & H. Ahn, "A Machine Learning-Based Vocational Training Dropout Prediction Model Considering Structured and Unstructured Data," Journal of the Korea Contents Association, Vol.19, No.1, 2019,DOI: https://doi.org/10.5392/JKCA.2019.19.01.001
- W. Cho & M. Yu, "Creating Value for Education through Big Data Analysis Education Programs", The Journal of BIGDATA, Vol.3, No.2, 2018, pp.123-130. 2020, DOI:https://doi.org/10.36498/kbigdt.2018.3.2.123
- A. Mubarak, A. Ahmed, C.Han , & M. Ibrahim. "Deep analytic model for student dropout prediction in massive open online courses." Computers & Electrical Engineering , vol 93, 2021, DOI: https://doi.org/10.1016/j.compeleceng.2021.107271
- F. Qian, et al. "CLSA: A novel deep learning model for MOOC dropout prediction." Computers & Electrical Engineering , vol 94, 2021. DOI: https://doi.org/10.1016/j.compeleceng.2021.107315
- B. Shah, & S. Margil. "A Survey on Machine Learning and Deep Learning Based Approaches for Sarcasm Identification in Social Media." Data Science and Intelligent Applications. Springer, Singapore, vol 40, 2021, pp. 247-259. DOI: https://doi.org/10.1016/j.cosrev.2021.100395
- D.J. Lemay, B. Clare, & D.Tenzin. "Comparison of learning analytics and educational data mining: A topic modeling approach." Computers and Education: Artificial Intelligence vol 2 , 2021. DOI: https://doi.org/10.1016/j.caeai.2021.100016
- A. Sarra, L. Fontanella & S. Di Zio. “Identifying students at risk of academic failure within the educational data mining framework”. Soc Indic Res, vol 146, 2019, pp. 41–60. DOI: https://doi.org/10.1007/s11205-018-1901-8
- M. Sharma, SN. Khera, PB. Sharma. “Applicability of machine learning in the measurement of emotional intelligence”. Ann Data Sci, vol 6, 2019, pp. 179–187. DOI: https://doi.org/10.1007/s40745-018-00185-1
- C. Garbin, X. Zhu & O. Marques. “Dropout vs. batch normalization: an empirical study of their impact to deep learning”. Multimed Tools Appl, vol 79, 2020, pp. 12777–12815. DOI: https://doi.org/10.1007/s11042-019-08453-9
- A. Scheunemann, T. Schnettler, J. Bobe, et al. “A longitudinal analysis of the reciprocal relationship between academic procrastination, study satisfaction, and dropout intentions in higher education”. Eur J Psychol Educ, vol 1, 2021. DOI: https://doi.org/10.1007/s10212-021-00571-z
- A. Cohen, “Analysis of student activity in web-supported courses as a tool for predicting dropout”. Education Tech Research, vol 65, 2017, pp 1285–1304, DOI: https://doi.org/10.1007/s11423-017-9524-3
- J. Zhang, M. Gao, & J. Zhang, “The learning behaviours of dropouts in MOOCs: A collective attention network perspective”, Computers & Education, vol. 167, 2021, pp. 104189, DOI: https://doi:10.1016/j.compedu.2021.104189
- M. Youssef, S. Mohammed, E. K. Hamada, and B. F. Wafaa, “A predictive approach based on efficient feature selection and learning algorithms’ competition: Case of learners’
- dropout in MOOCs”, Education and Information Technologies, vol. 24, no. 6, 2019, pp. 3591–3618, DOI: https://doi:10.1007/s10639-019-09934-y
- M. Şahin, “A Comparative Analysis of Dropout Prediction in Massive Open Online Courses”, Arabian Journal for Science and Engineering, vol. 46, no. 2, 2019, pp. 1845–1861, DOI: https://doi:10.1007/s13369-020-05127-9
- H. Camacho, D. Campos, I. Mercado, N. Cubillán, G. Castellar, “Uso de la cáscara de papa (Solanum tuberosum L.) en la clarificación del agua de la Ciénaga de Malambo,” Investigación e Innovación en Ingenierías., vol. 8, no. 1, pp. 100–111, 2020. DOI: https://doi.org/10.17081/invinno.8.1.3572
- N. Chen, J. Zhu, J. Chen, & T. Chen, “Dropout training for SVMs with data augmentation”, Frontiers of Computer Science, vol. 12, no. 4, 2018, pp. 694–713, DOI: https://doi:10.1007/s11704-018-7314-7
Referencias
R.L. do Nascimento, R. Fagundes, & R.M, de Souza, Statistical Learning for Predicting School Dropout in Elementary Education: A Comparative Study. Annals of Data Science, vol 1,pp.1-28, 2021. https://doi.org/10.1007/s40745-021-00321-4
O. Spositto, M. Etcheverry, H. Ryckeboer, & J. Bossero, “Aplicación de técnicas de mineria de datos para la evaluación del rendimiento académico y la deserción estudiantil.” Novena Conferencia Iberoamericana En Sistemas, Cibernética e Informática, CISCI, 29, 2–6. DOI: https://doi.org/10.18259/acs.2018005
