HVHenry Villarreal-Torres

Henry Villarreal-Torres

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Henry Villarreal-Torres has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Gestión de Residuos Domiciliarios y Percepción de Riesgos Naturales en Cuatro Distritos de Lima

    by Eberardo Antonio Osorio Rojas, Marlitt Florinda Naupay Vega, Aracelli Mónica Aguado Lingan, Henry Oswaldo Villarreal Torres

    La gestión de residuos sólidos domiciliarios y la exposición a riesgos naturales tienden a concentrarse en los mismos territorios periféricos de Lima Metropolitana, sin claridad sobre si ambos fenómenos han sido estudiados de manera conjunta. El objetivo de esta revisión fue identificar, sintetizar y analizar la evidencia científica y técnica sobre la gestión de residuos domiciliarios y la percepción de riesgos naturales en San Juan de Lurigancho, Comas, Puente Piedra y Callao. Se adoptó un enfoque cualitativo interpretativo, un método inductivo-analítico y un diseño no experimental documental, mediante una revisión sistemática narrativa de alcance exploratorio. Las búsquedas se realizaron en buscadores académicos de acceso abierto y en repositorios institucionales de universidades peruanas y de organismos como CENEPRED, PREDES y el Ministerio del Ambiente. Tras aplicar criterios de elegibilidad bajo el marco PEO (Población, Exposición, Resultado), se incluyeron 20 fuentes: artículos revisados por pares, tesis universitarias e informes técnicos institucionales. Los resultados muestran una brecha persistente entre la disposición ciudadana a segregar residuos y la capacidad institucional de sostenerla, además de una exposición física muy alta a peligros sísmicos, de tsunami e hidrometeorológicos; sin embargo, la percepción social de riesgo natural es escasamente documentada, y no se halló ningún estudio primario que examinara la relación entre ambos fenómenos. Se concluye que la evidencia converge en señalar a los mismos territorios como los de mayor vulnerabilidad relativa, lo que plantea investigar si la población relaciona la gestión de sus residuos con su exposición a riesgos naturales.

  • Open Access

    Generative artificial intelligence in higher education learning: A review based on academic databases

    by Daniel Andrade-Girón, William Marín-Rodriguez, Juana Sandivar-Rosas, Edgardo Carreño-Cisneros, Edgar Susanibar-Ramirez, Marcelo Zuñiga-Rojas, Julio Angeles-Morales, Henry Villarreal-Torres

    Objective. The rapid integration of Generative Artificial Intelligence (AI), especially tools like ChatGPT, into educational sectors has spurred significant academic interest. This review article provides a systematic examination of the current scholarly landscape concerning the use of ChatGPT within higher education. Design/Methodology/Approach. Drawing from a range of academic databases between 2022 and 2024, we meticulously adhere to PRISMA guidelines, evaluating a final set of 28 out of 1740 initial articles based on predetermined inclusion and exclusion criteria. Results/Discussion. Our analysis reveals diverse global contributions predominantly from Asia and identifies a prevalent quantitative research approach among the studies. We delve into the selected articles' geographical distribution, methodologies, and thematic outcomes, highlighting a notable lack of research from Latin America. The review critically assesses the validity, utility, and time optimization aspects of ChatGPT in educational settings, uncovering a positive impact on student learning and time management. However, we pinpoint a significant gap in rigorous experimental research, underscoring the need for studies with random sampling and controlled settings to enhance the external validity of findings. Additionally, we call attention to the ethical considerations and the necessity for higher education institutions to adapt teaching methodologies to incorporate AI effectively. Conclusion. The article concludes with recommendations for future research to address the identified gaps and optimize the educational use of generative AI technologies like ChatGPT.


  • Open Access

    Modelo de clasificación para la deserción estudiantil en las universidades públicas del Perú

    by Henry Villarreal-Torres, Julio Ángeles-Morales, William Marín-Rodriguez, Jenny Cano-Mejía

    Las tecnologías de información y comunicación cumplen un rol relevante en los diferentes campos del conocimiento, actualmente existe mayor capacidad para identificar patrones y anomalías en los datos de una organización utilizando la inteligencia artificial; el estudio tuvo como objetivo desarrollar un modelo de clasificación para la deserción estudiantil aplicando aprendizaje automático con el método autoML del framework H2O.ai, se ha tenido en cuenta la dimensionalidad de las características socioeconómicas y académicas. La metodología empleada fue de tipo predictivo y diseño no experimental, observacional y prospectivo; para ello, se aplicó un cuestionario de 20 ítems a 237 estudiantes de la Escuela de Posgrado matriculados en los programas de maestrías en educación. La investigación tuvo como resultado un modelo de aprendizaje automático supervisado, máquina de refuerzo de gradiente, para clasificar la deserción estudiantil, logrando así identificar los principales factores asociados que influyen en la deserción, obteniendo un coeficiente Gini del 92.20%, AUC del 96.10% y un LogLoss del 24.24% representando un modelo con desempeño eficiente. Se concluye que el modelo es apropiado por sus métricas de rendimiento, ofreciendo ventajas como trabajar con datos desequilibrados, validación cruzada y realizar predicciones en tiempo real.


