ResumenSe desarrolla una metodología para clasificar y predecir usuarios en ambientes virtuales de educación, estudiando la interacción de los estudiantes con la plataforma y su desempeño en los exámenes. Para esto se utilizaron las herramientas de aprendizaje automático, componentes principales, clusterización, lógica difusa, y el algoritmo del K vecino más cercano. La metodología relaciona los usuarios según las variables de estudio, para así implementar un análisis de clúster que identifica la formación de grupos. Finalmente utiliza un algoritmo de aprendizaje automático para clasificar los usuarios según su nivel de conocimiento. Los resultados muestran como el tiempo que un estudiante permanece en la plataforma no está relacionado con pertenecer al grupo de conocimiento alto. Se identificaron tres categorías de usuarios, aplicando la metodología Fuzzy K-means para determinar zonas de transición entre niveles de conocimiento. El algoritmo K vecino más cercano presenta los mejores resultados de predicción con un 91%. AbstractA methodology to classify and predict users in virtual education environments, studying the interaction of students with the platform and their performance in exams is proposed. For this, the machine learning tools, main components, clustering, fuzzy and the algorithm of the K nearest neighbor were used. The methodology first relates the users according to the study variables, to then implement a cluster analysis that identifies the formation of groups. Finally uses a machine learning algorithm to classify the users according to their level of knowledge. The results show how the time a student stays in the platform is not related to belonging to the high knowledge group. Three categories of users were identified, applying the Fuzzy K-means methodology to determine transition zones between levels of knowledge. The k nearest neighbor algorithm presents the best prediction results with 91%.
Electric vehicles (EVs) presence in the power grid can bring about pivotal concerns regarding their energy requirements. EVs charging behaviors can be affected by several aspects including socio-economics, psychological, seasonal among others. This work proposes a case study to analyze seasonal effects on charging patterns, using a public real-world based dataset that contains information from the aggregated load of the total charging stations of Boulder, Colorado. Our approach targets to forecast and recognize EVs demand considering seasonal factors. Principal component analysis (PCA) was used to provide a visual representation of the variables and their contribution and the correlation among them. Then, twelve classification models were trained and tested to discriminate among seasons the charging load of electric vehicles. Later, a benchmark stage is presented for regression as well as for classification results. For regression models, examined through Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE), the random Forest provides better prediction than quasi-Poisson model widely. However, it was observed that for large variations in electric vehicles’ charging load, quasi-Poisson fits better than random forest. For the classification models, evaluated through Accuracy and the Area under the Curve, the Lasso and elastic-net regularized generalized linear (GLMNET) model provided the best global performance with accuracy up to 100% when evaluated on the test dataset. The results of this work offer great insights for enhancing demand response strategies that involve PEV charging regarding charging habits across seasons.
Se propone un método para clasificar programas universitarios de ingeniería industrial, colocando especial atención a las relaciones entre las asignaturas del plan de estudio y las 12 áreas de conocimiento planteadas en el cuerpo de competencias publicado por el Instituto de Ingenieros Industriales y de Sistemas (IIES). Para la clasificación propuesta se utilizó técnicas de análisis no supervisado de datos como el Análisis de Componentes Principales (PCA) y Análisis de clúster. Como unidades de estudio se utilizan los 21 programas acreditados por alta calidad en Ingeniería Industrial en Colombia. Los resultados muestran que factores como, las acreditaciones internacionales, tamaño de las facultades de ingeniería y el perfil de universidad influye en la agrupación de los programas de estudio. La investigación permitió clasificar tres grandes componentes principales y perfiles de programas acreditados.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.