B. Castro-Montoya, C.M. Lopera-Gómez,R.D. Manrique-Hernández, & D. Gonzalez-Gómez, “A competing dropout and graduation risk survival analysis of undergraduate students at a private university in Medellín (Colombia).” Formación universitaria, vol 14(1), pp. 81-9, 2021. DOI:https://doi.org/10.4067/S0718-50062021000100081
H. Luan, & C.Tsai. “A Review of Using Machine Learning Approaches for Precision Education”. Educational Technology & Society, vol 24(1), pp. 250–266. 2021. DOI:https:// A Review of Using Machine Learning Approaches for Precision Education .www.jstor.org/stable/26977871
T. Cardona, E. Cudney, R. Hoerl, & J. Snyder, “Data Mining and Machine Learning Retention Models in Higher Education”. Journal of College Student Retention: Research, Theory & Practice, 2020. DOI:https://doi.org/10.1177/1521025120964920
M. Ha & H. Ahn, "A Machine Learning-Based Vocational Training Dropout Prediction Model Considering Structured and Unstructured Data," Journal of the Korea Contents Association, Vol.19, No.1, 2019,DOI: https://doi.org/10.5392/JKCA.2019.19.01.001
W. Cho & M. Yu, "Creating Value for Education through Big Data Analysis Education Programs", The Journal of BIGDATA, Vol.3, No.2, 2018, pp.123-130. 2020, DOI:https://doi.org/10.36498/kbigdt.2018.3.2.123
A. Mubarak, A. Ahmed, C.Han , & M. Ibrahim. "Deep analytic model for student dropout prediction in massive open online courses." Computers & Electrical Engineering , vol 93, 2021, DOI: https://doi.org/10.1016/j.compeleceng.2021.107271
F. Qian, et al. "CLSA: A novel deep learning model for MOOC dropout prediction." Computers & Electrical Engineering , vol 94, 2021. DOI: https://doi.org/10.1016/j.compeleceng.2021.107315
B. Shah, & S. Margil. "A Survey on Machine Learning and Deep Learning Based Approaches for Sarcasm Identification in Social Media." Data Science and Intelligent Applications. Springer, Singapore, vol 40, 2021, pp. 247-259. DOI: https://doi.org/10.1016/j.cosrev.2021.100395
D.J. Lemay, B. Clare, & D.Tenzin. "Comparison of learning analytics and educational data mining: A topic modeling approach." Computers and Education: Artificial Intelligence vol 2 , 2021. DOI: https://doi.org/10.1016/j.caeai.2021.100016
A. Sarra, L. Fontanella & S. Di Zio. “Identifying students at risk of academic failure within the educational data mining framework”. Soc Indic Res, vol 146, 2019, pp. 41–60. DOI: https://doi.org/10.1007/s11205-018-1901-8
M. Sharma, SN. Khera, PB. Sharma. “Applicability of machine learning in the measurement of emotional intelligence”. Ann Data Sci, vol 6, 2019, pp. 179–187. DOI: https://doi.org/10.1007/s40745-018-00185-1
C. Garbin, X. Zhu & O. Marques. “Dropout vs. batch normalization: an empirical study of their impact to deep learning”. Multimed Tools Appl, vol 79, 2020, pp. 12777–12815. DOI: https://doi.org/10.1007/s11042-019-08453-9
A. Scheunemann, T. Schnettler, J. Bobe, et al. “A longitudinal analysis of the reciprocal relationship between academic procrastination, study satisfaction, and dropout intentions in higher education”. Eur J Psychol Educ, vol 1, 2021. DOI: https://doi.org/10.1007/s10212-021-00571-z
A. Cohen, “Analysis of student activity in web-supported courses as a tool for predicting dropout”. Education Tech Research, vol 65, 2017, pp 1285–1304, DOI: https://doi.org/10.1007/s11423-017-9524-3
J. Zhang, M. Gao, & J. Zhang, “The learning behaviours of dropouts in MOOCs: A collective attention network perspective”, Computers & Education, vol. 167, 2021, pp. 104189, DOI: https://doi:10.1016/j.compedu.2021.104189
M. Youssef, S. Mohammed, E. K. Hamada, and B. F. Wafaa, “A predictive approach based on efficient feature selection and learning algorithms’ competition: Case of learners’
dropout in MOOCs”, Education and Information Technologies, vol. 24, no. 6, 2019, pp. 3591–3618, DOI: https://doi:10.1007/s10639-019-09934-y
M. Şahin, “A Comparative Analysis of Dropout Prediction in Massive Open Online Courses”, Arabian Journal for Science and Engineering, vol. 46, no. 2, 2019, pp. 1845–1861, DOI: https://doi:10.1007/s13369-020-05127-9
H. Camacho, D. Campos, I. Mercado, N. Cubillán, G. Castellar, “Uso de la cáscara de papa (Solanum tuberosum L.) en la clarificación del agua de la Ciénaga de Malambo,” Investigación e Innovación en Ingenierías., vol. 8, no. 1, pp. 100–111, 2020. DOI: https://doi.org/10.17081/invinno.8.1.3572
N. Chen, J. Zhu, J. Chen, & T. Chen, “Dropout training for SVMs with data augmentation”, Frontiers of Computer Science, vol. 12, no. 4, 2018, pp. 694–713, DOI: https://doi:10.1007/s11704-018-7314-7