  • Open Access

    Comparative analysis of performance of AutoML algorithms: Classification model of payment arrears in students of a private university

    by Henry Villarreal-Torres, Julio Ángeles-Morales, Jenny Cano-Mejía, Carmen Mejía-Murillo, Gumercindo Flores-Reyes, Oscar Cruz-Cruz, Manuel Urcia-Quispe, Manuel Palomino-Márquez, Miguel Ángel Solar-Jara, Reyna Escobedo-Zarzosa

    The impact of artificial intelligence in our society is important due to the innovation of processes through data science to know the academic and sociodemographic factors that contribute to late payments in university students, to identify them and make timely decisions for implementing prevention and correction programs, avoiding student dropout due to this economic problem, and ensuring success in their education in a meaningful and focused way. In this sense, the research aims to compare the performance metrics of classification models for late payments in students of a private university by using AutoML algorithms from various existing platforms and solutions such as AutoKeras, AutoGluon, HyperOPT, MLJar, and H2O in a data set consisting of 8,495 records and the application of data balancing techniques. From the implementation and execution of various algorithms, similar metrics have been obtained based on the parameters and optimization functions used automatically by each tool, providing better performance to the H2O platform through the Stacked Ensemble algorithm with metrics accuracy = 0.778. F1 = 0.870, recall = 0.904 and precision = 0.839. The research can be extended to other contexts or areas of knowledge due to the growing interest in automated machine learning, providing researchers with a valuable tool in data science without the need for deep knowledge.


  • Open Access

    Predicting Student Dropout based on Machine Learning and Deep Learning: A Systematic Review

    by Daniel Andrade-Girón, Juana Sandivar-Rosas, William Marín-Rodriguez, Edgar Susanibar-Ramirez, Eliseo Toro-Dextre, Jose Ausejo-Sanchez, Henry Villarreal-Torres, Julio Angeles-Morales

    Student dropout is one of the most complex challenges facing the education system worldwide. In order to evaluate the success of Machine Learning and Deep Learning algorithms in predicting student dropout, a systematic review was conducted. The search was carried out in several electronic bibliographic databases, including Scopus, IEEE, and Web of Science, covering up to June 2023, having 246 articles as search reports. Exclusion criteria, such as review articles, editorials, letters, and comments, were established. The final review included 23 studies in which performance metrics such as accuracy/precision, sensitivity/recall, specificity, and area under the curve (AUC) were evaluated. In addition, aspects related to study modality, training, testing strategy, cross-validation, and confounding matrix were considered. The review results revealed that the most used Machine Learning algorithm was Random Forest, present in 21.73% of the studies; this algorithm obtained an accuracy of 99% in the prediction of student dropout, higher than all the algorithms used in the total number of studies reviewed.


  • Open Access

    Payment behavior model for students at a private university in Peru

    by Henry Villarreal Torres, Julio Ángeles Morales, William Joel Marín Rodriguez, Daniel Andrade Girón, Edgardo Carreño Cisneros

    With the enactment of Law No. 29947, “Law for the Protection of the Family Economy”, students use the educational service with the payment of tuition, demonstrating a poor payment culture, failing to pay tuition until the beginning of the next semester. This motivates the university to present a state of illiquidity. The objective of the research was to develop a payment behavior classification model for students of a private university in Peru, with the purpose of predicting delinquency and compliance with payment commitments, through the implementation of strategies to improve the quality of the economic collection process. The methodology presents a research component of technological type, of propositional level, incremental innovation, the data collection was of retrospective type; with a synchronous temporal scope, because it was carried out in a short period of time, less than a year, the study population consisted of 8495 enrolled undergraduate students. The results show a classification model to predict payment behavior, using the H2O.ai platform and the R programming language, the data were obtained from computer systems, using the CRISP-DM methodology used in data science solutions. The datasets for training, validation and testing correspond to 70 %, 15 % and 15 %; obtaining the GBM Grid classification model whose performance metrics are AUC of 0,6272, AUCPR of 0,8751 and logLoss equivalent to 0,4577.

  • Open Access

    Classification model for student attrition in a Peru public university

    by Henry Villarreal Torres, William Marín Rodriguez, Julio Ángeles Morales, Jenny Cano Mejía, Carmen Mejía Murillo

    Information and communication technologies are playing a very important role in the different fields of knowledge; there is an increasing ability to identify patterns in the data of an organization; in this context, the study aimed to develop a classification model for student dropout by applying the autoML method of the H2Oai framework, taking into account socioeconomic and academic characteristics of students in order for authorities to make decisions in a timely manner. The methodology was technological, propositional level, incremental innovation, temporal scope, synchronous; the data collection was prospective, a 20-item questionnaire was applied to 237 graduate students of master’s degree programs in education. The research resulted in a supervised automatic learning model, Gradient Boosting Machine (GBM), to classify student desertion, identifying the main associated factors that influence desertion, obtaining a Gini coefficient of 92,20 %, AUC of 96,10 % and a LogLoss of 24,24 %.

  • Open Access

    Random and systematic errors in pairwise computer programming: A systematic review

    by Daniel Andrade Girón, Juana Sandivar Rosas, William Marín-Rodriguez, Edgardo Carreño Cisneros, Ernesto Diaz-Ronceros, Henry Villarreal-Torres

    In this article, a systematic review is carried out to identify random and systematic errors in studies on computer programming in pairs in higher education students. Methodologically, we applied the fundamentals of the PRISMA statement. One thousand one hundred eighty articles were selected from the Scopus, Web of Science, and IEEE Xplore databases. After a filtering process, the final sample was 23 23 articles. The results showed that couple programming has positive effects. The existence of both random and systematic errors was observed, which questions the internal and external validity. Further research is needed to establish the benefits of couple programming more precisely.

  • Open Access

    Comparison of Machine Learning Algorithms for Predicting Patients with Suspected COVID-19

    by Daniel Andrade-Girón, Edgardo Carreño-Cisneros, Cecilia Mejía-Domínguez, William Marín-Rodriguez, Henry Villarreal-Torres

    The coronavirus disease (COVID-19) outbreak has infected millions of people, causing a high death rate worldwide. Patients suspected of having COVID-19 are transferred to different health facilities, which has caused a saturation in care, for which it is necessary to have a prediction model to classify patients at high risk of clinical deterioration. The objective of the research was to compare classification algorithms based on automatic learning machines, for the prediction of clinical diagnosis in patients with COVID-19. 1000 records of patients with suspected SARS-CoV-2 infection who were admitted by the emergency service in health establishments in Peru were collected. After pre-processing the data and engineering the attributes, a sample of 700 records was determined. Models were designed and algorithms were compared: Logistic Regression, Support Vector Machine, Nearest Neighbors, Decision Tree, Random Forest, and Navie Bayes. The evaluation of the results of each algorithm was carried out using Accuracy, precision, sensitivity and Chohen's Kappa to know the degree of agreement between the prediction by the learning machine and the results of reality, that is, to what extent both results agree in their measurement. The algorithm that presented the best results was the Support Vector Machine and Random Forest, which predicted the patients with an accuracy of 97 %, and Cohen's Kappa of 0,95, with figures higher than the other models evaluated


  • Open Access

    Gestión de Tecnología de Información para universidades peruanas aplicando computación en la nube

    by Henry O. Villarreal-Torres, William J. Marín-Rodriguez, Julio C. Angeles-Morales, Jenny E. Cano-Mejía

    El propósito de la investigación fue integrar las buenas prácticas y normas internacionales relacionadas con las tecnologías de información para definir un marco de gestión y adoptar el modelo de computación en la nube en universidades peruanas con la finalidad de garantizar eficientemente la continuidad, disponibilidad y capacidad de los servicios de tecnologías de información bajo el esquema pago por uso. La investigación estuvo enmarcada en el aspecto tecnológico, en virtud de la propuesta realizada para solucionar un problema real presentado en el sistema universitario; por cuanto se logró definir el marco de gestión para la adopción del modelo de computación en la nube, la misma que contempla cinco dimensiones: negocio, personas, tecnología, información y seguridad, contemplado en cinco categorías: planificación, implementación, monitoreo, soporte y evaluación, los cuales están definidos en 24 procesos, roles y productos de trabajo.; el que será implementado mediante el ciclo de desarrollo. Se concluye que el modelo de computación en la nube, permitirá a las instituciones involucradas ventajas competitivas y generación de valor.